Endoscopy

Autonomous artificial intelligence (AI) can achieve similar accuracy to AI-assisted humans (AI-H) in the optical diagnosis of diminutive colorectal polyps, while providing greater alignment with pathology-based surveillance intervals, based on a randomized controlled trial.

These findings suggest that autonomous AI may one day replace histologic assessment of diminutive polyps, reported lead author Roupen Djinbachian, MD, of the Montreal University Hospital Research Center, Montreal, Quebec, Canada, and colleagues.Optical diagnosis of diminutive colorectal polyps has been proposed as a cost-effective alternative to histologic diagnosis, but its implementation in general clinical practice has been hindered by endoscopists’ concerns about incorrect diagnoses, the investigators wrote in Gastroenterology.“AI-based systems (CADx) have been proposed as a solution to these barriers to implementation, with studies showing high adherence to Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) thresholds when using AI-H,” they wrote. “However, the efficacy and safety of autonomous AI-based diagnostic platforms have not yet been evaluated.”

To address this knowledge gap, Dr. Djinbachian and colleagues conducted a randomized controlled noninferiority trial involving 467 patients, all of whom underwent elective colonoscopies at a single academic institution.

Participants were randomly assigned to one of two groups. The first group received an optical diagnosis of diminutive (1-5 mm) colorectal polyps using an autonomous AI-based CADx system without any human input. The second group had diagnoses performed by endoscopists who used AI-H to make their optical diagnoses.

The primary outcome was the accuracy of optical diagnosis compared with the gold standard of histologic evaluation. Secondarily, the investigators explored associations between pathology-based surveillance intervals and various measures of accuracy, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

The results showed that the accuracy of optical diagnosis for diminutive polyps was similar between the two groups, supporting noninferiority. Autonomous AI achieved an accuracy rate of 77.2%, while the AI-H group had an accuracy of 72.1%, which was not statistically significant (P = .86).

But when it came to pathology-based surveillance intervals, autonomous AI showed a clear advantage; the autonomous AI system achieved a 91.5% agreement rate, compared with 82.1% for the AI-H group (P = .016).

“These findings indicate that autonomous AI not only matches but also surpasses AI-H in accuracy for determining surveillance intervals,” the investigators wrote, noting that this finding highlights the “complexities of human interaction with AI modules where human intervention could lead to worse outcomes.”

Further analysis revealed that the sensitivity of autonomous AI for identifying adenomas was 84.8%, slightly higher than the 83.6% sensitivity of the AI-H group. Specificity was 64.4% for autonomous AI vs 63.8% for AI-H. While PPV was higher in the autonomous AI group (85.6%), compared with the AI-H group (78.6%), NPV was lower for autonomous AI than AI-H (63.0% vs 71.0%).

Dr. Djinbachian and colleagues suggested that future research should focus on larger, multicenter trials to validate these findings and further explore the integration of autonomous AI systems in clinical practice. They also noted that improving AI algorithms to accurately diagnose sessile serrated lesions could enhance the overall effectiveness of AI-based optical diagnosis.

“The performance of autonomous AI in accurately diagnosing diminutive polyps and determining appropriate surveillance intervals suggests that it could play a crucial role in streamlining colorectal cancer screening processes, reducing the burden on pathologists, and potentially lowering healthcare costs,” the investigators concluded.The study was supported by Fujifilm, which had no role in the study design or data analysis. Dr. von Renteln reported additional research funding from Vantage and Fujifilm.

Autonomous artificial intelligence (AI) can achieve similar accuracy to AI-assisted humans (AI-H) in the optical diagnosis of diminutive colorectal polyps, while providing greater alignment with pathology-based surveillance intervals, based on a randomized controlled trial.

These findings suggest that autonomous AI may one day replace histologic assessment of diminutive polyps, reported lead author Roupen Djinbachian, MD, of the Montreal University Hospital Research Center, Montreal, Quebec, Canada, and colleagues.Optical diagnosis of diminutive colorectal polyps has been proposed as a cost-effective alternative to histologic diagnosis, but its implementation in general clinical practice has been hindered by endoscopists’ concerns about incorrect diagnoses, the investigators wrote in Gastroenterology.“AI-based systems (CADx) have been proposed as a solution to these barriers to implementation, with studies showing high adherence to Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) thresholds when using AI-H,” they wrote. “However, the efficacy and safety of autonomous AI-based diagnostic platforms have not yet been evaluated.”

To address this knowledge gap, Dr. Djinbachian and colleagues conducted a randomized controlled noninferiority trial involving 467 patients, all of whom underwent elective colonoscopies at a single academic institution.

Participants were randomly assigned to one of two groups. The first group received an optical diagnosis of diminutive (1-5 mm) colorectal polyps using an autonomous AI-based CADx system without any human input. The second group had diagnoses performed by endoscopists who used AI-H to make their optical diagnoses.

The primary outcome was the accuracy of optical diagnosis compared with the gold standard of histologic evaluation. Secondarily, the investigators explored associations between pathology-based surveillance intervals and various measures of accuracy, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

The results showed that the accuracy of optical diagnosis for diminutive polyps was similar between the two groups, supporting noninferiority. Autonomous AI achieved an accuracy rate of 77.2%, while the AI-H group had an accuracy of 72.1%, which was not statistically significant (P = .86).

But when it came to pathology-based surveillance intervals, autonomous AI showed a clear advantage; the autonomous AI system achieved a 91.5% agreement rate, compared with 82.1% for the AI-H group (P = .016).

“These findings indicate that autonomous AI not only matches but also surpasses AI-H in accuracy for determining surveillance intervals,” the investigators wrote, noting that this finding highlights the “complexities of human interaction with AI modules where human intervention could lead to worse outcomes.”

Further analysis revealed that the sensitivity of autonomous AI for identifying adenomas was 84.8%, slightly higher than the 83.6% sensitivity of the AI-H group. Specificity was 64.4% for autonomous AI vs 63.8% for AI-H. While PPV was higher in the autonomous AI group (85.6%), compared with the AI-H group (78.6%), NPV was lower for autonomous AI than AI-H (63.0% vs 71.0%).

Dr. Djinbachian and colleagues suggested that future research should focus on larger, multicenter trials to validate these findings and further explore the integration of autonomous AI systems in clinical practice. They also noted that improving AI algorithms to accurately diagnose sessile serrated lesions could enhance the overall effectiveness of AI-based optical diagnosis.

“The performance of autonomous AI in accurately diagnosing diminutive polyps and determining appropriate surveillance intervals suggests that it could play a crucial role in streamlining colorectal cancer screening processes, reducing the burden on pathologists, and potentially lowering healthcare costs,” the investigators concluded.The study was supported by Fujifilm, which had no role in the study design or data analysis. Dr. von Renteln reported additional research funding from Vantage and Fujifilm.

Autonomous artificial intelligence (AI) can achieve similar accuracy to AI-assisted humans (AI-H) in the optical diagnosis of diminutive colorectal polyps, while providing greater alignment with pathology-based surveillance intervals, based on a randomized controlled trial.

These findings suggest that autonomous AI may one day replace histologic assessment of diminutive polyps, reported lead author Roupen Djinbachian, MD, of the Montreal University Hospital Research Center, Montreal, Quebec, Canada, and colleagues.Optical diagnosis of diminutive colorectal polyps has been proposed as a cost-effective alternative to histologic diagnosis, but its implementation in general clinical practice has been hindered by endoscopists’ concerns about incorrect diagnoses, the investigators wrote in Gastroenterology.“AI-based systems (CADx) have been proposed as a solution to these barriers to implementation, with studies showing high adherence to Preservation and Incorporation of Valuable Endoscopic Innovations (PIVI) thresholds when using AI-H,” they wrote. “However, the efficacy and safety of autonomous AI-based diagnostic platforms have not yet been evaluated.”

To address this knowledge gap, Dr. Djinbachian and colleagues conducted a randomized controlled noninferiority trial involving 467 patients, all of whom underwent elective colonoscopies at a single academic institution.

Participants were randomly assigned to one of two groups. The first group received an optical diagnosis of diminutive (1-5 mm) colorectal polyps using an autonomous AI-based CADx system without any human input. The second group had diagnoses performed by endoscopists who used AI-H to make their optical diagnoses.

The primary outcome was the accuracy of optical diagnosis compared with the gold standard of histologic evaluation. Secondarily, the investigators explored associations between pathology-based surveillance intervals and various measures of accuracy, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

The results showed that the accuracy of optical diagnosis for diminutive polyps was similar between the two groups, supporting noninferiority. Autonomous AI achieved an accuracy rate of 77.2%, while the AI-H group had an accuracy of 72.1%, which was not statistically significant (P = .86).

But when it came to pathology-based surveillance intervals, autonomous AI showed a clear advantage; the autonomous AI system achieved a 91.5% agreement rate, compared with 82.1% for the AI-H group (P = .016).

“These findings indicate that autonomous AI not only matches but also surpasses AI-H in accuracy for determining surveillance intervals,” the investigators wrote, noting that this finding highlights the “complexities of human interaction with AI modules where human intervention could lead to worse outcomes.”

Further analysis revealed that the sensitivity of autonomous AI for identifying adenomas was 84.8%, slightly higher than the 83.6% sensitivity of the AI-H group. Specificity was 64.4% for autonomous AI vs 63.8% for AI-H. While PPV was higher in the autonomous AI group (85.6%), compared with the AI-H group (78.6%), NPV was lower for autonomous AI than AI-H (63.0% vs 71.0%).

Dr. Djinbachian and colleagues suggested that future research should focus on larger, multicenter trials to validate these findings and further explore the integration of autonomous AI systems in clinical practice. They also noted that improving AI algorithms to accurately diagnose sessile serrated lesions could enhance the overall effectiveness of AI-based optical diagnosis.

“The performance of autonomous AI in accurately diagnosing diminutive polyps and determining appropriate surveillance intervals suggests that it could play a crucial role in streamlining colorectal cancer screening processes, reducing the burden on pathologists, and potentially lowering healthcare costs,” the investigators concluded.The study was supported by Fujifilm, which had no role in the study design or data analysis. Dr. von Renteln reported additional research funding from Vantage and Fujifilm.

gastufrimarabobireloswaclonitholiphiwufratroleprukistuhunonuwrewophophutholonirecipragaceclafrostonapadoprikashigaspichehesigoclufreruspuprosherajuticricheproswuprepichuslaheslauucevestiwriprihanurucuslowistestuduwraspeswotronawobunucronidul

In this issue:

1. Eosinophilic Gastrointestinal Diseases: Beyond EoE
   Nirmala Gonsalves, MD, AGAF, FACG
2. The Changing Face of IBD: Beyond the Western World
   Gilaad G. Kaplan, MD, MPH, AGAF; Paulo Kotze, MD, MS, PhD; Siew C. Ng, MBBS, PhD, AGAF
3. Role of Non-invasive Biomarkers in the Evaluation and Management of MASLD
   Julia J. Wattacheril, MD, MPH
4. The Emerging Role of Liquid Biopsy in the Diagnosis and Management of CRC
   David Lieberman, MD, AGAF
5. Cannabinoids and Digestive Disorders
   Jami A. Kinnucan, MD, AGAF, FACG
6. AI and Machine Learning in IBD: Promising Applications and Remaining Challenges
   Shirley Cohen-Mekelburg, MD, MS
7. Simulation-Based Training in Endoscopy: Benefits and Challenges
   Richa Shukla, MD
8. Fluid Management in Acute Pancreatitis
   Jorge D. Machicado, MD, MPH

gastufrimarabobireloswaclonitholiphiwufratroleprukistuhunonuwrewophophutholonirecipragaceclafrostonapadoprikashigaspichehesigoclufreruspuprosherajuticricheproswuprepichuslaheslauucevestiwriprihanurucuslowistestuduwraspeswotronawobunucronidul

In this issue:

1. Eosinophilic Gastrointestinal Diseases: Beyond EoE
   Nirmala Gonsalves, MD, AGAF, FACG
2. The Changing Face of IBD: Beyond the Western World
   Gilaad G. Kaplan, MD, MPH, AGAF; Paulo Kotze, MD, MS, PhD; Siew C. Ng, MBBS, PhD, AGAF
3. Role of Non-invasive Biomarkers in the Evaluation and Management of MASLD
   Julia J. Wattacheril, MD, MPH
4. The Emerging Role of Liquid Biopsy in the Diagnosis and Management of CRC
   David Lieberman, MD, AGAF
5. Cannabinoids and Digestive Disorders
   Jami A. Kinnucan, MD, AGAF, FACG
6. AI and Machine Learning in IBD: Promising Applications and Remaining Challenges
   Shirley Cohen-Mekelburg, MD, MS
7. Simulation-Based Training in Endoscopy: Benefits and Challenges
   Richa Shukla, MD
8. Fluid Management in Acute Pancreatitis
   Jorge D. Machicado, MD, MPH

gastufrimarabobireloswaclonitholiphiwufratroleprukistuhunonuwrewophophutholonirecipragaceclafrostonapadoprikashigaspichehesigoclufreruspuprosherajuticricheproswuprepichuslaheslauucevestiwriprihanurucuslowistestuduwraspeswotronawobunucronidul

In this issue:

1. Eosinophilic Gastrointestinal Diseases: Beyond EoE
   Nirmala Gonsalves, MD, AGAF, FACG
2. The Changing Face of IBD: Beyond the Western World
   Gilaad G. Kaplan, MD, MPH, AGAF; Paulo Kotze, MD, MS, PhD; Siew C. Ng, MBBS, PhD, AGAF
3. Role of Non-invasive Biomarkers in the Evaluation and Management of MASLD
   Julia J. Wattacheril, MD, MPH
4. The Emerging Role of Liquid Biopsy in the Diagnosis and Management of CRC
   David Lieberman, MD, AGAF
5. Cannabinoids and Digestive Disorders
   Jami A. Kinnucan, MD, AGAF, FACG
6. AI and Machine Learning in IBD: Promising Applications and Remaining Challenges
   Shirley Cohen-Mekelburg, MD, MS
7. Simulation-Based Training in Endoscopy: Benefits and Challenges
   Richa Shukla, MD
8. Fluid Management in Acute Pancreatitis
   Jorge D. Machicado, MD, MPH

Click here to view more from Gastroenterology Data Trends 2024

Click here to view more from Gastroenterology Data Trends 2024

Click here to view more from Gastroenterology Data Trends 2024

WASHINGTON — As part of a quality improvement initiative, gastroenterologists at the University of Texas Health Science Center reduced endoscopic waste by using a single tool rather than multiple tools during colonoscopies, according to a study presented at Digestive Disease Week^® (DDW).

After discussing environmentally conscious practices during regular meetings, the odds of gastroenterologists using a single tool — either biopsy forceps or a snare — compared with multiple disposable tools was three times higher.

“The burden of waste is massive, with GI being the third-largest waste generator in healthcare. The number of procedures is increasing, which just means more waste, and we have to look at ways to reduce it,” said lead author Prateek Harne, MD, a gastroenterology fellow at the University of Texas Health Science Center.

Overall, the healthcare industry generates 8.5% of U.S. greenhouse emissions, with more than 70% coming from used instruments and supplies, he said. GI endoscopy generates 85,000 metric tons of carbon dioxide waste annually. That waste stems from high case volumes, patient travel, the decontamination process, and single-use devices.

After seeing the waste at his institution, Dr. Harne wondered how to reduce single-use device and nonrenewable waste, particularly the tools used during polypectomies. He and colleagues decided to focus on single-tool use and collected data about the tools used during screening colonoscopies for 8 weeks before an intervention.

As part of the intervention, Dr. Harne and colleagues discussed green endoscopy initiatives supported by North American gastrointestinal societies during a journal club meeting with gastroenterology faculty. They also discussed potential strategies to reduce waste in day-to-day practice during a monthly business meeting, particularly focused on being mindful of using tools during polypectomies. The meetings occurred 3 days apart.

Then Dr. Harne and colleagues collected data regarding tool use during screening colonoscopies, looking at the number and type of instruments used. Before the meetings, 210 patients underwent colonoscopies, including 34% that required no intervention, 32% that required one tool, and 33% that required multiple tools.

After the meetings, 112 patients underwent colonoscopies, including 34% that required no tools, 49% that used one tool, and 17% that used multiple tools. This represented a 17% increase in the use of one tool (P < .01) and a 16% decrease in the use of multiple tools (P < .01). The odds of using a single tool compared with multiple tools was 2.98, and there was a statistically significant increase in uptake of snare for polypectomy.

The study was limited by being at a single center, having a small sample size, and using a short-term assessment. At the same time, the findings show potential for a low-cost solution through open discussion with gastroenterologists.

“Sir Isaac Newton had two holes for two different sized cats in his home, but all of his cats ended up using the bigger hole,” Dr. Harne said in his conclusion. “Maybe we can do the same for polypectomies and use only the tools that we need.”

In an interview, Dr. Harne noted he spoke with the janitorial staff at his institution to learn more about endoscopy unit waste, including how much is recycled, how much is incinerated, and who handles the waste. He recognized the work being done in Europe to understand and reduce endoscopic waste and hopes U.S. groups begin to implement more measures.

“Gastroenterologists and their teams need to be more cognizant of the impact we have on the environment,” Dr. Harne said. “As our study shows, if providers are aware that they can and should use fewer tools to get the same results, it can lead to a statistically significant impact, just with a friendly reminder to reduce use.”

After the presentation, Dr. Harne discussed other shifts with conference attendees, such as not opening or unwrapping tools until needed during a procedure.

“Small changes could have big impacts. Everything that we do in QI [quality improvement] is meant to help patients and the environment,” said Amanda Krouse, MD, a research fellow at the University of California, San Diego, who was a moderator of the DDW session on GI fellow–directed QI projects.

In an interview, Alana Persaud, MD, an endoscopy fellow at Geisinger Medical Center in Danville, Pennsylvania, also a moderator of the session, said: “Ultimately, the medical services we’re providing are for the longevity of our patients, but at the same time, we don’t want it to be to the detriment of the environment, so paying attention to green endoscopy when we can preserve and use more discretion with our devices is worth it so we can all thrive together.”

Dr. Harne did not have any disclosures.

WASHINGTON — As part of a quality improvement initiative, gastroenterologists at the University of Texas Health Science Center reduced endoscopic waste by using a single tool rather than multiple tools during colonoscopies, according to a study presented at Digestive Disease Week^® (DDW).

After discussing environmentally conscious practices during regular meetings, the odds of gastroenterologists using a single tool — either biopsy forceps or a snare — compared with multiple disposable tools was three times higher.

“The burden of waste is massive, with GI being the third-largest waste generator in healthcare. The number of procedures is increasing, which just means more waste, and we have to look at ways to reduce it,” said lead author Prateek Harne, MD, a gastroenterology fellow at the University of Texas Health Science Center.

Overall, the healthcare industry generates 8.5% of U.S. greenhouse emissions, with more than 70% coming from used instruments and supplies, he said. GI endoscopy generates 85,000 metric tons of carbon dioxide waste annually. That waste stems from high case volumes, patient travel, the decontamination process, and single-use devices.

After seeing the waste at his institution, Dr. Harne wondered how to reduce single-use device and nonrenewable waste, particularly the tools used during polypectomies. He and colleagues decided to focus on single-tool use and collected data about the tools used during screening colonoscopies for 8 weeks before an intervention.

As part of the intervention, Dr. Harne and colleagues discussed green endoscopy initiatives supported by North American gastrointestinal societies during a journal club meeting with gastroenterology faculty. They also discussed potential strategies to reduce waste in day-to-day practice during a monthly business meeting, particularly focused on being mindful of using tools during polypectomies. The meetings occurred 3 days apart.

Then Dr. Harne and colleagues collected data regarding tool use during screening colonoscopies, looking at the number and type of instruments used. Before the meetings, 210 patients underwent colonoscopies, including 34% that required no intervention, 32% that required one tool, and 33% that required multiple tools.

After the meetings, 112 patients underwent colonoscopies, including 34% that required no tools, 49% that used one tool, and 17% that used multiple tools. This represented a 17% increase in the use of one tool (P < .01) and a 16% decrease in the use of multiple tools (P < .01). The odds of using a single tool compared with multiple tools was 2.98, and there was a statistically significant increase in uptake of snare for polypectomy.

The study was limited by being at a single center, having a small sample size, and using a short-term assessment. At the same time, the findings show potential for a low-cost solution through open discussion with gastroenterologists.

“Sir Isaac Newton had two holes for two different sized cats in his home, but all of his cats ended up using the bigger hole,” Dr. Harne said in his conclusion. “Maybe we can do the same for polypectomies and use only the tools that we need.”

In an interview, Dr. Harne noted he spoke with the janitorial staff at his institution to learn more about endoscopy unit waste, including how much is recycled, how much is incinerated, and who handles the waste. He recognized the work being done in Europe to understand and reduce endoscopic waste and hopes U.S. groups begin to implement more measures.

“Gastroenterologists and their teams need to be more cognizant of the impact we have on the environment,” Dr. Harne said. “As our study shows, if providers are aware that they can and should use fewer tools to get the same results, it can lead to a statistically significant impact, just with a friendly reminder to reduce use.”

After the presentation, Dr. Harne discussed other shifts with conference attendees, such as not opening or unwrapping tools until needed during a procedure.

“Small changes could have big impacts. Everything that we do in QI [quality improvement] is meant to help patients and the environment,” said Amanda Krouse, MD, a research fellow at the University of California, San Diego, who was a moderator of the DDW session on GI fellow–directed QI projects.

In an interview, Alana Persaud, MD, an endoscopy fellow at Geisinger Medical Center in Danville, Pennsylvania, also a moderator of the session, said: “Ultimately, the medical services we’re providing are for the longevity of our patients, but at the same time, we don’t want it to be to the detriment of the environment, so paying attention to green endoscopy when we can preserve and use more discretion with our devices is worth it so we can all thrive together.”

Dr. Harne did not have any disclosures.

WASHINGTON — As part of a quality improvement initiative, gastroenterologists at the University of Texas Health Science Center reduced endoscopic waste by using a single tool rather than multiple tools during colonoscopies, according to a study presented at Digestive Disease Week^® (DDW).

After discussing environmentally conscious practices during regular meetings, the odds of gastroenterologists using a single tool — either biopsy forceps or a snare — compared with multiple disposable tools was three times higher.

“The burden of waste is massive, with GI being the third-largest waste generator in healthcare. The number of procedures is increasing, which just means more waste, and we have to look at ways to reduce it,” said lead author Prateek Harne, MD, a gastroenterology fellow at the University of Texas Health Science Center.

Overall, the healthcare industry generates 8.5% of U.S. greenhouse emissions, with more than 70% coming from used instruments and supplies, he said. GI endoscopy generates 85,000 metric tons of carbon dioxide waste annually. That waste stems from high case volumes, patient travel, the decontamination process, and single-use devices.

After seeing the waste at his institution, Dr. Harne wondered how to reduce single-use device and nonrenewable waste, particularly the tools used during polypectomies. He and colleagues decided to focus on single-tool use and collected data about the tools used during screening colonoscopies for 8 weeks before an intervention.

As part of the intervention, Dr. Harne and colleagues discussed green endoscopy initiatives supported by North American gastrointestinal societies during a journal club meeting with gastroenterology faculty. They also discussed potential strategies to reduce waste in day-to-day practice during a monthly business meeting, particularly focused on being mindful of using tools during polypectomies. The meetings occurred 3 days apart.

Then Dr. Harne and colleagues collected data regarding tool use during screening colonoscopies, looking at the number and type of instruments used. Before the meetings, 210 patients underwent colonoscopies, including 34% that required no intervention, 32% that required one tool, and 33% that required multiple tools.

After the meetings, 112 patients underwent colonoscopies, including 34% that required no tools, 49% that used one tool, and 17% that used multiple tools. This represented a 17% increase in the use of one tool (P < .01) and a 16% decrease in the use of multiple tools (P < .01). The odds of using a single tool compared with multiple tools was 2.98, and there was a statistically significant increase in uptake of snare for polypectomy.

The study was limited by being at a single center, having a small sample size, and using a short-term assessment. At the same time, the findings show potential for a low-cost solution through open discussion with gastroenterologists.

“Sir Isaac Newton had two holes for two different sized cats in his home, but all of his cats ended up using the bigger hole,” Dr. Harne said in his conclusion. “Maybe we can do the same for polypectomies and use only the tools that we need.”

In an interview, Dr. Harne noted he spoke with the janitorial staff at his institution to learn more about endoscopy unit waste, including how much is recycled, how much is incinerated, and who handles the waste. He recognized the work being done in Europe to understand and reduce endoscopic waste and hopes U.S. groups begin to implement more measures.

“Gastroenterologists and their teams need to be more cognizant of the impact we have on the environment,” Dr. Harne said. “As our study shows, if providers are aware that they can and should use fewer tools to get the same results, it can lead to a statistically significant impact, just with a friendly reminder to reduce use.”

After the presentation, Dr. Harne discussed other shifts with conference attendees, such as not opening or unwrapping tools until needed during a procedure.

“Small changes could have big impacts. Everything that we do in QI [quality improvement] is meant to help patients and the environment,” said Amanda Krouse, MD, a research fellow at the University of California, San Diego, who was a moderator of the DDW session on GI fellow–directed QI projects.

In an interview, Alana Persaud, MD, an endoscopy fellow at Geisinger Medical Center in Danville, Pennsylvania, also a moderator of the session, said: “Ultimately, the medical services we’re providing are for the longevity of our patients, but at the same time, we don’t want it to be to the detriment of the environment, so paying attention to green endoscopy when we can preserve and use more discretion with our devices is worth it so we can all thrive together.”

Dr. Harne did not have any disclosures.

Introduction

Barrett’s esophagus (BE) is characterized by the replacement of squamous epithelium by columnar metaplasia of the distal esophagus (>1 cm length). It is a precancerous condition, with 3%-5% of patients with BE developing esophageal adenocarcinoma (EAC) in their lifetime. EAC is one of the cancers with high morbidity and mortality (5-year survival < 20%), and its incidence has been on the rise. Studies examining the natural history of BE have demonstrated that the progression happens through a metaplasia-dysplasia-neoplasia sequence. Therefore, early detection of BE and timely management to prevent progression to EAC is crucial.

Grades of Dysplasia

The current gold standard for the diagnosis of BE neoplasia includes a high-quality endoscopic evaluation and biopsies. Biopsies should be obtained from any visible lesions (nodules, ulcers) followed by a random 4-quadrant fashion (Seattle protocol) interval of the entire length of the BE segment. It is essential to pay attention to the results of the biopsy that have been obtained since it will not only determine the surveillance interval but is crucial in planning any necessary endoscopic therapy. The possible results of the biopsy and its implications are:

• No intestinal metaplasia (IM): This would rule out Barrett’s esophagus and no further surveillance would be necessary. A recent population-based study of over 1 million patients showed a 55% and 61% reduced risk of upper gastrointestinal (UGI) cancer and deaths respectively after a negative endoscopy.¹
• Intestinal metaplasia with no dysplasia (non-dysplastic BE): Biopsies confirm presence of intestinal metaplasia in the biopsies without any evidence of dysplasia. While the rate of progression to EAC is low (0.07%-0.25%), it is not absent and thus surveillance would be indicated. Current guidelines suggest repeating an endoscopy with biopsy in 5 years if the length of BE is < 3 cm or 3 years if length of BE ≥ 3 cm.²
• Indeterminate for dysplasia (BE-IND): Biopsies confirm IM but are not able to definitively rule out dysplasia. This can be seen in about 4%-8% of the biopsies obtained. The progression rates to EAC are reported to be comparable or lower to low-grade dysplasia (LGD), so the current recommendation is to intensify acid reduction therapy and repeat endoscopy in 6 months. If repeat endoscopy downgrades to non-dysplastic, then can follow surveillance according to NDBE protocol; otherwise recommend continuing surveillance every 12 months.
• Low-grade dysplasia (BE-LGD): Biopsies confirm IM but also show tightly packed overlapping basal nuclei with hyperchromasia and irregular contours, basal stratification of nuclei, and diminished goblet and columnar cell mucus. There is significant inter-observer variability reported,³ and thus the slides must be reviewed by a second pathologist with experience in BE to confirm the findings. Once confirmed, based on risk factors such as presence of multifocal LGD, persistence of LGD, presence of visible lesions, etc., the patient can be offered Barrett’s endoscopic therapy (BET) or undergo continued surveillance. The decision of pursuing one or the other would be dependent on patient preference and shared decision-making between the patient and the provider.
• High-grade dysplasia (BE-HGD): Biopsies confirm IM with cells showing greater degree of cytologic and architectural alterations of dysplasia than LGD but without overt neoplastic features. Over 40% of the patients would progress to EAC and thus the current recommendations would be to recommend BET in these patients.⁴
• Esophageal adenocarcinoma (EAC): Biopsies demonstrate neoplasia. If the neoplastic changes are limited to the mucosa (T1a) on endoscopic ultrasound or cross-sectional imaging, then BET is suggested. If there is involvement of submucosa, then depending on the depth of invasion, absence of high-risk features (poor differentiation, lymphovascular invasion), BET can be considered as an alternative to esophagectomy.

Lesion Detection on Endoscopy

Data from large population-based studies with at least 3 years of follow-up reported that 58%-66% of EAC detected during endoscopy were diagnosed within 1 year of an index Barrett’s esophagus screening endoscopy, or post-endoscopy Barrett’s neoplasia, and were considered likely to have been missed during index endoscopy.⁵ This underscores the importance of careful and systematic endoscopic examination during an upper endoscopy.

Studies have also demonstrated that longer examination time was associated with significantly higher detection of HGD/EAC.^6,7 Careful examination of the tubular esophagus and gastroesophageal junction (GEJ) should be performed in forward and retroflexed views looking for any subtle areas of nodularity, loop distortion, variability in vascular patterns, mucosal changes concerning for dysplasia or neoplasia. Use of high-definition white light endoscopy (HD-WLE) and virtual chromoendoscopy techniques such as narrow banding imaging (NBI) or blue laser imaging (BLI) are currently recommended in the guidelines.² Spray chromoendoscopy using acetic acid can also be utilized. Another exciting development is the use of artificial intelligence (AI) in detecting and diagnosing BE associated lesions and neoplasia.
 

Barrett’s Endoscopic Therapy (BET)

Patients with visible lesions, dysplasia, or early EAC are candidates for BET (Table 1).

167527_table_web.jpg

BET involves resective and ablative modalities. The resective modalities include endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) and are the modalities of choice for nodular or raised lesions.

EMR involves endoscopic resection of abnormal mucosa using either lift-assisted technique or multi-band ligation (Figure 1).

167527_figure_web.jpg

ESD, on the other hand, involves submucosal dissection and perimeter resection of the lesion, thus providing the advantage of an en-bloc resection. In a recent randomized controlled trial (RCT) of 40 patients undergoing ESD vs EMR for HGD/EAC, ESD was better for curative resection (R0) (58%) compared with EMR (12%); however, the remission rates at 3 months were comparable with two perforations reported in the ESD group while there were no complications in the EMR group.⁸

There is an apparent learning curve when it comes to these advanced techniques, and with more experience, we are seeing comparable results for both these modalities. However, given the complexity and time required for the procedure, current practices typically involve preserving ESD for lesions > 2 cm, those having a likelihood of cancer in the superficial submucosa, or those that EMR cannot remove due to underlying fibrosis or post-EMR recurrence.

Srinivasan_Sachin_KS_web.jpg

Barrett’s Refractory to Endoscopic Therapy

Failure of BET is defined as persistent columnar lined epithelium (intestinal metaplasia) with inadequate response, after adequate attempts at endoscopic ablation therapy (after resection) with at least four ablation sessions.¹³ If encountered, special attention must be given to check compliance with proton pump inhibitors (PPIs), previous incomplete resection, and presence of large hiatal hernia. If CE-IM is not achieved after multiple sessions, change of ablative modality is typically considered. In addition, careful examination for visible lesions should be performed and even if a small one is noted, this should be first resected prior to application of any ablative therapy.

Sharma_Prateek_KS_2024_web.jpg

Currently there are no guideline recommendations regarding the preference of one endoscopic modality over another or consideration of potential endoscopic or surgical fundoplication. These modalities primarily rely on technologies available at an institution and the preference of a provider based on their training and experience. Most studies indicate 1-3 sessions (~ 3 months apart) of ablative treatment before achieving CE-IM.
 

Success and Adverse Events of BET

In a recent real-world study of over 27,000 patients with dysplastic BE, 5295 underwent BET. Analysis showed that patients with HGD/EAC who had BET had a significantly lower 3-year mortality (HGD: RR, 0.59; 95%CI, 0.49-0.71; EAC: RR, 0.53; 95% CI, 0.44-0.65) compared with those who did not undergo BET. Esophageal strictures were the most common adverse event and were noted in 6.5%, followed by chest pain (1.8%), upper GI bleeding (0.47%), and esophageal perforation (0.2%).¹⁴

In general, adverse events can be divided into immediate and delayed adverse events. Immediate adverse events typically involve bleeding and perforation that can occur during or shortly after the procedure. These are reported at higher rates with resective modalities compared with ablative therapies. Standard endoscopic techniques involving coagulation grasper or clips can be used to achieve hemostasis. Endoscopic suturing devices offer the ability to contain any perforation. The need for surgical intervention is small and limited to adverse events not detected during the procedure.

Delayed adverse events such as stricture and stenosis are higher for resective modalities (up to 30%), especially when involving more significant than 75% of the esophageal circumference. Post-procedural pain/dysphagia is most common after ablative therapies. Dysphagia reported after any endoscopic therapy should be promptly evaluated, and sequential dilation until the goal esophageal lumen is achieved should be performed every 2-4 weeks.
 

Recurrences and Surveillance After BET

What is established is that recurrences can occur and may be subtle, therefore detailed endoscopic surveillance is required. In a prospective study, recurrence rates of 15%-16% for IM and 3%-5% for any dysplasia were reported, with the majority being in the first 2 years after achieving CE-IM.¹⁵ A systematic review of 21 studies looking at the location of recurrences suggested that the majority (56%) occur in the distal esophagus. Of those that occur in the esophagus, about 80% of them were in the distal 2 cm of the esophagus and only 50% of the recurrences were visible recurrences, thus reiterating the importance of meticulous examination and systematic biopsies.¹⁶

On the contrary, a recent single-center study of 217 patients who had achieved CE-IM with 5.5 years of follow-up demonstrated a 26% and 8% recurrence of IM and dysplasia, respectively. One hundred percent of the recurrence in the esophagus was reported as visible.¹⁷ Therefore, follow-up endoscopy surveillance protocol after CE-IM should still involve meticulous examination, biopsy of visible lesions, and systematic biopsies for non-visible lesions from the original BE segment, similar to those patients who have not needed BET.

Current guidelines based on expert consensus and evidence recommend surveillance after CE-IM based on original most advanced histology:²

1. LGD: 1 year, 3 years, and every 2 years after that.

2. HGD/EAC: 3 months, 6 months, 12 months, and annually after that.

There is no clear guideline on when to stop surveillance since the longest available follow-up is around 10 years, and recurrences are still detected. A potential surveillance endpoint may be based on age and comorbidities, especially those that would preclude a patient from being a candidate for BET.
 

When Should a Patient Be Referred?

BE patients with visible lesions and/or dysplastic changes in the biopsy who would require BET should be considered for referral to high-volume centers. Studies have shown higher success for CE-IM and lower rates of adverse events and recurrences in these patients managed at expert centers. The presence of a multidisciplinary team involving pathologists, surgeons, and oncologists is critical and offers a timely opportunity in case of need for a high-risk patient.

Conclusion

BE is a precursor to EAC, with rising incidence and poor 5-year survival. Endoscopic diagnosis is the gold standard and requires a high-quality examination and biopsies. Based on histopathology, a systematic surveillance and BET plan should be performed to achieve CE-IM in patients with dysplasia. Once CE-IM is achieved, regular surveillance should be performed with careful attention to recurrences and complications from the BET modalities.

Dr. Srinivasan and Dr. Sharma are based at the University of Kansas Medical Center, Kansas City, Kansas, and the Kansas City Veterans Affairs Medical Center, Kansas City, Missouri. Dr. Srinivasan has no relevant disclosures. Dr. Sharma disclosed research grants from ERBE, Ironwood Pharmaceuticals, Olympus, and Medtronic. He has served as a consultant for Takeda, Samsung Bioepis, Olympus, and Lumendi, and reports other funding from Medtronic, Fujifilm Medical Systems USA, and Salix.

References

1. Holmberg D, et al. Incidence and mortality in upper gastrointestinal cancer after negative endoscopy for gastroesophageal reflux disease. Gastroenterology. 2022;162(2):431-438.e4.

2. Shaheen NJ, et al. Diagnosis and management of Barrett’s esophagus: An updated ACG guideline. Am J Gastroenterol. 2022 Apr;117(4):559-587.

3. Pech O, et al. Inter-observer variability in the diagnosis of low-grade dysplasia in pathologists: A comparison between experienced and inexperienced pathologists. Gastrointest Endosc. 2006 Apr;63(5):AB130.

4. Krishnamoorthi R, et al. Factors associated with progression of Barrett’s esophagus: A systematic review and meta-analysis. Clin Gastroenterol Hepatol. 2018 Jul;16(7):1046-1055.e8.

5. Visrodia K, et al. Magnitude of missed esophageal adenocarcinoma after Barrett’s esophagus diagnosis: A systematic review and meta-analysis. Gastroenterology. 2016 Mar;150(3):599-607.e7; quiz e14-5.

6. Perisetti A, Sharma P. Tips for improving the identification of neoplastic visible lesions in Barrett’s esophagus. Gastrointest Endosc. 2023 Feb;97(2):248-250.

7. Gupta N, et al. Longer inspection time is associated with increased detection of high-grade dysplasia and esophageal adenocarcinoma in Barrett’s esophagus. Gastrointest Endosc. 2012 Sep;76(3):531-538.

8. Terheggen G, et al. A randomised trial of endoscopic submucosal dissection versus endoscopic mucosal resection for early Barrett’s neoplasia. Gut. 2017 May;66(5):783-793.

9. Wolfson P, et al. Endoscopic eradication therapy for Barrett’s esophagus-related neoplasia: A final 10-year report from the UK National HALO Radiofrequency Ablation Registry. Gastrointest Endosc. 2022 Aug;96(2):223-233.

10. Rösch T, et al. 1151 Multicenter feasibility study of combined injection and argon plasma coagulation (hybrid-APC) in the ablation therapy of neoplastic Barrett esophagus. Gastrointest Endosc. 2017;85(5):AB154.

11. Knabe M, et al. Radiofrequency ablation versus hybrid argon plasma coagulation in Barrett’s esophagus: A prospective randomised trial. Surg Endosc. 2023;37(10):7803-7811.

12. Van Munster SN, et al. Radiofrequency vapor ablation for Barrett’s esophagus: Feasibility, safety, and proof of concept in a stepwise study with in vitro, animal, and the first in-human application. Endoscopy. 2021 Nov;53(11):1162-1168.

13. Emura F, et al. Rio de Janeiro global consensus on landmarks, definitions, and classifications in Barrett’s esophagus: World Endoscopy Organization Delphi study. Gastroenterology. 2022 Jul;163(1):84-96.e2.

14. Singh RR, et al. Real-world evidence of safety and effectiveness of Barrett’s endoscopic therapy. Gastrointest Endosc. 2023 Aug;98(2):155-161.e1.

15. Wani S, et al. Recurrence Is rare following complete eradication of intestinal metaplasia in patients with Barrett’s esophagus and peaks at 18 months. Clin Gastroenterol Hepatol. 2020 Oct;18(11):2609-2617.e2.

16. Duvvuri A, et al. Mo1273 Location and pattern of recurrences in patients with Barrett’s esophagus after endoscopic therapy: A systematic review and critical analysis of the published literature. Gastrointest Endosc. 2020;91(6):AB410-1.

17. He T, et al. Location and appearance of dysplastic Barrett’s esophagus recurrence after endoscopic eradication therapy: No additional yield from random biopsy sampling neosquamous mucosa. Gastrointest Endosc. 2023 Nov;98(5):722-732.

Introduction

Barrett’s esophagus (BE) is characterized by the replacement of squamous epithelium by columnar metaplasia of the distal esophagus (>1 cm length). It is a precancerous condition, with 3%-5% of patients with BE developing esophageal adenocarcinoma (EAC) in their lifetime. EAC is one of the cancers with high morbidity and mortality (5-year survival < 20%), and its incidence has been on the rise. Studies examining the natural history of BE have demonstrated that the progression happens through a metaplasia-dysplasia-neoplasia sequence. Therefore, early detection of BE and timely management to prevent progression to EAC is crucial.

Grades of Dysplasia

The current gold standard for the diagnosis of BE neoplasia includes a high-quality endoscopic evaluation and biopsies. Biopsies should be obtained from any visible lesions (nodules, ulcers) followed by a random 4-quadrant fashion (Seattle protocol) interval of the entire length of the BE segment. It is essential to pay attention to the results of the biopsy that have been obtained since it will not only determine the surveillance interval but is crucial in planning any necessary endoscopic therapy. The possible results of the biopsy and its implications are:

• No intestinal metaplasia (IM): This would rule out Barrett’s esophagus and no further surveillance would be necessary. A recent population-based study of over 1 million patients showed a 55% and 61% reduced risk of upper gastrointestinal (UGI) cancer and deaths respectively after a negative endoscopy.¹
• Intestinal metaplasia with no dysplasia (non-dysplastic BE): Biopsies confirm presence of intestinal metaplasia in the biopsies without any evidence of dysplasia. While the rate of progression to EAC is low (0.07%-0.25%), it is not absent and thus surveillance would be indicated. Current guidelines suggest repeating an endoscopy with biopsy in 5 years if the length of BE is < 3 cm or 3 years if length of BE ≥ 3 cm.²
• Indeterminate for dysplasia (BE-IND): Biopsies confirm IM but are not able to definitively rule out dysplasia. This can be seen in about 4%-8% of the biopsies obtained. The progression rates to EAC are reported to be comparable or lower to low-grade dysplasia (LGD), so the current recommendation is to intensify acid reduction therapy and repeat endoscopy in 6 months. If repeat endoscopy downgrades to non-dysplastic, then can follow surveillance according to NDBE protocol; otherwise recommend continuing surveillance every 12 months.
• Low-grade dysplasia (BE-LGD): Biopsies confirm IM but also show tightly packed overlapping basal nuclei with hyperchromasia and irregular contours, basal stratification of nuclei, and diminished goblet and columnar cell mucus. There is significant inter-observer variability reported,³ and thus the slides must be reviewed by a second pathologist with experience in BE to confirm the findings. Once confirmed, based on risk factors such as presence of multifocal LGD, persistence of LGD, presence of visible lesions, etc., the patient can be offered Barrett’s endoscopic therapy (BET) or undergo continued surveillance. The decision of pursuing one or the other would be dependent on patient preference and shared decision-making between the patient and the provider.
• High-grade dysplasia (BE-HGD): Biopsies confirm IM with cells showing greater degree of cytologic and architectural alterations of dysplasia than LGD but without overt neoplastic features. Over 40% of the patients would progress to EAC and thus the current recommendations would be to recommend BET in these patients.⁴
• Esophageal adenocarcinoma (EAC): Biopsies demonstrate neoplasia. If the neoplastic changes are limited to the mucosa (T1a) on endoscopic ultrasound or cross-sectional imaging, then BET is suggested. If there is involvement of submucosa, then depending on the depth of invasion, absence of high-risk features (poor differentiation, lymphovascular invasion), BET can be considered as an alternative to esophagectomy.

Lesion Detection on Endoscopy

Data from large population-based studies with at least 3 years of follow-up reported that 58%-66% of EAC detected during endoscopy were diagnosed within 1 year of an index Barrett’s esophagus screening endoscopy, or post-endoscopy Barrett’s neoplasia, and were considered likely to have been missed during index endoscopy.⁵ This underscores the importance of careful and systematic endoscopic examination during an upper endoscopy.

Studies have also demonstrated that longer examination time was associated with significantly higher detection of HGD/EAC.^6,7 Careful examination of the tubular esophagus and gastroesophageal junction (GEJ) should be performed in forward and retroflexed views looking for any subtle areas of nodularity, loop distortion, variability in vascular patterns, mucosal changes concerning for dysplasia or neoplasia. Use of high-definition white light endoscopy (HD-WLE) and virtual chromoendoscopy techniques such as narrow banding imaging (NBI) or blue laser imaging (BLI) are currently recommended in the guidelines.² Spray chromoendoscopy using acetic acid can also be utilized. Another exciting development is the use of artificial intelligence (AI) in detecting and diagnosing BE associated lesions and neoplasia.
 

Barrett’s Endoscopic Therapy (BET)

Patients with visible lesions, dysplasia, or early EAC are candidates for BET (Table 1).

167527_table_web.jpg

BET involves resective and ablative modalities. The resective modalities include endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) and are the modalities of choice for nodular or raised lesions.

EMR involves endoscopic resection of abnormal mucosa using either lift-assisted technique or multi-band ligation (Figure 1).

167527_figure_web.jpg

ESD, on the other hand, involves submucosal dissection and perimeter resection of the lesion, thus providing the advantage of an en-bloc resection. In a recent randomized controlled trial (RCT) of 40 patients undergoing ESD vs EMR for HGD/EAC, ESD was better for curative resection (R0) (58%) compared with EMR (12%); however, the remission rates at 3 months were comparable with two perforations reported in the ESD group while there were no complications in the EMR group.⁸

There is an apparent learning curve when it comes to these advanced techniques, and with more experience, we are seeing comparable results for both these modalities. However, given the complexity and time required for the procedure, current practices typically involve preserving ESD for lesions > 2 cm, those having a likelihood of cancer in the superficial submucosa, or those that EMR cannot remove due to underlying fibrosis or post-EMR recurrence.

Srinivasan_Sachin_KS_web.jpg

Barrett’s Refractory to Endoscopic Therapy

Failure of BET is defined as persistent columnar lined epithelium (intestinal metaplasia) with inadequate response, after adequate attempts at endoscopic ablation therapy (after resection) with at least four ablation sessions.¹³ If encountered, special attention must be given to check compliance with proton pump inhibitors (PPIs), previous incomplete resection, and presence of large hiatal hernia. If CE-IM is not achieved after multiple sessions, change of ablative modality is typically considered. In addition, careful examination for visible lesions should be performed and even if a small one is noted, this should be first resected prior to application of any ablative therapy.

Sharma_Prateek_KS_2024_web.jpg

Currently there are no guideline recommendations regarding the preference of one endoscopic modality over another or consideration of potential endoscopic or surgical fundoplication. These modalities primarily rely on technologies available at an institution and the preference of a provider based on their training and experience. Most studies indicate 1-3 sessions (~ 3 months apart) of ablative treatment before achieving CE-IM.
 

Success and Adverse Events of BET

In a recent real-world study of over 27,000 patients with dysplastic BE, 5295 underwent BET. Analysis showed that patients with HGD/EAC who had BET had a significantly lower 3-year mortality (HGD: RR, 0.59; 95%CI, 0.49-0.71; EAC: RR, 0.53; 95% CI, 0.44-0.65) compared with those who did not undergo BET. Esophageal strictures were the most common adverse event and were noted in 6.5%, followed by chest pain (1.8%), upper GI bleeding (0.47%), and esophageal perforation (0.2%).¹⁴

In general, adverse events can be divided into immediate and delayed adverse events. Immediate adverse events typically involve bleeding and perforation that can occur during or shortly after the procedure. These are reported at higher rates with resective modalities compared with ablative therapies. Standard endoscopic techniques involving coagulation grasper or clips can be used to achieve hemostasis. Endoscopic suturing devices offer the ability to contain any perforation. The need for surgical intervention is small and limited to adverse events not detected during the procedure.

Delayed adverse events such as stricture and stenosis are higher for resective modalities (up to 30%), especially when involving more significant than 75% of the esophageal circumference. Post-procedural pain/dysphagia is most common after ablative therapies. Dysphagia reported after any endoscopic therapy should be promptly evaluated, and sequential dilation until the goal esophageal lumen is achieved should be performed every 2-4 weeks.
 

Recurrences and Surveillance After BET

What is established is that recurrences can occur and may be subtle, therefore detailed endoscopic surveillance is required. In a prospective study, recurrence rates of 15%-16% for IM and 3%-5% for any dysplasia were reported, with the majority being in the first 2 years after achieving CE-IM.¹⁵ A systematic review of 21 studies looking at the location of recurrences suggested that the majority (56%) occur in the distal esophagus. Of those that occur in the esophagus, about 80% of them were in the distal 2 cm of the esophagus and only 50% of the recurrences were visible recurrences, thus reiterating the importance of meticulous examination and systematic biopsies.¹⁶

On the contrary, a recent single-center study of 217 patients who had achieved CE-IM with 5.5 years of follow-up demonstrated a 26% and 8% recurrence of IM and dysplasia, respectively. One hundred percent of the recurrence in the esophagus was reported as visible.¹⁷ Therefore, follow-up endoscopy surveillance protocol after CE-IM should still involve meticulous examination, biopsy of visible lesions, and systematic biopsies for non-visible lesions from the original BE segment, similar to those patients who have not needed BET.

Current guidelines based on expert consensus and evidence recommend surveillance after CE-IM based on original most advanced histology:²

1. LGD: 1 year, 3 years, and every 2 years after that.

2. HGD/EAC: 3 months, 6 months, 12 months, and annually after that.

There is no clear guideline on when to stop surveillance since the longest available follow-up is around 10 years, and recurrences are still detected. A potential surveillance endpoint may be based on age and comorbidities, especially those that would preclude a patient from being a candidate for BET.
 

When Should a Patient Be Referred?

BE patients with visible lesions and/or dysplastic changes in the biopsy who would require BET should be considered for referral to high-volume centers. Studies have shown higher success for CE-IM and lower rates of adverse events and recurrences in these patients managed at expert centers. The presence of a multidisciplinary team involving pathologists, surgeons, and oncologists is critical and offers a timely opportunity in case of need for a high-risk patient.

Conclusion

BE is a precursor to EAC, with rising incidence and poor 5-year survival. Endoscopic diagnosis is the gold standard and requires a high-quality examination and biopsies. Based on histopathology, a systematic surveillance and BET plan should be performed to achieve CE-IM in patients with dysplasia. Once CE-IM is achieved, regular surveillance should be performed with careful attention to recurrences and complications from the BET modalities.

Dr. Srinivasan and Dr. Sharma are based at the University of Kansas Medical Center, Kansas City, Kansas, and the Kansas City Veterans Affairs Medical Center, Kansas City, Missouri. Dr. Srinivasan has no relevant disclosures. Dr. Sharma disclosed research grants from ERBE, Ironwood Pharmaceuticals, Olympus, and Medtronic. He has served as a consultant for Takeda, Samsung Bioepis, Olympus, and Lumendi, and reports other funding from Medtronic, Fujifilm Medical Systems USA, and Salix.

References

1. Holmberg D, et al. Incidence and mortality in upper gastrointestinal cancer after negative endoscopy for gastroesophageal reflux disease. Gastroenterology. 2022;162(2):431-438.e4.

2. Shaheen NJ, et al. Diagnosis and management of Barrett’s esophagus: An updated ACG guideline. Am J Gastroenterol. 2022 Apr;117(4):559-587.

3. Pech O, et al. Inter-observer variability in the diagnosis of low-grade dysplasia in pathologists: A comparison between experienced and inexperienced pathologists. Gastrointest Endosc. 2006 Apr;63(5):AB130.

4. Krishnamoorthi R, et al. Factors associated with progression of Barrett’s esophagus: A systematic review and meta-analysis. Clin Gastroenterol Hepatol. 2018 Jul;16(7):1046-1055.e8.

5. Visrodia K, et al. Magnitude of missed esophageal adenocarcinoma after Barrett’s esophagus diagnosis: A systematic review and meta-analysis. Gastroenterology. 2016 Mar;150(3):599-607.e7; quiz e14-5.

6. Perisetti A, Sharma P. Tips for improving the identification of neoplastic visible lesions in Barrett’s esophagus. Gastrointest Endosc. 2023 Feb;97(2):248-250.

7. Gupta N, et al. Longer inspection time is associated with increased detection of high-grade dysplasia and esophageal adenocarcinoma in Barrett’s esophagus. Gastrointest Endosc. 2012 Sep;76(3):531-538.

8. Terheggen G, et al. A randomised trial of endoscopic submucosal dissection versus endoscopic mucosal resection for early Barrett’s neoplasia. Gut. 2017 May;66(5):783-793.

9. Wolfson P, et al. Endoscopic eradication therapy for Barrett’s esophagus-related neoplasia: A final 10-year report from the UK National HALO Radiofrequency Ablation Registry. Gastrointest Endosc. 2022 Aug;96(2):223-233.

10. Rösch T, et al. 1151 Multicenter feasibility study of combined injection and argon plasma coagulation (hybrid-APC) in the ablation therapy of neoplastic Barrett esophagus. Gastrointest Endosc. 2017;85(5):AB154.

11. Knabe M, et al. Radiofrequency ablation versus hybrid argon plasma coagulation in Barrett’s esophagus: A prospective randomised trial. Surg Endosc. 2023;37(10):7803-7811.

12. Van Munster SN, et al. Radiofrequency vapor ablation for Barrett’s esophagus: Feasibility, safety, and proof of concept in a stepwise study with in vitro, animal, and the first in-human application. Endoscopy. 2021 Nov;53(11):1162-1168.

13. Emura F, et al. Rio de Janeiro global consensus on landmarks, definitions, and classifications in Barrett’s esophagus: World Endoscopy Organization Delphi study. Gastroenterology. 2022 Jul;163(1):84-96.e2.

14. Singh RR, et al. Real-world evidence of safety and effectiveness of Barrett’s endoscopic therapy. Gastrointest Endosc. 2023 Aug;98(2):155-161.e1.

15. Wani S, et al. Recurrence Is rare following complete eradication of intestinal metaplasia in patients with Barrett’s esophagus and peaks at 18 months. Clin Gastroenterol Hepatol. 2020 Oct;18(11):2609-2617.e2.

16. Duvvuri A, et al. Mo1273 Location and pattern of recurrences in patients with Barrett’s esophagus after endoscopic therapy: A systematic review and critical analysis of the published literature. Gastrointest Endosc. 2020;91(6):AB410-1.

17. He T, et al. Location and appearance of dysplastic Barrett’s esophagus recurrence after endoscopic eradication therapy: No additional yield from random biopsy sampling neosquamous mucosa. Gastrointest Endosc. 2023 Nov;98(5):722-732.

Introduction

Barrett’s esophagus (BE) is characterized by the replacement of squamous epithelium by columnar metaplasia of the distal esophagus (>1 cm length). It is a precancerous condition, with 3%-5% of patients with BE developing esophageal adenocarcinoma (EAC) in their lifetime. EAC is one of the cancers with high morbidity and mortality (5-year survival < 20%), and its incidence has been on the rise. Studies examining the natural history of BE have demonstrated that the progression happens through a metaplasia-dysplasia-neoplasia sequence. Therefore, early detection of BE and timely management to prevent progression to EAC is crucial.

Grades of Dysplasia

The current gold standard for the diagnosis of BE neoplasia includes a high-quality endoscopic evaluation and biopsies. Biopsies should be obtained from any visible lesions (nodules, ulcers) followed by a random 4-quadrant fashion (Seattle protocol) interval of the entire length of the BE segment. It is essential to pay attention to the results of the biopsy that have been obtained since it will not only determine the surveillance interval but is crucial in planning any necessary endoscopic therapy. The possible results of the biopsy and its implications are:

• No intestinal metaplasia (IM): This would rule out Barrett’s esophagus and no further surveillance would be necessary. A recent population-based study of over 1 million patients showed a 55% and 61% reduced risk of upper gastrointestinal (UGI) cancer and deaths respectively after a negative endoscopy.¹
• Intestinal metaplasia with no dysplasia (non-dysplastic BE): Biopsies confirm presence of intestinal metaplasia in the biopsies without any evidence of dysplasia. While the rate of progression to EAC is low (0.07%-0.25%), it is not absent and thus surveillance would be indicated. Current guidelines suggest repeating an endoscopy with biopsy in 5 years if the length of BE is < 3 cm or 3 years if length of BE ≥ 3 cm.²
• Indeterminate for dysplasia (BE-IND): Biopsies confirm IM but are not able to definitively rule out dysplasia. This can be seen in about 4%-8% of the biopsies obtained. The progression rates to EAC are reported to be comparable or lower to low-grade dysplasia (LGD), so the current recommendation is to intensify acid reduction therapy and repeat endoscopy in 6 months. If repeat endoscopy downgrades to non-dysplastic, then can follow surveillance according to NDBE protocol; otherwise recommend continuing surveillance every 12 months.
• Low-grade dysplasia (BE-LGD): Biopsies confirm IM but also show tightly packed overlapping basal nuclei with hyperchromasia and irregular contours, basal stratification of nuclei, and diminished goblet and columnar cell mucus. There is significant inter-observer variability reported,³ and thus the slides must be reviewed by a second pathologist with experience in BE to confirm the findings. Once confirmed, based on risk factors such as presence of multifocal LGD, persistence of LGD, presence of visible lesions, etc., the patient can be offered Barrett’s endoscopic therapy (BET) or undergo continued surveillance. The decision of pursuing one or the other would be dependent on patient preference and shared decision-making between the patient and the provider.
• High-grade dysplasia (BE-HGD): Biopsies confirm IM with cells showing greater degree of cytologic and architectural alterations of dysplasia than LGD but without overt neoplastic features. Over 40% of the patients would progress to EAC and thus the current recommendations would be to recommend BET in these patients.⁴
• Esophageal adenocarcinoma (EAC): Biopsies demonstrate neoplasia. If the neoplastic changes are limited to the mucosa (T1a) on endoscopic ultrasound or cross-sectional imaging, then BET is suggested. If there is involvement of submucosa, then depending on the depth of invasion, absence of high-risk features (poor differentiation, lymphovascular invasion), BET can be considered as an alternative to esophagectomy.

Lesion Detection on Endoscopy

Data from large population-based studies with at least 3 years of follow-up reported that 58%-66% of EAC detected during endoscopy were diagnosed within 1 year of an index Barrett’s esophagus screening endoscopy, or post-endoscopy Barrett’s neoplasia, and were considered likely to have been missed during index endoscopy.⁵ This underscores the importance of careful and systematic endoscopic examination during an upper endoscopy.

Studies have also demonstrated that longer examination time was associated with significantly higher detection of HGD/EAC.^6,7 Careful examination of the tubular esophagus and gastroesophageal junction (GEJ) should be performed in forward and retroflexed views looking for any subtle areas of nodularity, loop distortion, variability in vascular patterns, mucosal changes concerning for dysplasia or neoplasia. Use of high-definition white light endoscopy (HD-WLE) and virtual chromoendoscopy techniques such as narrow banding imaging (NBI) or blue laser imaging (BLI) are currently recommended in the guidelines.² Spray chromoendoscopy using acetic acid can also be utilized. Another exciting development is the use of artificial intelligence (AI) in detecting and diagnosing BE associated lesions and neoplasia.
 

Barrett’s Endoscopic Therapy (BET)

Patients with visible lesions, dysplasia, or early EAC are candidates for BET (Table 1).

167527_table_web.jpg

BET involves resective and ablative modalities. The resective modalities include endoscopic mucosal resection (EMR) and endoscopic submucosal dissection (ESD) and are the modalities of choice for nodular or raised lesions.

EMR involves endoscopic resection of abnormal mucosa using either lift-assisted technique or multi-band ligation (Figure 1).

167527_figure_web.jpg

ESD, on the other hand, involves submucosal dissection and perimeter resection of the lesion, thus providing the advantage of an en-bloc resection. In a recent randomized controlled trial (RCT) of 40 patients undergoing ESD vs EMR for HGD/EAC, ESD was better for curative resection (R0) (58%) compared with EMR (12%); however, the remission rates at 3 months were comparable with two perforations reported in the ESD group while there were no complications in the EMR group.⁸

There is an apparent learning curve when it comes to these advanced techniques, and with more experience, we are seeing comparable results for both these modalities. However, given the complexity and time required for the procedure, current practices typically involve preserving ESD for lesions > 2 cm, those having a likelihood of cancer in the superficial submucosa, or those that EMR cannot remove due to underlying fibrosis or post-EMR recurrence.

Srinivasan_Sachin_KS_web.jpg

Barrett’s Refractory to Endoscopic Therapy

Failure of BET is defined as persistent columnar lined epithelium (intestinal metaplasia) with inadequate response, after adequate attempts at endoscopic ablation therapy (after resection) with at least four ablation sessions.¹³ If encountered, special attention must be given to check compliance with proton pump inhibitors (PPIs), previous incomplete resection, and presence of large hiatal hernia. If CE-IM is not achieved after multiple sessions, change of ablative modality is typically considered. In addition, careful examination for visible lesions should be performed and even if a small one is noted, this should be first resected prior to application of any ablative therapy.

Sharma_Prateek_KS_2024_web.jpg

Currently there are no guideline recommendations regarding the preference of one endoscopic modality over another or consideration of potential endoscopic or surgical fundoplication. These modalities primarily rely on technologies available at an institution and the preference of a provider based on their training and experience. Most studies indicate 1-3 sessions (~ 3 months apart) of ablative treatment before achieving CE-IM.
 

Success and Adverse Events of BET

In a recent real-world study of over 27,000 patients with dysplastic BE, 5295 underwent BET. Analysis showed that patients with HGD/EAC who had BET had a significantly lower 3-year mortality (HGD: RR, 0.59; 95%CI, 0.49-0.71; EAC: RR, 0.53; 95% CI, 0.44-0.65) compared with those who did not undergo BET. Esophageal strictures were the most common adverse event and were noted in 6.5%, followed by chest pain (1.8%), upper GI bleeding (0.47%), and esophageal perforation (0.2%).¹⁴

In general, adverse events can be divided into immediate and delayed adverse events. Immediate adverse events typically involve bleeding and perforation that can occur during or shortly after the procedure. These are reported at higher rates with resective modalities compared with ablative therapies. Standard endoscopic techniques involving coagulation grasper or clips can be used to achieve hemostasis. Endoscopic suturing devices offer the ability to contain any perforation. The need for surgical intervention is small and limited to adverse events not detected during the procedure.

Delayed adverse events such as stricture and stenosis are higher for resective modalities (up to 30%), especially when involving more significant than 75% of the esophageal circumference. Post-procedural pain/dysphagia is most common after ablative therapies. Dysphagia reported after any endoscopic therapy should be promptly evaluated, and sequential dilation until the goal esophageal lumen is achieved should be performed every 2-4 weeks.
 

Recurrences and Surveillance After BET

What is established is that recurrences can occur and may be subtle, therefore detailed endoscopic surveillance is required. In a prospective study, recurrence rates of 15%-16% for IM and 3%-5% for any dysplasia were reported, with the majority being in the first 2 years after achieving CE-IM.¹⁵ A systematic review of 21 studies looking at the location of recurrences suggested that the majority (56%) occur in the distal esophagus. Of those that occur in the esophagus, about 80% of them were in the distal 2 cm of the esophagus and only 50% of the recurrences were visible recurrences, thus reiterating the importance of meticulous examination and systematic biopsies.¹⁶

On the contrary, a recent single-center study of 217 patients who had achieved CE-IM with 5.5 years of follow-up demonstrated a 26% and 8% recurrence of IM and dysplasia, respectively. One hundred percent of the recurrence in the esophagus was reported as visible.¹⁷ Therefore, follow-up endoscopy surveillance protocol after CE-IM should still involve meticulous examination, biopsy of visible lesions, and systematic biopsies for non-visible lesions from the original BE segment, similar to those patients who have not needed BET.

Current guidelines based on expert consensus and evidence recommend surveillance after CE-IM based on original most advanced histology:²

1. LGD: 1 year, 3 years, and every 2 years after that.

2. HGD/EAC: 3 months, 6 months, 12 months, and annually after that.

There is no clear guideline on when to stop surveillance since the longest available follow-up is around 10 years, and recurrences are still detected. A potential surveillance endpoint may be based on age and comorbidities, especially those that would preclude a patient from being a candidate for BET.
 

When Should a Patient Be Referred?

BE patients with visible lesions and/or dysplastic changes in the biopsy who would require BET should be considered for referral to high-volume centers. Studies have shown higher success for CE-IM and lower rates of adverse events and recurrences in these patients managed at expert centers. The presence of a multidisciplinary team involving pathologists, surgeons, and oncologists is critical and offers a timely opportunity in case of need for a high-risk patient.

Conclusion

BE is a precursor to EAC, with rising incidence and poor 5-year survival. Endoscopic diagnosis is the gold standard and requires a high-quality examination and biopsies. Based on histopathology, a systematic surveillance and BET plan should be performed to achieve CE-IM in patients with dysplasia. Once CE-IM is achieved, regular surveillance should be performed with careful attention to recurrences and complications from the BET modalities.

Dr. Srinivasan and Dr. Sharma are based at the University of Kansas Medical Center, Kansas City, Kansas, and the Kansas City Veterans Affairs Medical Center, Kansas City, Missouri. Dr. Srinivasan has no relevant disclosures. Dr. Sharma disclosed research grants from ERBE, Ironwood Pharmaceuticals, Olympus, and Medtronic. He has served as a consultant for Takeda, Samsung Bioepis, Olympus, and Lumendi, and reports other funding from Medtronic, Fujifilm Medical Systems USA, and Salix.

References

1. Holmberg D, et al. Incidence and mortality in upper gastrointestinal cancer after negative endoscopy for gastroesophageal reflux disease. Gastroenterology. 2022;162(2):431-438.e4.

2. Shaheen NJ, et al. Diagnosis and management of Barrett’s esophagus: An updated ACG guideline. Am J Gastroenterol. 2022 Apr;117(4):559-587.

3. Pech O, et al. Inter-observer variability in the diagnosis of low-grade dysplasia in pathologists: A comparison between experienced and inexperienced pathologists. Gastrointest Endosc. 2006 Apr;63(5):AB130.

4. Krishnamoorthi R, et al. Factors associated with progression of Barrett’s esophagus: A systematic review and meta-analysis. Clin Gastroenterol Hepatol. 2018 Jul;16(7):1046-1055.e8.

5. Visrodia K, et al. Magnitude of missed esophageal adenocarcinoma after Barrett’s esophagus diagnosis: A systematic review and meta-analysis. Gastroenterology. 2016 Mar;150(3):599-607.e7; quiz e14-5.

6. Perisetti A, Sharma P. Tips for improving the identification of neoplastic visible lesions in Barrett’s esophagus. Gastrointest Endosc. 2023 Feb;97(2):248-250.

7. Gupta N, et al. Longer inspection time is associated with increased detection of high-grade dysplasia and esophageal adenocarcinoma in Barrett’s esophagus. Gastrointest Endosc. 2012 Sep;76(3):531-538.

8. Terheggen G, et al. A randomised trial of endoscopic submucosal dissection versus endoscopic mucosal resection for early Barrett’s neoplasia. Gut. 2017 May;66(5):783-793.

9. Wolfson P, et al. Endoscopic eradication therapy for Barrett’s esophagus-related neoplasia: A final 10-year report from the UK National HALO Radiofrequency Ablation Registry. Gastrointest Endosc. 2022 Aug;96(2):223-233.

10. Rösch T, et al. 1151 Multicenter feasibility study of combined injection and argon plasma coagulation (hybrid-APC) in the ablation therapy of neoplastic Barrett esophagus. Gastrointest Endosc. 2017;85(5):AB154.

11. Knabe M, et al. Radiofrequency ablation versus hybrid argon plasma coagulation in Barrett’s esophagus: A prospective randomised trial. Surg Endosc. 2023;37(10):7803-7811.

12. Van Munster SN, et al. Radiofrequency vapor ablation for Barrett’s esophagus: Feasibility, safety, and proof of concept in a stepwise study with in vitro, animal, and the first in-human application. Endoscopy. 2021 Nov;53(11):1162-1168.

13. Emura F, et al. Rio de Janeiro global consensus on landmarks, definitions, and classifications in Barrett’s esophagus: World Endoscopy Organization Delphi study. Gastroenterology. 2022 Jul;163(1):84-96.e2.

14. Singh RR, et al. Real-world evidence of safety and effectiveness of Barrett’s endoscopic therapy. Gastrointest Endosc. 2023 Aug;98(2):155-161.e1.

15. Wani S, et al. Recurrence Is rare following complete eradication of intestinal metaplasia in patients with Barrett’s esophagus and peaks at 18 months. Clin Gastroenterol Hepatol. 2020 Oct;18(11):2609-2617.e2.

16. Duvvuri A, et al. Mo1273 Location and pattern of recurrences in patients with Barrett’s esophagus after endoscopic therapy: A systematic review and critical analysis of the published literature. Gastrointest Endosc. 2020;91(6):AB410-1.

17. He T, et al. Location and appearance of dysplastic Barrett’s esophagus recurrence after endoscopic eradication therapy: No additional yield from random biopsy sampling neosquamous mucosa. Gastrointest Endosc. 2023 Nov;98(5):722-732.

Gastroenterology

January 2024

Hirano I, et al; ASCENT WORKING GROUP. Ascending to New Heights for Novel Therapeutics for Eosinophilic Esophagitis. Gastroenterology. 2024 Jan;166(1):1-10. doi: 10.1053/j.gastro.2023.09.004. Epub 2023 Sep 9. PMID: 37690772; PMCID: PMC10872872.



Åkerström JH, et al. Antireflux Surgery Versus Antireflux Medication and Risk of Esophageal Adenocarcinoma in Patients With Barrett’s Esophagus. Gastroenterology. 2024 Jan;166(1):132-138.e3. doi: 10.1053/j.gastro.2023.08.050. Epub 2023 Sep 9. PMID: 37690771.



Barnes EL, et al; AGA Clinical Guidelines Committee. AGA Clinical Practice Guideline on the Management of Pouchitis and Inflammatory Pouch Disorders. Gastroenterology. 2024 Jan;166(1):59-85. doi: 10.1053/j.gastro.2023.10.015. PMID: 38128971.

February 2024

Yoo HW, et al. Helicobacter pylori Treatment and Gastric Cancer Risk After Endoscopic Resection of Dysplasia: A Nationwide Cohort Study. Gastroenterology. 2024 Feb;166(2):313-322.e3. doi: 10.1053/j.gastro.2023.10.013. Epub 2023 Oct 18. PMID: 37863270.



Yang J, et al. High Soluble Fiber Promotes Colorectal Tumorigenesis Through Modulating Gut Microbiota and Metabolites in Mice. Gastroenterology. 2024 Feb;166(2):323-337.e7. doi: 10.1053/j.gastro.2023.10.012. Epub 2023 Oct 18. PMID: 37858797.



Young E, et al. Texture and Color Enhancement Imaging Improves Colonic Adenoma Detection: A Multicenter Randomized Controlled Trial. Gastroenterology. 2024 Feb;166(2):338-340.e3. doi: 10.1053/j.gastro.2023.10.008. Epub 2023 Oct 14. PMID: 37839498.
 

Clinical Gastroenterology and Hepatology

January 2024

Overbeek KA, et al; Dutch Familial Pancreatic Cancer Surveillance Study work group. Intraductal Papillary Mucinous Neoplasms in High-Risk Individuals: Incidence, Growth Rate, and Malignancy Risk. Clin Gastroenterol Hepatol. 2024 Jan;22(1):62-71.e7. doi: 10.1016/j.cgh.2023.03.035. Epub 2023 Apr 7. PMID: 37031711.

Reddy CA, et al. Achalasia is Strongly Associated With Eosinophilic Esophagitis and Other Allergic Disorders. Clin Gastroenterol Hepatol. 2024 Jan;22(1):34-41.e2. doi: 10.1016/j.cgh.2023.06.013. Epub 2023 Jun 28. PMID: 37391057; PMCID: PMC10753026.

Thiruvengadam NR, et al. The Clinical Impact and Cost-Effectiveness of Surveillance of Incidentally Detected Gastric Intestinal Metaplasia: A Microsimulation Analysis. Clin Gastroenterol Hepatol. 2024 Jan;22(1):51-61. doi: 10.1016/j.cgh.2023.05.028. Epub 2023 Jun 9. Erratum in: Clin Gastroenterol Hepatol. 2024 Jan 19;: PMID: 37302442.

February 2024

Goodoory VC, et al. Systematic Review and Meta-analysis: Efficacy of Mesalamine in Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):243-251.e5. doi: 10.1016/j.cgh.2023.02.014. Epub 2023 Feb 27. PMID: 36858143.

Brenner DM, et al. Development and Current State of Digital Therapeutics for Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):222-234. doi: 10.1016/j.cgh.2023.09.013. Epub 2023 Sep 22. PMID: 37743035.
 

Techniques and Innovations in Gastrointestinal Endoscopy

January 2024

Ramirez PR, et al. Gaps and Improvement Opportunities in Post-Colonoscopy Communication. Tech Innov Gastrointest Endosc. 2024 Jan;26(1):90-92. doi: 10.1016/j.tige.2023.10.001. Epub 2023 Oct 22.

Gonzaga ER, et al. Gastric Peroral Endoscopic Myotomy (G-POEM) for the Management of Gastroparesis. Tech Innov Gastrointest Endosc. 2024 Jan; 26(1): 46-55. doi: 10.1016/j.tige.2023.09.002. Epub 2023 Oct 13.



Wang D, et al. Sphincterotomy vs Sham Procedure for Pain Relief in Sphincter of Oddi Dysfunction: Systematic Review and Meta-analysis. Tech Innov Gastrointest Endosc. 2024 Jan;26(1): 30-37. doi: 10.1016/j.tige.2023.10.003. Epub 2023 Nov 8.
 

Gastro Hep Advances

January 2024

Adeniran E, et al. Intense and Sustained Alcohol Consumption Associated With Acute Pancreatitis Warrants Early Intervention. Gastro Hep Advances. 2024 Jan;3(1):61-63. doi: 10.1016/j.gastha.2023.08.017. Epub 2023 Sep 2.

Alkhouri N, et al. A Novel Prescription Digital Therapeutic Option for the Treatment of Metabolic Dysfunction-Associated Steatotic Liver Disease. Gastro Hep Advances. 2024 Jan;3(1): 9-16. doi: 10.1016/j.gastha.2023.08.019. Epub 2023 Oct 1.

Gastroenterology

January 2024

Hirano I, et al; ASCENT WORKING GROUP. Ascending to New Heights for Novel Therapeutics for Eosinophilic Esophagitis. Gastroenterology. 2024 Jan;166(1):1-10. doi: 10.1053/j.gastro.2023.09.004. Epub 2023 Sep 9. PMID: 37690772; PMCID: PMC10872872.



Åkerström JH, et al. Antireflux Surgery Versus Antireflux Medication and Risk of Esophageal Adenocarcinoma in Patients With Barrett’s Esophagus. Gastroenterology. 2024 Jan;166(1):132-138.e3. doi: 10.1053/j.gastro.2023.08.050. Epub 2023 Sep 9. PMID: 37690771.



Barnes EL, et al; AGA Clinical Guidelines Committee. AGA Clinical Practice Guideline on the Management of Pouchitis and Inflammatory Pouch Disorders. Gastroenterology. 2024 Jan;166(1):59-85. doi: 10.1053/j.gastro.2023.10.015. PMID: 38128971.

February 2024

Yoo HW, et al. Helicobacter pylori Treatment and Gastric Cancer Risk After Endoscopic Resection of Dysplasia: A Nationwide Cohort Study. Gastroenterology. 2024 Feb;166(2):313-322.e3. doi: 10.1053/j.gastro.2023.10.013. Epub 2023 Oct 18. PMID: 37863270.



Yang J, et al. High Soluble Fiber Promotes Colorectal Tumorigenesis Through Modulating Gut Microbiota and Metabolites in Mice. Gastroenterology. 2024 Feb;166(2):323-337.e7. doi: 10.1053/j.gastro.2023.10.012. Epub 2023 Oct 18. PMID: 37858797.



Young E, et al. Texture and Color Enhancement Imaging Improves Colonic Adenoma Detection: A Multicenter Randomized Controlled Trial. Gastroenterology. 2024 Feb;166(2):338-340.e3. doi: 10.1053/j.gastro.2023.10.008. Epub 2023 Oct 14. PMID: 37839498.
 

Clinical Gastroenterology and Hepatology

January 2024

Overbeek KA, et al; Dutch Familial Pancreatic Cancer Surveillance Study work group. Intraductal Papillary Mucinous Neoplasms in High-Risk Individuals: Incidence, Growth Rate, and Malignancy Risk. Clin Gastroenterol Hepatol. 2024 Jan;22(1):62-71.e7. doi: 10.1016/j.cgh.2023.03.035. Epub 2023 Apr 7. PMID: 37031711.

Reddy CA, et al. Achalasia is Strongly Associated With Eosinophilic Esophagitis and Other Allergic Disorders. Clin Gastroenterol Hepatol. 2024 Jan;22(1):34-41.e2. doi: 10.1016/j.cgh.2023.06.013. Epub 2023 Jun 28. PMID: 37391057; PMCID: PMC10753026.

Thiruvengadam NR, et al. The Clinical Impact and Cost-Effectiveness of Surveillance of Incidentally Detected Gastric Intestinal Metaplasia: A Microsimulation Analysis. Clin Gastroenterol Hepatol. 2024 Jan;22(1):51-61. doi: 10.1016/j.cgh.2023.05.028. Epub 2023 Jun 9. Erratum in: Clin Gastroenterol Hepatol. 2024 Jan 19;: PMID: 37302442.

February 2024

Goodoory VC, et al. Systematic Review and Meta-analysis: Efficacy of Mesalamine in Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):243-251.e5. doi: 10.1016/j.cgh.2023.02.014. Epub 2023 Feb 27. PMID: 36858143.

Brenner DM, et al. Development and Current State of Digital Therapeutics for Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):222-234. doi: 10.1016/j.cgh.2023.09.013. Epub 2023 Sep 22. PMID: 37743035.
 

Techniques and Innovations in Gastrointestinal Endoscopy

January 2024

Ramirez PR, et al. Gaps and Improvement Opportunities in Post-Colonoscopy Communication. Tech Innov Gastrointest Endosc. 2024 Jan;26(1):90-92. doi: 10.1016/j.tige.2023.10.001. Epub 2023 Oct 22.

Gonzaga ER, et al. Gastric Peroral Endoscopic Myotomy (G-POEM) for the Management of Gastroparesis. Tech Innov Gastrointest Endosc. 2024 Jan; 26(1): 46-55. doi: 10.1016/j.tige.2023.09.002. Epub 2023 Oct 13.



Wang D, et al. Sphincterotomy vs Sham Procedure for Pain Relief in Sphincter of Oddi Dysfunction: Systematic Review and Meta-analysis. Tech Innov Gastrointest Endosc. 2024 Jan;26(1): 30-37. doi: 10.1016/j.tige.2023.10.003. Epub 2023 Nov 8.
 

Gastro Hep Advances

January 2024

Adeniran E, et al. Intense and Sustained Alcohol Consumption Associated With Acute Pancreatitis Warrants Early Intervention. Gastro Hep Advances. 2024 Jan;3(1):61-63. doi: 10.1016/j.gastha.2023.08.017. Epub 2023 Sep 2.

Alkhouri N, et al. A Novel Prescription Digital Therapeutic Option for the Treatment of Metabolic Dysfunction-Associated Steatotic Liver Disease. Gastro Hep Advances. 2024 Jan;3(1): 9-16. doi: 10.1016/j.gastha.2023.08.019. Epub 2023 Oct 1.

Gastroenterology

January 2024

Hirano I, et al; ASCENT WORKING GROUP. Ascending to New Heights for Novel Therapeutics for Eosinophilic Esophagitis. Gastroenterology. 2024 Jan;166(1):1-10. doi: 10.1053/j.gastro.2023.09.004. Epub 2023 Sep 9. PMID: 37690772; PMCID: PMC10872872.



Åkerström JH, et al. Antireflux Surgery Versus Antireflux Medication and Risk of Esophageal Adenocarcinoma in Patients With Barrett’s Esophagus. Gastroenterology. 2024 Jan;166(1):132-138.e3. doi: 10.1053/j.gastro.2023.08.050. Epub 2023 Sep 9. PMID: 37690771.



Barnes EL, et al; AGA Clinical Guidelines Committee. AGA Clinical Practice Guideline on the Management of Pouchitis and Inflammatory Pouch Disorders. Gastroenterology. 2024 Jan;166(1):59-85. doi: 10.1053/j.gastro.2023.10.015. PMID: 38128971.

February 2024

Yoo HW, et al. Helicobacter pylori Treatment and Gastric Cancer Risk After Endoscopic Resection of Dysplasia: A Nationwide Cohort Study. Gastroenterology. 2024 Feb;166(2):313-322.e3. doi: 10.1053/j.gastro.2023.10.013. Epub 2023 Oct 18. PMID: 37863270.



Yang J, et al. High Soluble Fiber Promotes Colorectal Tumorigenesis Through Modulating Gut Microbiota and Metabolites in Mice. Gastroenterology. 2024 Feb;166(2):323-337.e7. doi: 10.1053/j.gastro.2023.10.012. Epub 2023 Oct 18. PMID: 37858797.



Young E, et al. Texture and Color Enhancement Imaging Improves Colonic Adenoma Detection: A Multicenter Randomized Controlled Trial. Gastroenterology. 2024 Feb;166(2):338-340.e3. doi: 10.1053/j.gastro.2023.10.008. Epub 2023 Oct 14. PMID: 37839498.
 

Clinical Gastroenterology and Hepatology

January 2024

Overbeek KA, et al; Dutch Familial Pancreatic Cancer Surveillance Study work group. Intraductal Papillary Mucinous Neoplasms in High-Risk Individuals: Incidence, Growth Rate, and Malignancy Risk. Clin Gastroenterol Hepatol. 2024 Jan;22(1):62-71.e7. doi: 10.1016/j.cgh.2023.03.035. Epub 2023 Apr 7. PMID: 37031711.

Reddy CA, et al. Achalasia is Strongly Associated With Eosinophilic Esophagitis and Other Allergic Disorders. Clin Gastroenterol Hepatol. 2024 Jan;22(1):34-41.e2. doi: 10.1016/j.cgh.2023.06.013. Epub 2023 Jun 28. PMID: 37391057; PMCID: PMC10753026.

Thiruvengadam NR, et al. The Clinical Impact and Cost-Effectiveness of Surveillance of Incidentally Detected Gastric Intestinal Metaplasia: A Microsimulation Analysis. Clin Gastroenterol Hepatol. 2024 Jan;22(1):51-61. doi: 10.1016/j.cgh.2023.05.028. Epub 2023 Jun 9. Erratum in: Clin Gastroenterol Hepatol. 2024 Jan 19;: PMID: 37302442.

February 2024

Goodoory VC, et al. Systematic Review and Meta-analysis: Efficacy of Mesalamine in Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):243-251.e5. doi: 10.1016/j.cgh.2023.02.014. Epub 2023 Feb 27. PMID: 36858143.

Brenner DM, et al. Development and Current State of Digital Therapeutics for Irritable Bowel Syndrome. Clin Gastroenterol Hepatol. 2024 Feb;22(2):222-234. doi: 10.1016/j.cgh.2023.09.013. Epub 2023 Sep 22. PMID: 37743035.
 

Techniques and Innovations in Gastrointestinal Endoscopy

January 2024

Ramirez PR, et al. Gaps and Improvement Opportunities in Post-Colonoscopy Communication. Tech Innov Gastrointest Endosc. 2024 Jan;26(1):90-92. doi: 10.1016/j.tige.2023.10.001. Epub 2023 Oct 22.

Gonzaga ER, et al. Gastric Peroral Endoscopic Myotomy (G-POEM) for the Management of Gastroparesis. Tech Innov Gastrointest Endosc. 2024 Jan; 26(1): 46-55. doi: 10.1016/j.tige.2023.09.002. Epub 2023 Oct 13.



Wang D, et al. Sphincterotomy vs Sham Procedure for Pain Relief in Sphincter of Oddi Dysfunction: Systematic Review and Meta-analysis. Tech Innov Gastrointest Endosc. 2024 Jan;26(1): 30-37. doi: 10.1016/j.tige.2023.10.003. Epub 2023 Nov 8.
 

Gastro Hep Advances

January 2024

Adeniran E, et al. Intense and Sustained Alcohol Consumption Associated With Acute Pancreatitis Warrants Early Intervention. Gastro Hep Advances. 2024 Jan;3(1):61-63. doi: 10.1016/j.gastha.2023.08.017. Epub 2023 Sep 2.

Alkhouri N, et al. A Novel Prescription Digital Therapeutic Option for the Treatment of Metabolic Dysfunction-Associated Steatotic Liver Disease. Gastro Hep Advances. 2024 Jan;3(1): 9-16. doi: 10.1016/j.gastha.2023.08.019. Epub 2023 Oct 1.

Dear colleagues,

Since our prior Perspectives piece on artificial intelligence (AI) in GI and Hepatology in 2022, the field has seen almost exponential growth. Expectations are high that AI will revolutionize our field and significantly improve patient care. But as the global discussion on AI has shown, there are real challenges with adoption, including issues with accuracy, reliability, and privacy.

In this issue, Dr. Nabil M. Mansour and Dr. Thomas R. McCarty explore the current and future impact of AI on gastroenterology, while Dr. Basile Njei and Yazan A. Al Ajlouni assess its role in hepatology. We hope these pieces will help your discussions in incorporating or researching AI for use in your own practices. We welcome your thoughts on this issue on X @AGA_GIHN.

Gyanprakash A. Ketwaroo, MD, MSc, is associate professor of medicine, Yale University, New Haven, Conn., and chief of endoscopy at West Haven (Conn.) VA Medical Center. He is an associate editor for GI & Hepatology News.

Artificial Intelligence in Gastrointestinal Endoscopy

BY THOMAS R. MCCARTY, MD, MPH; NABIL M. MANSOUR, MD

The last few decades have seen an exponential increase and interest in the role of artificial intelligence (AI) and adoption of deep learning algorithms within healthcare and patient care services. The field of gastroenterology and endoscopy has similarly seen a tremendous uptake in acceptance and implementation of AI for a variety of gastrointestinal conditions. The spectrum of AI-based applications includes detection or diagnostic-based as well as therapeutic assistance tools. From the first US Food and Drug Administration (FDA)-approved device that uses machine learning to assist clinicians in detecting lesions during colonoscopy, to other more innovative machine learning techniques for small bowel, esophageal, and hepatobiliary conditions, AI has dramatically changed the landscape of gastrointestinal endoscopy.

Mansour_Nabil_M_HOUSTON_web.jpg

Ultimately, this data led to FDA approval of the CADe system GI Genius (Medtronic, Dublin, Ireland) in 2021.⁴ Additional systems have since been FDA approved or 510(k) cleared including Endoscreener (Wision AI, Shanghai, China), SKOUT (Iterative Health, Cambridge, Massachusetts), MAGENTIQ-COLO (MAGENTIQ-EYE LTD, Haifa, Israel), and CAD EYE (Fujifilm, Tokyo), all of which have shown increased ADR and/or increased APC and/or reduced adenoma miss rates in randomized trials.⁵

Yet despite the promise of improved quality and subsequent translation to better patient outcomes, there has been a noticeable disconnect between RCT data and more real-world literature.⁶ In a recent study, no improvement was seen in ADR after implementation of a CADe system for colorectal cancer screening — including both higher and lower-ADR performers. Looking at change over time after implementation, CADe had no positive effect in any group over time, divergent from early RCT data. In a more recent multicenter, community-based RCT study, again CADe did not result in a statistically significant difference in the number of adenomas detected.⁷ The differences between some of these more recent “real-world” studies vs the majority of data from RCTs raise important questions regarding the potential of bias (due to unblinding) in prospective trials, as well as the role of the human-AI interaction.

Importantly for RCT data, both cohorts in these studies met adequate ADR benchmarks, though it remains unclear whether a truly increased ADR necessitates better patient outcomes — is higher always better? In addition, an important consideration with evaluating any AI/CADe system is that they often undergo frequent updates, each promising improved accuracy, sensitivity, and specificity. This is an interesting dilemma and raises questions about the enduring relevance of studies conducted using an outdated version of a CADe system.

Additional unanswered questions regarding an ideal ADR for implementation, preferred patient populations for screening (especially for younger individuals), and the role and adoption of computer-aided polyp diagnosis/characterization (CADx) within the United States remain. Furthermore, questions regarding procedural withdrawal time, impact on sessile serrated lesion detection, cost-effectiveness, and preferred adoption strategies have begun to be explored, though require more data to better define a best practice approach. Ultimately, answers to some of these unknowns may explain the discordant results and help guide future implementation measures.

Innovative applications for alternative gastrointestinal conditions

Given the fervor and excitement, as well as the outcomes associated with AI-based colorectal screening, it is not surprising these techniques have been expanded to other gastrointestinal conditions. At this time, all of these are fledgling, mostly single-center tools, not yet ready for widespread adoption. Nonetheless, these represent a potentially important step forward for difficult-to-manage gastrointestinal diseases.

Machine learning CADe systems have been developed to help identify early Barrett’s neoplasia, depth and invasion of gastric cancer, as well as lesion detection in small bowel video capsule endoscopy.^8-10 Endoscopic retrograde cholangiopancreatography (ERCP)-based applications for cholangiocarcinoma and indeterminate stricture diagnosis have also been studied.¹¹ Additional AI-based algorithms have been employed for complex procedures such as endoscopic submucosal dissection (ESD) or peroral endoscopic myotomy (POEM) to delineate vessels, better define tissue planes for dissection, and visualize landmark structures.^12,13 Furthermore, AI-based scope guidance/manipulation, bleeding detection, landmark identification, and lesion detection have the potential to revolutionize endoscopic training and education. The impact that generative AI can potentially have on clinical practice is also an exciting prospect that warrants further investigation.

Artificial intelligence adoption in clinical practice

Clinical practice with regard to AI and colorectal cancer screening largely mirrors the disconnect in the current literature, with “believers” and “non-believers” as well as innovators and early adopters alongside laggards. In our own academic practices, we continue to struggle with the adoption and standardized implementation of AI-based colorectal cancer CADe systems, despite the RCT data showing positive results. It is likely that AI uptake will follow the technology predictions of Amara’s Law — i.e., individuals tend to overestimate the short-term impact of new technologies while underestimating long-term effects. In the end, more widespread adoption in community practice and larger scale real-world clinical outcomes studies are likely to determine the true impact of these exciting technologies. For other, less established AI-based tools, more data are currently required.

Conclusions

Ultimately, AI-based algorithms are likely here to stay, with continued improvement and evolution to occur based on provider feedback and patient care needs. Current tools, while not all-encompassing, have the potential to dramatically change the landscape of endoscopic training, diagnostic evaluation, and therapeutic care. It is critically important that relevant stakeholders, both endoscopists and patients, be involved in future applications and design to improve efficiency and quality outcomes overall.

Dr. McCarty is based in the Lynda K. and David M. Underwood Center for Digestive Disorders, Houston Methodist Hospital. Dr. Mansour is based in the section of gastroenterology, Baylor College of Medicine, Houston. Dr. McCarty reports no conflicts of interest. Dr. Mansour reports having been a consultant for Iterative Health.

References

1. Repici A, et al. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology. 2020 Aug. doi: 10.1053/j.gastro.2020.04.062.

2. Repici A, et al. Artificial intelligence and colonoscopy experience: Lessons from two randomised trials. Gut. Apr 2022. doi: 10.1136/gutjnl-2021-324471.

3. Wallace MB, et al. Impact of artificial intelligence on miss rate of colorectal neoplasia. Gastroenterology 2022 Jul. doi: 10.1053/j.gastro.2022.03.007.

4. United States Food and Drug Administration (FDA). GI Genius FDA Approval [April 9, 2021]. Accessed January 5, 2022. Available at: www.accessdata.fda.gov/cdrh_docs/pdf21/K211951.pdf.

5. Maas MHJ, et al. A computer-aided polyp detection system in screening and surveillance colonoscopy: An international, multicentre, randomised, tandem trial. Lancet Digit Health. 2024 Mar. doi: 10.1016/S2589-7500(23)00242-X.

6. Ladabaum U, et al. Computer-aided detection of polyps does not improve colonoscopist performance in a pragmatic implementation trial. Gastroenterology. 2023 Mar. doi: 10.1053/j.gastro.2022.12.004.

7. Wei MT, et al. Evaluation of computer-aided detection during colonoscopy in the community (AI-SEE): A multicenter randomized clinical trial. Am J Gastroenterol. 2023 Oct. doi: 10.14309/ajg.0000000000002239.

8. de Groof J, et al. The Argos project: The development of a computer-aided detection system to improve detection of Barrett’s neoplasia on white light endoscopy. United European Gastroenterol J. 2019 May. doi: 10.1177/2050640619837443.

9. Kanesaka T, et al. Computer-aided diagnosis for identifying and delineating early gastric cancers in magnifying narrow-band imaging. Gastrointest Endosc. 2018 May. doi: 10.1016/j.gie.2017.11.029.

10. Sahafi A, et al. Edge artificial intelligence wireless video capsule endoscopy. Sci Rep. 2022 Aug. doi: 10.1038/s41598-022-17502-7.

11. Njei B, et al. Artificial intelligence in endoscopic imaging for detection of malignant biliary strictures and cholangiocarcinoma: A systematic review. Ann Gastroenterol. 2023 Mar-Apr. doi: 10.20524/aog.2023.0779.

12. Ebigbo A, et al. Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm. Gut. 2022 Dec. doi: 10.1136/gutjnl-2021-326470.

13. Cao J, et al. Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study. Nat Commun. 2023 Oct. doi: 10.1038/s41467-023-42451-8.

The Promise and Challenges of AI in Hepatology

BY BASILE NJEI, MD, MPH, PHD; YAZAN A. AL-AJLOUNI, MPHIL

In the dynamic realm of medicine, artificial intelligence (AI) emerges as a transformative force, notably within hepatology. The discipline of hepatology, dedicated to liver and related organ diseases, is ripe for AI’s promise to revolutionize diagnostics and treatment, pushing toward a future of precision medicine. Yet, the path to fully realizing AI’s potential in hepatology is laced with data, ethical, and integration challenges.

The application of AI, particularly in histopathology, significantly enhances disease diagnosis and staging in hepatology. AI-driven approaches remedy traditional histopathological challenges, such as interpretative variability, providing more consistent and accurate disease analyses. This is especially evident in conditions like metabolic dysfunction-associated steatohepatitis (MASH) and hepatocellular carcinoma (HCC), where AI aids in identifying critical gene signatures, thereby refining therapy selection.

Njei_Basile_CT_web.jpg

Similarly, deep learning (DL), a branch of AI, has attracted significant interest globally, particularly in image recognition. AI’s incorporation into medical imaging marks a significant advancement, enabling early detection of malignancies like HCC and improving diagnostics in steatotic liver disease through enhanced imaging analyses using convolutional neural networks (CNN). The abundance of imaging data alongside clinical outcomes has catalyzed AI’s integration into radiology, leading to the swift growth of radiomics as a novel domain in medical research.

AI has also been shown to identify nuanced alterations in electrocardiograms (EKGs) associated with liver conditions, potentially detecting the progression of liver diseases at an earlier stage than currently possible. By leveraging complex algorithms and machine learning, AI can analyze EKG patterns with a precision and depth unattainable through traditional manual interpretation. Given that liver diseases, such as cirrhosis or hepatitis, can induce subtle cardiac changes long before other clinical symptoms manifest, early detection through AI-enhanced EKG analysis could lead to timely interventions, potentially halting or reversing disease progression. This approach further enriches our understanding of the intricate interplay between liver function and cardiac health, highlighting the potential for AI to transform not just liver disease diagnostics but also to foster a more integrated approach to patient care.

Al_Ajlouni_Yazan_NY_web.jpg

Beyond diagnostics, the burgeoning field of generative AI introduces groundbreaking possibilities in treatment planning and patient education, particularly for chronic conditions like cirrhosis. Generative AI produces original content, including text, visuals, and music, by identifying and learning patterns from its training data. When it leverages large language models (LLMs), it entails training on vast collections of textual data and using AI models characterized by many parameters. A notable instance of generative AI employing LLMs is ChatGPT (General Pretrained Transformers). By simulating disease progression and treatment outcomes, generative AI can foster personalized treatment strategies and empower patients with knowledge about their health trajectories. Yet, realizing these potential demands requires overcoming data quality and interpretability challenges, and ensuring AI outputs are accessible and actionable for clinicians and patients.

Despite these advancements, leveraging AI in hepatology is not devoid of hurdles. The development and training of AI models require extensive and diverse datasets, raising concerns about data privacy and ethical use. Addressing these concerns is paramount for successfully integrating AI into clinical hepatology practice, necessitating transparent algorithmic processes and stringent ethical standards. Ethical considerations are central to AI’s integration into hepatology. Algorithmic biases, patient privacy, and the impact of AI-driven decisions underscore the need for cautious AI deployment. Developing transparent, understandable algorithms and establishing ethical guidelines for AI use are critical steps towards ethically leveraging AI in patient care.

In conclusion, AI’s integration into hepatology holds tremendous promise for advancing patient care through enhanced diagnostics, treatment planning, and patient education. Overcoming the associated challenges, including ethical concerns, data diversity, and algorithm interpretability, is crucial. As the hepatology community navigates this technological evolution, a balanced approach that marries technological advancements with ethical stewardship will be key to harnessing AI’s full potential, ensuring it serves the best interests of patients and propels the field of hepatology into the future.

We predict a trajectory of increased use and adoption of AI in hepatology. AI in hepatology is likely to meet the test of pervasiveness, improvement, and innovation. The adoption of AI in routine hepatology diagnosis and management will likely follow Amara’s law and the five stages of the hype cycle. We believe that we are still in the infant stages of adopting AI technology in hepatology, and this phase may last 5 years before there is a peak of inflated expectations. The trough of disillusionment and slopes of enlightenment may only be observed in the next decades.

Dr. Njei is based in the Section of Digestive Diseases, Yale School of Medicine, New Haven, Conn. Mr. Al-Ajlouni is a senior medical student at New York Medical College School of Medicine, Valhalla, N.Y. They have no conflicts of interest to declare.

Sources

Taylor-Weiner A, et al. A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH. Hepatology. 2021 Jul. doi: 10.1002/hep.31750.

Zeng Q, et al. Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology. J Hepatol. 2022 Jul. doi: 10.1016/j.jhep.2022.01.018.

Ahn JC, et al. Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis. Am J Gastroenterol. 2022 Mar. doi: 10.14309/ajg.0000000000001617.

Nduma BN, et al. The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review. Cureus. 2023 Dec 15. doi: 10.7759/cureus.50601.

Dear colleagues,

Since our prior Perspectives piece on artificial intelligence (AI) in GI and Hepatology in 2022, the field has seen almost exponential growth. Expectations are high that AI will revolutionize our field and significantly improve patient care. But as the global discussion on AI has shown, there are real challenges with adoption, including issues with accuracy, reliability, and privacy.

In this issue, Dr. Nabil M. Mansour and Dr. Thomas R. McCarty explore the current and future impact of AI on gastroenterology, while Dr. Basile Njei and Yazan A. Al Ajlouni assess its role in hepatology. We hope these pieces will help your discussions in incorporating or researching AI for use in your own practices. We welcome your thoughts on this issue on X @AGA_GIHN.

Gyanprakash A. Ketwaroo, MD, MSc, is associate professor of medicine, Yale University, New Haven, Conn., and chief of endoscopy at West Haven (Conn.) VA Medical Center. He is an associate editor for GI & Hepatology News.

Artificial Intelligence in Gastrointestinal Endoscopy

BY THOMAS R. MCCARTY, MD, MPH; NABIL M. MANSOUR, MD

The last few decades have seen an exponential increase and interest in the role of artificial intelligence (AI) and adoption of deep learning algorithms within healthcare and patient care services. The field of gastroenterology and endoscopy has similarly seen a tremendous uptake in acceptance and implementation of AI for a variety of gastrointestinal conditions. The spectrum of AI-based applications includes detection or diagnostic-based as well as therapeutic assistance tools. From the first US Food and Drug Administration (FDA)-approved device that uses machine learning to assist clinicians in detecting lesions during colonoscopy, to other more innovative machine learning techniques for small bowel, esophageal, and hepatobiliary conditions, AI has dramatically changed the landscape of gastrointestinal endoscopy.

Mansour_Nabil_M_HOUSTON_web.jpg

Ultimately, this data led to FDA approval of the CADe system GI Genius (Medtronic, Dublin, Ireland) in 2021.⁴ Additional systems have since been FDA approved or 510(k) cleared including Endoscreener (Wision AI, Shanghai, China), SKOUT (Iterative Health, Cambridge, Massachusetts), MAGENTIQ-COLO (MAGENTIQ-EYE LTD, Haifa, Israel), and CAD EYE (Fujifilm, Tokyo), all of which have shown increased ADR and/or increased APC and/or reduced adenoma miss rates in randomized trials.⁵

Yet despite the promise of improved quality and subsequent translation to better patient outcomes, there has been a noticeable disconnect between RCT data and more real-world literature.⁶ In a recent study, no improvement was seen in ADR after implementation of a CADe system for colorectal cancer screening — including both higher and lower-ADR performers. Looking at change over time after implementation, CADe had no positive effect in any group over time, divergent from early RCT data. In a more recent multicenter, community-based RCT study, again CADe did not result in a statistically significant difference in the number of adenomas detected.⁷ The differences between some of these more recent “real-world” studies vs the majority of data from RCTs raise important questions regarding the potential of bias (due to unblinding) in prospective trials, as well as the role of the human-AI interaction.

Importantly for RCT data, both cohorts in these studies met adequate ADR benchmarks, though it remains unclear whether a truly increased ADR necessitates better patient outcomes — is higher always better? In addition, an important consideration with evaluating any AI/CADe system is that they often undergo frequent updates, each promising improved accuracy, sensitivity, and specificity. This is an interesting dilemma and raises questions about the enduring relevance of studies conducted using an outdated version of a CADe system.

Additional unanswered questions regarding an ideal ADR for implementation, preferred patient populations for screening (especially for younger individuals), and the role and adoption of computer-aided polyp diagnosis/characterization (CADx) within the United States remain. Furthermore, questions regarding procedural withdrawal time, impact on sessile serrated lesion detection, cost-effectiveness, and preferred adoption strategies have begun to be explored, though require more data to better define a best practice approach. Ultimately, answers to some of these unknowns may explain the discordant results and help guide future implementation measures.

Innovative applications for alternative gastrointestinal conditions

Given the fervor and excitement, as well as the outcomes associated with AI-based colorectal screening, it is not surprising these techniques have been expanded to other gastrointestinal conditions. At this time, all of these are fledgling, mostly single-center tools, not yet ready for widespread adoption. Nonetheless, these represent a potentially important step forward for difficult-to-manage gastrointestinal diseases.

Machine learning CADe systems have been developed to help identify early Barrett’s neoplasia, depth and invasion of gastric cancer, as well as lesion detection in small bowel video capsule endoscopy.^8-10 Endoscopic retrograde cholangiopancreatography (ERCP)-based applications for cholangiocarcinoma and indeterminate stricture diagnosis have also been studied.¹¹ Additional AI-based algorithms have been employed for complex procedures such as endoscopic submucosal dissection (ESD) or peroral endoscopic myotomy (POEM) to delineate vessels, better define tissue planes for dissection, and visualize landmark structures.^12,13 Furthermore, AI-based scope guidance/manipulation, bleeding detection, landmark identification, and lesion detection have the potential to revolutionize endoscopic training and education. The impact that generative AI can potentially have on clinical practice is also an exciting prospect that warrants further investigation.

Artificial intelligence adoption in clinical practice

Clinical practice with regard to AI and colorectal cancer screening largely mirrors the disconnect in the current literature, with “believers” and “non-believers” as well as innovators and early adopters alongside laggards. In our own academic practices, we continue to struggle with the adoption and standardized implementation of AI-based colorectal cancer CADe systems, despite the RCT data showing positive results. It is likely that AI uptake will follow the technology predictions of Amara’s Law — i.e., individuals tend to overestimate the short-term impact of new technologies while underestimating long-term effects. In the end, more widespread adoption in community practice and larger scale real-world clinical outcomes studies are likely to determine the true impact of these exciting technologies. For other, less established AI-based tools, more data are currently required.

Conclusions

Ultimately, AI-based algorithms are likely here to stay, with continued improvement and evolution to occur based on provider feedback and patient care needs. Current tools, while not all-encompassing, have the potential to dramatically change the landscape of endoscopic training, diagnostic evaluation, and therapeutic care. It is critically important that relevant stakeholders, both endoscopists and patients, be involved in future applications and design to improve efficiency and quality outcomes overall.

Dr. McCarty is based in the Lynda K. and David M. Underwood Center for Digestive Disorders, Houston Methodist Hospital. Dr. Mansour is based in the section of gastroenterology, Baylor College of Medicine, Houston. Dr. McCarty reports no conflicts of interest. Dr. Mansour reports having been a consultant for Iterative Health.

References

1. Repici A, et al. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology. 2020 Aug. doi: 10.1053/j.gastro.2020.04.062.

2. Repici A, et al. Artificial intelligence and colonoscopy experience: Lessons from two randomised trials. Gut. Apr 2022. doi: 10.1136/gutjnl-2021-324471.

3. Wallace MB, et al. Impact of artificial intelligence on miss rate of colorectal neoplasia. Gastroenterology 2022 Jul. doi: 10.1053/j.gastro.2022.03.007.

4. United States Food and Drug Administration (FDA). GI Genius FDA Approval [April 9, 2021]. Accessed January 5, 2022. Available at: www.accessdata.fda.gov/cdrh_docs/pdf21/K211951.pdf.

5. Maas MHJ, et al. A computer-aided polyp detection system in screening and surveillance colonoscopy: An international, multicentre, randomised, tandem trial. Lancet Digit Health. 2024 Mar. doi: 10.1016/S2589-7500(23)00242-X.

6. Ladabaum U, et al. Computer-aided detection of polyps does not improve colonoscopist performance in a pragmatic implementation trial. Gastroenterology. 2023 Mar. doi: 10.1053/j.gastro.2022.12.004.

7. Wei MT, et al. Evaluation of computer-aided detection during colonoscopy in the community (AI-SEE): A multicenter randomized clinical trial. Am J Gastroenterol. 2023 Oct. doi: 10.14309/ajg.0000000000002239.

8. de Groof J, et al. The Argos project: The development of a computer-aided detection system to improve detection of Barrett’s neoplasia on white light endoscopy. United European Gastroenterol J. 2019 May. doi: 10.1177/2050640619837443.

9. Kanesaka T, et al. Computer-aided diagnosis for identifying and delineating early gastric cancers in magnifying narrow-band imaging. Gastrointest Endosc. 2018 May. doi: 10.1016/j.gie.2017.11.029.

10. Sahafi A, et al. Edge artificial intelligence wireless video capsule endoscopy. Sci Rep. 2022 Aug. doi: 10.1038/s41598-022-17502-7.

11. Njei B, et al. Artificial intelligence in endoscopic imaging for detection of malignant biliary strictures and cholangiocarcinoma: A systematic review. Ann Gastroenterol. 2023 Mar-Apr. doi: 10.20524/aog.2023.0779.

12. Ebigbo A, et al. Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm. Gut. 2022 Dec. doi: 10.1136/gutjnl-2021-326470.

13. Cao J, et al. Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study. Nat Commun. 2023 Oct. doi: 10.1038/s41467-023-42451-8.

The Promise and Challenges of AI in Hepatology

BY BASILE NJEI, MD, MPH, PHD; YAZAN A. AL-AJLOUNI, MPHIL

In the dynamic realm of medicine, artificial intelligence (AI) emerges as a transformative force, notably within hepatology. The discipline of hepatology, dedicated to liver and related organ diseases, is ripe for AI’s promise to revolutionize diagnostics and treatment, pushing toward a future of precision medicine. Yet, the path to fully realizing AI’s potential in hepatology is laced with data, ethical, and integration challenges.

The application of AI, particularly in histopathology, significantly enhances disease diagnosis and staging in hepatology. AI-driven approaches remedy traditional histopathological challenges, such as interpretative variability, providing more consistent and accurate disease analyses. This is especially evident in conditions like metabolic dysfunction-associated steatohepatitis (MASH) and hepatocellular carcinoma (HCC), where AI aids in identifying critical gene signatures, thereby refining therapy selection.

Njei_Basile_CT_web.jpg

Similarly, deep learning (DL), a branch of AI, has attracted significant interest globally, particularly in image recognition. AI’s incorporation into medical imaging marks a significant advancement, enabling early detection of malignancies like HCC and improving diagnostics in steatotic liver disease through enhanced imaging analyses using convolutional neural networks (CNN). The abundance of imaging data alongside clinical outcomes has catalyzed AI’s integration into radiology, leading to the swift growth of radiomics as a novel domain in medical research.

AI has also been shown to identify nuanced alterations in electrocardiograms (EKGs) associated with liver conditions, potentially detecting the progression of liver diseases at an earlier stage than currently possible. By leveraging complex algorithms and machine learning, AI can analyze EKG patterns with a precision and depth unattainable through traditional manual interpretation. Given that liver diseases, such as cirrhosis or hepatitis, can induce subtle cardiac changes long before other clinical symptoms manifest, early detection through AI-enhanced EKG analysis could lead to timely interventions, potentially halting or reversing disease progression. This approach further enriches our understanding of the intricate interplay between liver function and cardiac health, highlighting the potential for AI to transform not just liver disease diagnostics but also to foster a more integrated approach to patient care.

Al_Ajlouni_Yazan_NY_web.jpg

Beyond diagnostics, the burgeoning field of generative AI introduces groundbreaking possibilities in treatment planning and patient education, particularly for chronic conditions like cirrhosis. Generative AI produces original content, including text, visuals, and music, by identifying and learning patterns from its training data. When it leverages large language models (LLMs), it entails training on vast collections of textual data and using AI models characterized by many parameters. A notable instance of generative AI employing LLMs is ChatGPT (General Pretrained Transformers). By simulating disease progression and treatment outcomes, generative AI can foster personalized treatment strategies and empower patients with knowledge about their health trajectories. Yet, realizing these potential demands requires overcoming data quality and interpretability challenges, and ensuring AI outputs are accessible and actionable for clinicians and patients.

Despite these advancements, leveraging AI in hepatology is not devoid of hurdles. The development and training of AI models require extensive and diverse datasets, raising concerns about data privacy and ethical use. Addressing these concerns is paramount for successfully integrating AI into clinical hepatology practice, necessitating transparent algorithmic processes and stringent ethical standards. Ethical considerations are central to AI’s integration into hepatology. Algorithmic biases, patient privacy, and the impact of AI-driven decisions underscore the need for cautious AI deployment. Developing transparent, understandable algorithms and establishing ethical guidelines for AI use are critical steps towards ethically leveraging AI in patient care.

In conclusion, AI’s integration into hepatology holds tremendous promise for advancing patient care through enhanced diagnostics, treatment planning, and patient education. Overcoming the associated challenges, including ethical concerns, data diversity, and algorithm interpretability, is crucial. As the hepatology community navigates this technological evolution, a balanced approach that marries technological advancements with ethical stewardship will be key to harnessing AI’s full potential, ensuring it serves the best interests of patients and propels the field of hepatology into the future.

We predict a trajectory of increased use and adoption of AI in hepatology. AI in hepatology is likely to meet the test of pervasiveness, improvement, and innovation. The adoption of AI in routine hepatology diagnosis and management will likely follow Amara’s law and the five stages of the hype cycle. We believe that we are still in the infant stages of adopting AI technology in hepatology, and this phase may last 5 years before there is a peak of inflated expectations. The trough of disillusionment and slopes of enlightenment may only be observed in the next decades.

Dr. Njei is based in the Section of Digestive Diseases, Yale School of Medicine, New Haven, Conn. Mr. Al-Ajlouni is a senior medical student at New York Medical College School of Medicine, Valhalla, N.Y. They have no conflicts of interest to declare.

Sources

Taylor-Weiner A, et al. A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH. Hepatology. 2021 Jul. doi: 10.1002/hep.31750.

Zeng Q, et al. Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology. J Hepatol. 2022 Jul. doi: 10.1016/j.jhep.2022.01.018.

Ahn JC, et al. Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis. Am J Gastroenterol. 2022 Mar. doi: 10.14309/ajg.0000000000001617.

Nduma BN, et al. The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review. Cureus. 2023 Dec 15. doi: 10.7759/cureus.50601.

Dear colleagues,

Since our prior Perspectives piece on artificial intelligence (AI) in GI and Hepatology in 2022, the field has seen almost exponential growth. Expectations are high that AI will revolutionize our field and significantly improve patient care. But as the global discussion on AI has shown, there are real challenges with adoption, including issues with accuracy, reliability, and privacy.

In this issue, Dr. Nabil M. Mansour and Dr. Thomas R. McCarty explore the current and future impact of AI on gastroenterology, while Dr. Basile Njei and Yazan A. Al Ajlouni assess its role in hepatology. We hope these pieces will help your discussions in incorporating or researching AI for use in your own practices. We welcome your thoughts on this issue on X @AGA_GIHN.

Gyanprakash A. Ketwaroo, MD, MSc, is associate professor of medicine, Yale University, New Haven, Conn., and chief of endoscopy at West Haven (Conn.) VA Medical Center. He is an associate editor for GI & Hepatology News.

Artificial Intelligence in Gastrointestinal Endoscopy

BY THOMAS R. MCCARTY, MD, MPH; NABIL M. MANSOUR, MD

The last few decades have seen an exponential increase and interest in the role of artificial intelligence (AI) and adoption of deep learning algorithms within healthcare and patient care services. The field of gastroenterology and endoscopy has similarly seen a tremendous uptake in acceptance and implementation of AI for a variety of gastrointestinal conditions. The spectrum of AI-based applications includes detection or diagnostic-based as well as therapeutic assistance tools. From the first US Food and Drug Administration (FDA)-approved device that uses machine learning to assist clinicians in detecting lesions during colonoscopy, to other more innovative machine learning techniques for small bowel, esophageal, and hepatobiliary conditions, AI has dramatically changed the landscape of gastrointestinal endoscopy.

Mansour_Nabil_M_HOUSTON_web.jpg

Ultimately, this data led to FDA approval of the CADe system GI Genius (Medtronic, Dublin, Ireland) in 2021.⁴ Additional systems have since been FDA approved or 510(k) cleared including Endoscreener (Wision AI, Shanghai, China), SKOUT (Iterative Health, Cambridge, Massachusetts), MAGENTIQ-COLO (MAGENTIQ-EYE LTD, Haifa, Israel), and CAD EYE (Fujifilm, Tokyo), all of which have shown increased ADR and/or increased APC and/or reduced adenoma miss rates in randomized trials.⁵

Yet despite the promise of improved quality and subsequent translation to better patient outcomes, there has been a noticeable disconnect between RCT data and more real-world literature.⁶ In a recent study, no improvement was seen in ADR after implementation of a CADe system for colorectal cancer screening — including both higher and lower-ADR performers. Looking at change over time after implementation, CADe had no positive effect in any group over time, divergent from early RCT data. In a more recent multicenter, community-based RCT study, again CADe did not result in a statistically significant difference in the number of adenomas detected.⁷ The differences between some of these more recent “real-world” studies vs the majority of data from RCTs raise important questions regarding the potential of bias (due to unblinding) in prospective trials, as well as the role of the human-AI interaction.

Importantly for RCT data, both cohorts in these studies met adequate ADR benchmarks, though it remains unclear whether a truly increased ADR necessitates better patient outcomes — is higher always better? In addition, an important consideration with evaluating any AI/CADe system is that they often undergo frequent updates, each promising improved accuracy, sensitivity, and specificity. This is an interesting dilemma and raises questions about the enduring relevance of studies conducted using an outdated version of a CADe system.

Additional unanswered questions regarding an ideal ADR for implementation, preferred patient populations for screening (especially for younger individuals), and the role and adoption of computer-aided polyp diagnosis/characterization (CADx) within the United States remain. Furthermore, questions regarding procedural withdrawal time, impact on sessile serrated lesion detection, cost-effectiveness, and preferred adoption strategies have begun to be explored, though require more data to better define a best practice approach. Ultimately, answers to some of these unknowns may explain the discordant results and help guide future implementation measures.

Innovative applications for alternative gastrointestinal conditions

Given the fervor and excitement, as well as the outcomes associated with AI-based colorectal screening, it is not surprising these techniques have been expanded to other gastrointestinal conditions. At this time, all of these are fledgling, mostly single-center tools, not yet ready for widespread adoption. Nonetheless, these represent a potentially important step forward for difficult-to-manage gastrointestinal diseases.

Machine learning CADe systems have been developed to help identify early Barrett’s neoplasia, depth and invasion of gastric cancer, as well as lesion detection in small bowel video capsule endoscopy.^8-10 Endoscopic retrograde cholangiopancreatography (ERCP)-based applications for cholangiocarcinoma and indeterminate stricture diagnosis have also been studied.¹¹ Additional AI-based algorithms have been employed for complex procedures such as endoscopic submucosal dissection (ESD) or peroral endoscopic myotomy (POEM) to delineate vessels, better define tissue planes for dissection, and visualize landmark structures.^12,13 Furthermore, AI-based scope guidance/manipulation, bleeding detection, landmark identification, and lesion detection have the potential to revolutionize endoscopic training and education. The impact that generative AI can potentially have on clinical practice is also an exciting prospect that warrants further investigation.

Artificial intelligence adoption in clinical practice

Clinical practice with regard to AI and colorectal cancer screening largely mirrors the disconnect in the current literature, with “believers” and “non-believers” as well as innovators and early adopters alongside laggards. In our own academic practices, we continue to struggle with the adoption and standardized implementation of AI-based colorectal cancer CADe systems, despite the RCT data showing positive results. It is likely that AI uptake will follow the technology predictions of Amara’s Law — i.e., individuals tend to overestimate the short-term impact of new technologies while underestimating long-term effects. In the end, more widespread adoption in community practice and larger scale real-world clinical outcomes studies are likely to determine the true impact of these exciting technologies. For other, less established AI-based tools, more data are currently required.

Conclusions

Ultimately, AI-based algorithms are likely here to stay, with continued improvement and evolution to occur based on provider feedback and patient care needs. Current tools, while not all-encompassing, have the potential to dramatically change the landscape of endoscopic training, diagnostic evaluation, and therapeutic care. It is critically important that relevant stakeholders, both endoscopists and patients, be involved in future applications and design to improve efficiency and quality outcomes overall.

Dr. McCarty is based in the Lynda K. and David M. Underwood Center for Digestive Disorders, Houston Methodist Hospital. Dr. Mansour is based in the section of gastroenterology, Baylor College of Medicine, Houston. Dr. McCarty reports no conflicts of interest. Dr. Mansour reports having been a consultant for Iterative Health.

References

1. Repici A, et al. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology. 2020 Aug. doi: 10.1053/j.gastro.2020.04.062.

2. Repici A, et al. Artificial intelligence and colonoscopy experience: Lessons from two randomised trials. Gut. Apr 2022. doi: 10.1136/gutjnl-2021-324471.

3. Wallace MB, et al. Impact of artificial intelligence on miss rate of colorectal neoplasia. Gastroenterology 2022 Jul. doi: 10.1053/j.gastro.2022.03.007.

4. United States Food and Drug Administration (FDA). GI Genius FDA Approval [April 9, 2021]. Accessed January 5, 2022. Available at: www.accessdata.fda.gov/cdrh_docs/pdf21/K211951.pdf.

5. Maas MHJ, et al. A computer-aided polyp detection system in screening and surveillance colonoscopy: An international, multicentre, randomised, tandem trial. Lancet Digit Health. 2024 Mar. doi: 10.1016/S2589-7500(23)00242-X.

6. Ladabaum U, et al. Computer-aided detection of polyps does not improve colonoscopist performance in a pragmatic implementation trial. Gastroenterology. 2023 Mar. doi: 10.1053/j.gastro.2022.12.004.

7. Wei MT, et al. Evaluation of computer-aided detection during colonoscopy in the community (AI-SEE): A multicenter randomized clinical trial. Am J Gastroenterol. 2023 Oct. doi: 10.14309/ajg.0000000000002239.

8. de Groof J, et al. The Argos project: The development of a computer-aided detection system to improve detection of Barrett’s neoplasia on white light endoscopy. United European Gastroenterol J. 2019 May. doi: 10.1177/2050640619837443.

9. Kanesaka T, et al. Computer-aided diagnosis for identifying and delineating early gastric cancers in magnifying narrow-band imaging. Gastrointest Endosc. 2018 May. doi: 10.1016/j.gie.2017.11.029.

10. Sahafi A, et al. Edge artificial intelligence wireless video capsule endoscopy. Sci Rep. 2022 Aug. doi: 10.1038/s41598-022-17502-7.

11. Njei B, et al. Artificial intelligence in endoscopic imaging for detection of malignant biliary strictures and cholangiocarcinoma: A systematic review. Ann Gastroenterol. 2023 Mar-Apr. doi: 10.20524/aog.2023.0779.

12. Ebigbo A, et al. Vessel and tissue recognition during third-space endoscopy using a deep learning algorithm. Gut. 2022 Dec. doi: 10.1136/gutjnl-2021-326470.

13. Cao J, et al. Intelligent surgical workflow recognition for endoscopic submucosal dissection with real-time animal study. Nat Commun. 2023 Oct. doi: 10.1038/s41467-023-42451-8.

The Promise and Challenges of AI in Hepatology

BY BASILE NJEI, MD, MPH, PHD; YAZAN A. AL-AJLOUNI, MPHIL

In the dynamic realm of medicine, artificial intelligence (AI) emerges as a transformative force, notably within hepatology. The discipline of hepatology, dedicated to liver and related organ diseases, is ripe for AI’s promise to revolutionize diagnostics and treatment, pushing toward a future of precision medicine. Yet, the path to fully realizing AI’s potential in hepatology is laced with data, ethical, and integration challenges.

The application of AI, particularly in histopathology, significantly enhances disease diagnosis and staging in hepatology. AI-driven approaches remedy traditional histopathological challenges, such as interpretative variability, providing more consistent and accurate disease analyses. This is especially evident in conditions like metabolic dysfunction-associated steatohepatitis (MASH) and hepatocellular carcinoma (HCC), where AI aids in identifying critical gene signatures, thereby refining therapy selection.

Njei_Basile_CT_web.jpg

Similarly, deep learning (DL), a branch of AI, has attracted significant interest globally, particularly in image recognition. AI’s incorporation into medical imaging marks a significant advancement, enabling early detection of malignancies like HCC and improving diagnostics in steatotic liver disease through enhanced imaging analyses using convolutional neural networks (CNN). The abundance of imaging data alongside clinical outcomes has catalyzed AI’s integration into radiology, leading to the swift growth of radiomics as a novel domain in medical research.

AI has also been shown to identify nuanced alterations in electrocardiograms (EKGs) associated with liver conditions, potentially detecting the progression of liver diseases at an earlier stage than currently possible. By leveraging complex algorithms and machine learning, AI can analyze EKG patterns with a precision and depth unattainable through traditional manual interpretation. Given that liver diseases, such as cirrhosis or hepatitis, can induce subtle cardiac changes long before other clinical symptoms manifest, early detection through AI-enhanced EKG analysis could lead to timely interventions, potentially halting or reversing disease progression. This approach further enriches our understanding of the intricate interplay between liver function and cardiac health, highlighting the potential for AI to transform not just liver disease diagnostics but also to foster a more integrated approach to patient care.

Al_Ajlouni_Yazan_NY_web.jpg

Beyond diagnostics, the burgeoning field of generative AI introduces groundbreaking possibilities in treatment planning and patient education, particularly for chronic conditions like cirrhosis. Generative AI produces original content, including text, visuals, and music, by identifying and learning patterns from its training data. When it leverages large language models (LLMs), it entails training on vast collections of textual data and using AI models characterized by many parameters. A notable instance of generative AI employing LLMs is ChatGPT (General Pretrained Transformers). By simulating disease progression and treatment outcomes, generative AI can foster personalized treatment strategies and empower patients with knowledge about their health trajectories. Yet, realizing these potential demands requires overcoming data quality and interpretability challenges, and ensuring AI outputs are accessible and actionable for clinicians and patients.

Despite these advancements, leveraging AI in hepatology is not devoid of hurdles. The development and training of AI models require extensive and diverse datasets, raising concerns about data privacy and ethical use. Addressing these concerns is paramount for successfully integrating AI into clinical hepatology practice, necessitating transparent algorithmic processes and stringent ethical standards. Ethical considerations are central to AI’s integration into hepatology. Algorithmic biases, patient privacy, and the impact of AI-driven decisions underscore the need for cautious AI deployment. Developing transparent, understandable algorithms and establishing ethical guidelines for AI use are critical steps towards ethically leveraging AI in patient care.

In conclusion, AI’s integration into hepatology holds tremendous promise for advancing patient care through enhanced diagnostics, treatment planning, and patient education. Overcoming the associated challenges, including ethical concerns, data diversity, and algorithm interpretability, is crucial. As the hepatology community navigates this technological evolution, a balanced approach that marries technological advancements with ethical stewardship will be key to harnessing AI’s full potential, ensuring it serves the best interests of patients and propels the field of hepatology into the future.

We predict a trajectory of increased use and adoption of AI in hepatology. AI in hepatology is likely to meet the test of pervasiveness, improvement, and innovation. The adoption of AI in routine hepatology diagnosis and management will likely follow Amara’s law and the five stages of the hype cycle. We believe that we are still in the infant stages of adopting AI technology in hepatology, and this phase may last 5 years before there is a peak of inflated expectations. The trough of disillusionment and slopes of enlightenment may only be observed in the next decades.

Dr. Njei is based in the Section of Digestive Diseases, Yale School of Medicine, New Haven, Conn. Mr. Al-Ajlouni is a senior medical student at New York Medical College School of Medicine, Valhalla, N.Y. They have no conflicts of interest to declare.

Sources

Taylor-Weiner A, et al. A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH. Hepatology. 2021 Jul. doi: 10.1002/hep.31750.

Zeng Q, et al. Artificial intelligence predicts immune and inflammatory gene signatures directly from hepatocellular carcinoma histology. J Hepatol. 2022 Jul. doi: 10.1016/j.jhep.2022.01.018.

Ahn JC, et al. Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis. Am J Gastroenterol. 2022 Mar. doi: 10.14309/ajg.0000000000001617.

Nduma BN, et al. The Application of Artificial Intelligence (AI)-Based Ultrasound for the Diagnosis of Fatty Liver Disease: A Systematic Review. Cureus. 2023 Dec 15. doi: 10.7759/cureus.50601.

The use of glucagon-like peptide-1 receptor agonists (GLP-1 RAs) may lead to an increased risk for aspiration pneumonia after endoscopic procedures, according to a new large population-based study.

In June 2023, the American Society of Anesthesiologists (ASA) recommended holding GLP-1 RAs before an endoscopic or surgical procedure to reduce the risk for complications associated with anesthesia and delayed stomach emptying.

In response, the American Gastroenterological Association (AGA) published a rapid clinical practice update in November 2023 that found insufficient evidence to support patients stopping the medications before endoscopic procedures.

“It is known that GLP-1 RAs significantly reduce the motility of the stomach and small bowel. As more and more patients are being started on GLP-1 RAs at higher doses and longer half-life, the question became whether the current recommended fasting durations are enough to reasonably assume the stomach is empty prior to procedures that require sedation,” said senior author Ali Rezaie, MD, medical director of the GI Motility Program at Cedars-Sinai Medical Center in Los Angeles.

“We wanted to see if these medications in fact increased the chance of aspiration before the ASA suggestion went into effect,” he said. “However, this is not an easy task, as aspiration is a rare event and a large sample size is needed to confidently answer that question. That is why we evaluated nearly 1 million cases.”

The study was published online in Gastroenterology.
 

Analyzing GLP-1 RA Use

Dr. Rezaie and colleagues conducted a population-based, retrospective cohort study of the TriNetX dataset, which includes 114 million deidentified individual health records from 80 healthcare organizations. The research team analyzed nearly 1 million records for adult patients between ages 21 and 70 who underwent upper and lower endoscopies between January 2018 and December 2020.

Rezaie_Ali_CA_web.jpg

The researchers defined GLP-1 RA users as those who had the medication for more than 6 months and two or more refills within 6 months before the procedure. They adjusted for 59 factors that could affect gut motility or aspiration risks, such as obesity, numerous chronic diseases, and dozens of medications. The primary outcome was aspiration pneumonia within a month after the procedure.

Among 963,184 patients who underwent endoscopy, 46,935 (4.9%) were considered GLP-1 RA users. Among those, 20,099 GLP-1 RA users met the inclusion criteria and had their results compared with non-GLP-1 RA users.

After propensity score matching for the 59 potential confounders, GLP-1 RA use had a higher incidence rate of aspiration pneumonia (0.83% vs 0.63%) and was associated with a significantly higher risk for aspiration pneumonia, with a hazard ratio (HR) of 1.33.

An even higher risk was seen among patients with propofol-assisted endoscopies (HR, 1.49) but not among those without propofol (HR, 1.31).

In a subgroup analysis based on endoscopy type, an elevated risk was observed among patients who underwent upper endoscopy (HR, 1.82) and combined upper and lower endoscopy (HR, 2.26) but not lower endoscopy (HR, 0.56).

“The results were not necessarily surprising given the mechanism of action of GLP-1 RAs. However, for the first time, this was shown with a clinically relevant outcome, such as aspiration pneumonia,” Dr. Rezaie said. “Aspiration during sedation can have devastating consequences, and the 0.2% difference in risk of aspiration can have a significant effect on healthcare as well.”

More than 20 million endoscopies are performed across the United States annually. Based on the assumption that about 3% of those patients are taking GLP-1 RAs, about 1200 aspiration cases per year can be prevented by raising awareness, he said.
 

Considering Next Steps

The varying risk profiles observed with separate sedation and endoscopy types point to a need for more tailored guidance in managing GLP-1 RA use before a procedure, the study authors wrote.

Although holding the medications before endoscopy may disrupt diabetes management, the potential increased risk for aspiration could justify a change in practice, particularly for upper endoscopy and propofol-associated procedures, they added.

At the same time, additional studies are needed to understand the optimal drug withholding windows before endoscopies and other procedures, they concluded.

“We will need more data on what is the optimal duration of holding GLP-1 RAs,” Dr. Rezaie said. “But given our data and current ASA guidance, stopping these medications prior to elective procedures is the safe thing to do.”

For now, AGA guidance remains the same as offered in the November 2023 update, suggesting an individual approach for each patient on a GLP-1 RA rather than a “blanket statement” on how to manage all patients taking these medications.

“Overall, I believe that this study is important, but we require more high-level data to inform clinical decision-making regarding patients using GLP-1 receptor agonists prior to gastrointestinal endoscopy,” said Andrew Y. Wang, MD, AGAF, chief of gastroenterology and hepatology and director of interventional endoscopy at the University of Virginia in Charlottesville.

Dr. Wang, who wasn’t involved with this study, coauthored the AGA rapid clinical practice update. He and colleagues advised continuing with a procedure as planned for patients on GLP-1 RAs who followed standard preprocedure fasting instructions and didn’t have nausea, vomiting, dyspepsia, or abdominal distention.

Wang_Andrew_VA_web.jpg

A version of this article appeared on Medscape.com.

The use of glucagon-like peptide-1 receptor agonists (GLP-1 RAs) may lead to an increased risk for aspiration pneumonia after endoscopic procedures, according to a new large population-based study.

In June 2023, the American Society of Anesthesiologists (ASA) recommended holding GLP-1 RAs before an endoscopic or surgical procedure to reduce the risk for complications associated with anesthesia and delayed stomach emptying.

In response, the American Gastroenterological Association (AGA) published a rapid clinical practice update in November 2023 that found insufficient evidence to support patients stopping the medications before endoscopic procedures.

“It is known that GLP-1 RAs significantly reduce the motility of the stomach and small bowel. As more and more patients are being started on GLP-1 RAs at higher doses and longer half-life, the question became whether the current recommended fasting durations are enough to reasonably assume the stomach is empty prior to procedures that require sedation,” said senior author Ali Rezaie, MD, medical director of the GI Motility Program at Cedars-Sinai Medical Center in Los Angeles.

“We wanted to see if these medications in fact increased the chance of aspiration before the ASA suggestion went into effect,” he said. “However, this is not an easy task, as aspiration is a rare event and a large sample size is needed to confidently answer that question. That is why we evaluated nearly 1 million cases.”

The study was published online in Gastroenterology.
 

Analyzing GLP-1 RA Use

Dr. Rezaie and colleagues conducted a population-based, retrospective cohort study of the TriNetX dataset, which includes 114 million deidentified individual health records from 80 healthcare organizations. The research team analyzed nearly 1 million records for adult patients between ages 21 and 70 who underwent upper and lower endoscopies between January 2018 and December 2020.

Rezaie_Ali_CA_web.jpg

The researchers defined GLP-1 RA users as those who had the medication for more than 6 months and two or more refills within 6 months before the procedure. They adjusted for 59 factors that could affect gut motility or aspiration risks, such as obesity, numerous chronic diseases, and dozens of medications. The primary outcome was aspiration pneumonia within a month after the procedure.

Among 963,184 patients who underwent endoscopy, 46,935 (4.9%) were considered GLP-1 RA users. Among those, 20,099 GLP-1 RA users met the inclusion criteria and had their results compared with non-GLP-1 RA users.

After propensity score matching for the 59 potential confounders, GLP-1 RA use had a higher incidence rate of aspiration pneumonia (0.83% vs 0.63%) and was associated with a significantly higher risk for aspiration pneumonia, with a hazard ratio (HR) of 1.33.

An even higher risk was seen among patients with propofol-assisted endoscopies (HR, 1.49) but not among those without propofol (HR, 1.31).

In a subgroup analysis based on endoscopy type, an elevated risk was observed among patients who underwent upper endoscopy (HR, 1.82) and combined upper and lower endoscopy (HR, 2.26) but not lower endoscopy (HR, 0.56).

“The results were not necessarily surprising given the mechanism of action of GLP-1 RAs. However, for the first time, this was shown with a clinically relevant outcome, such as aspiration pneumonia,” Dr. Rezaie said. “Aspiration during sedation can have devastating consequences, and the 0.2% difference in risk of aspiration can have a significant effect on healthcare as well.”

More than 20 million endoscopies are performed across the United States annually. Based on the assumption that about 3% of those patients are taking GLP-1 RAs, about 1200 aspiration cases per year can be prevented by raising awareness, he said.
 

Considering Next Steps

The varying risk profiles observed with separate sedation and endoscopy types point to a need for more tailored guidance in managing GLP-1 RA use before a procedure, the study authors wrote.

Although holding the medications before endoscopy may disrupt diabetes management, the potential increased risk for aspiration could justify a change in practice, particularly for upper endoscopy and propofol-associated procedures, they added.

At the same time, additional studies are needed to understand the optimal drug withholding windows before endoscopies and other procedures, they concluded.

“We will need more data on what is the optimal duration of holding GLP-1 RAs,” Dr. Rezaie said. “But given our data and current ASA guidance, stopping these medications prior to elective procedures is the safe thing to do.”

For now, AGA guidance remains the same as offered in the November 2023 update, suggesting an individual approach for each patient on a GLP-1 RA rather than a “blanket statement” on how to manage all patients taking these medications.

“Overall, I believe that this study is important, but we require more high-level data to inform clinical decision-making regarding patients using GLP-1 receptor agonists prior to gastrointestinal endoscopy,” said Andrew Y. Wang, MD, AGAF, chief of gastroenterology and hepatology and director of interventional endoscopy at the University of Virginia in Charlottesville.

Dr. Wang, who wasn’t involved with this study, coauthored the AGA rapid clinical practice update. He and colleagues advised continuing with a procedure as planned for patients on GLP-1 RAs who followed standard preprocedure fasting instructions and didn’t have nausea, vomiting, dyspepsia, or abdominal distention.

Wang_Andrew_VA_web.jpg

A version of this article appeared on Medscape.com.

The use of glucagon-like peptide-1 receptor agonists (GLP-1 RAs) may lead to an increased risk for aspiration pneumonia after endoscopic procedures, according to a new large population-based study.

In June 2023, the American Society of Anesthesiologists (ASA) recommended holding GLP-1 RAs before an endoscopic or surgical procedure to reduce the risk for complications associated with anesthesia and delayed stomach emptying.

In response, the American Gastroenterological Association (AGA) published a rapid clinical practice update in November 2023 that found insufficient evidence to support patients stopping the medications before endoscopic procedures.

“It is known that GLP-1 RAs significantly reduce the motility of the stomach and small bowel. As more and more patients are being started on GLP-1 RAs at higher doses and longer half-life, the question became whether the current recommended fasting durations are enough to reasonably assume the stomach is empty prior to procedures that require sedation,” said senior author Ali Rezaie, MD, medical director of the GI Motility Program at Cedars-Sinai Medical Center in Los Angeles.

“We wanted to see if these medications in fact increased the chance of aspiration before the ASA suggestion went into effect,” he said. “However, this is not an easy task, as aspiration is a rare event and a large sample size is needed to confidently answer that question. That is why we evaluated nearly 1 million cases.”

The study was published online in Gastroenterology.
 

Analyzing GLP-1 RA Use

Dr. Rezaie and colleagues conducted a population-based, retrospective cohort study of the TriNetX dataset, which includes 114 million deidentified individual health records from 80 healthcare organizations. The research team analyzed nearly 1 million records for adult patients between ages 21 and 70 who underwent upper and lower endoscopies between January 2018 and December 2020.

Rezaie_Ali_CA_web.jpg

The researchers defined GLP-1 RA users as those who had the medication for more than 6 months and two or more refills within 6 months before the procedure. They adjusted for 59 factors that could affect gut motility or aspiration risks, such as obesity, numerous chronic diseases, and dozens of medications. The primary outcome was aspiration pneumonia within a month after the procedure.

Among 963,184 patients who underwent endoscopy, 46,935 (4.9%) were considered GLP-1 RA users. Among those, 20,099 GLP-1 RA users met the inclusion criteria and had their results compared with non-GLP-1 RA users.

After propensity score matching for the 59 potential confounders, GLP-1 RA use had a higher incidence rate of aspiration pneumonia (0.83% vs 0.63%) and was associated with a significantly higher risk for aspiration pneumonia, with a hazard ratio (HR) of 1.33.

An even higher risk was seen among patients with propofol-assisted endoscopies (HR, 1.49) but not among those without propofol (HR, 1.31).

In a subgroup analysis based on endoscopy type, an elevated risk was observed among patients who underwent upper endoscopy (HR, 1.82) and combined upper and lower endoscopy (HR, 2.26) but not lower endoscopy (HR, 0.56).

“The results were not necessarily surprising given the mechanism of action of GLP-1 RAs. However, for the first time, this was shown with a clinically relevant outcome, such as aspiration pneumonia,” Dr. Rezaie said. “Aspiration during sedation can have devastating consequences, and the 0.2% difference in risk of aspiration can have a significant effect on healthcare as well.”

More than 20 million endoscopies are performed across the United States annually. Based on the assumption that about 3% of those patients are taking GLP-1 RAs, about 1200 aspiration cases per year can be prevented by raising awareness, he said.
 

Considering Next Steps

The varying risk profiles observed with separate sedation and endoscopy types point to a need for more tailored guidance in managing GLP-1 RA use before a procedure, the study authors wrote.

Although holding the medications before endoscopy may disrupt diabetes management, the potential increased risk for aspiration could justify a change in practice, particularly for upper endoscopy and propofol-associated procedures, they added.

At the same time, additional studies are needed to understand the optimal drug withholding windows before endoscopies and other procedures, they concluded.

“We will need more data on what is the optimal duration of holding GLP-1 RAs,” Dr. Rezaie said. “But given our data and current ASA guidance, stopping these medications prior to elective procedures is the safe thing to do.”

For now, AGA guidance remains the same as offered in the November 2023 update, suggesting an individual approach for each patient on a GLP-1 RA rather than a “blanket statement” on how to manage all patients taking these medications.

“Overall, I believe that this study is important, but we require more high-level data to inform clinical decision-making regarding patients using GLP-1 receptor agonists prior to gastrointestinal endoscopy,” said Andrew Y. Wang, MD, AGAF, chief of gastroenterology and hepatology and director of interventional endoscopy at the University of Virginia in Charlottesville.

Dr. Wang, who wasn’t involved with this study, coauthored the AGA rapid clinical practice update. He and colleagues advised continuing with a procedure as planned for patients on GLP-1 RAs who followed standard preprocedure fasting instructions and didn’t have nausea, vomiting, dyspepsia, or abdominal distention.

Wang_Andrew_VA_web.jpg

A version of this article appeared on Medscape.com.

American Gastroenterological Association (AGA) has published a clinical practice update detailing best practices for performing a high-quality upper endoscopy exam.

The update, authored by Satish Nagula, MD, of Icahn School of Medicine at Mount Sinai, New York, NY, and colleagues, includes nine pieces of best practice advice that address procedure optimization, evaluation of suspected premalignancy, and postprocedure follow-up evaluation.

Nagula_Satish_NY_web.jpg

“Defining what constitutes a high-quality esophagogastroduodenoscopy (EGD) poses somewhat of a challenge because the spectrum of indications and the breadth of benign and (pre)malignant disease pathology in the upper GI tract is very broad,” the update panelists wrote in Clinical Gastroenterology and Hepatology. “Standardizing the measures defining a high-quality upper endoscopic examination is one of the first steps for assessing quality.”
 

Preprocedure Recommendations

Dr. Nagula and colleagues first emphasized that EGD should be performed for an appropriate indication, citing a recent meta-analysis that found 21.7% of upper endoscopy procedures were performed for an inappropriate indication. Of note, diagnostic yields were 42% higher in procedures performed for an appropriate indication.

After ensuring an appropriate indication, the update also encourages clinicians to inform patients of the various benefits, risks, and alternatives of the procedure prior to providing consent.
 

Intraprocedure Recommendations

During the procedure, endoscopists should take several steps to ensure optimal visualization of tissues, according to the update.

First, a high-definition (HD) white-light endoscopy system should be employed.

“Although HD imaging is a standard feature of newer-generation endoscopes, legacy standard-definition scopes remain in use,” Dr. Nagula and colleagues noted. “Moreover, to provide true HD image resolution, each component of the system (eg, the endoscope video chip, the processor, the monitor, and transmission cables) must be HD compatible.”

This HD-compatible system should be coupled with image-enhancing technology to further improve lesion detection. In Barrett’s esophagus, the panelists noted, image enhancement can improve lesion detection as much as 20%.

They predicted that AI-assisted software may boost detection rates even higher: “Computer-aided detection and computer-aided diagnosis systems for upper endoscopy are still in the early phases of development but do show similar promise for improving the detection and characterization of upper GI tract neoplasia.”

Beyond selection of best available technologies, the update encourages more fundamental strategies to improve visualization, including mucosal cleansing and insufflation, with sufficient time spent inspecting the foregut mucosa via anterograde and retroflexed views.

Where appropriate, standardized biopsy protocols should be followed to evaluate and manage foregut conditions.
 

Postprocedure Recommendations

After the procedure, endoscopists should offer patients management recommendations based on the endoscopic findings and, if necessary, notify them that more recommendations may be forthcoming based on histopathology results, according to the update.

Similarly, endoscopists should follow established surveillance intervals for future procedures, with modifications made as needed, based on histopathology findings.
 

Document, Document, Document

Throughout the update, Dr. Nagula and colleagues repeatedly emphasize the importance of documentation, from preprocedural discussions with patients through planned surveillance schedules.

However, the recommendations are clear about “weighing the practical implications” of “onerous” documentation, particularly photodocumentation requirements. For instance, the authors note that “there are some scenarios in which more rigorous photodocumentation standards during upper endoscopy should be considered, such as patients with risk factors for neoplasia,” but at the very least “photodocumentation of any suspicious abnormalities, ideally with annotations, is strongly advised.”
 

Moving Toward Quality Standardization for Upper Endoscopy

“These best practice advice statements are intended to improve measurable clinical, patient-reported, and economic healthcare outcomes and are not meant to put an additional burden on endoscopists,” the panelists wrote. “Ideally, future research will set threshold indicators of adherence to these best practices that optimally are associated with these aforementioned objective outcomes.”

This update was commissioned and approved by AGA. The update panelists disclosed relationships with Covidien LP, Fujifilm USA, Mahana Therapeutics, and others.

American Gastroenterological Association (AGA) has published a clinical practice update detailing best practices for performing a high-quality upper endoscopy exam.

The update, authored by Satish Nagula, MD, of Icahn School of Medicine at Mount Sinai, New York, NY, and colleagues, includes nine pieces of best practice advice that address procedure optimization, evaluation of suspected premalignancy, and postprocedure follow-up evaluation.

Nagula_Satish_NY_web.jpg

“Defining what constitutes a high-quality esophagogastroduodenoscopy (EGD) poses somewhat of a challenge because the spectrum of indications and the breadth of benign and (pre)malignant disease pathology in the upper GI tract is very broad,” the update panelists wrote in Clinical Gastroenterology and Hepatology. “Standardizing the measures defining a high-quality upper endoscopic examination is one of the first steps for assessing quality.”
 

Preprocedure Recommendations

Dr. Nagula and colleagues first emphasized that EGD should be performed for an appropriate indication, citing a recent meta-analysis that found 21.7% of upper endoscopy procedures were performed for an inappropriate indication. Of note, diagnostic yields were 42% higher in procedures performed for an appropriate indication.

After ensuring an appropriate indication, the update also encourages clinicians to inform patients of the various benefits, risks, and alternatives of the procedure prior to providing consent.
 

Intraprocedure Recommendations

During the procedure, endoscopists should take several steps to ensure optimal visualization of tissues, according to the update.

First, a high-definition (HD) white-light endoscopy system should be employed.

“Although HD imaging is a standard feature of newer-generation endoscopes, legacy standard-definition scopes remain in use,” Dr. Nagula and colleagues noted. “Moreover, to provide true HD image resolution, each component of the system (eg, the endoscope video chip, the processor, the monitor, and transmission cables) must be HD compatible.”

This HD-compatible system should be coupled with image-enhancing technology to further improve lesion detection. In Barrett’s esophagus, the panelists noted, image enhancement can improve lesion detection as much as 20%.

They predicted that AI-assisted software may boost detection rates even higher: “Computer-aided detection and computer-aided diagnosis systems for upper endoscopy are still in the early phases of development but do show similar promise for improving the detection and characterization of upper GI tract neoplasia.”

Beyond selection of best available technologies, the update encourages more fundamental strategies to improve visualization, including mucosal cleansing and insufflation, with sufficient time spent inspecting the foregut mucosa via anterograde and retroflexed views.

Where appropriate, standardized biopsy protocols should be followed to evaluate and manage foregut conditions.
 

Postprocedure Recommendations

After the procedure, endoscopists should offer patients management recommendations based on the endoscopic findings and, if necessary, notify them that more recommendations may be forthcoming based on histopathology results, according to the update.

Similarly, endoscopists should follow established surveillance intervals for future procedures, with modifications made as needed, based on histopathology findings.
 

Document, Document, Document

Throughout the update, Dr. Nagula and colleagues repeatedly emphasize the importance of documentation, from preprocedural discussions with patients through planned surveillance schedules.

However, the recommendations are clear about “weighing the practical implications” of “onerous” documentation, particularly photodocumentation requirements. For instance, the authors note that “there are some scenarios in which more rigorous photodocumentation standards during upper endoscopy should be considered, such as patients with risk factors for neoplasia,” but at the very least “photodocumentation of any suspicious abnormalities, ideally with annotations, is strongly advised.”
 

Moving Toward Quality Standardization for Upper Endoscopy

“These best practice advice statements are intended to improve measurable clinical, patient-reported, and economic healthcare outcomes and are not meant to put an additional burden on endoscopists,” the panelists wrote. “Ideally, future research will set threshold indicators of adherence to these best practices that optimally are associated with these aforementioned objective outcomes.”

This update was commissioned and approved by AGA. The update panelists disclosed relationships with Covidien LP, Fujifilm USA, Mahana Therapeutics, and others.

American Gastroenterological Association (AGA) has published a clinical practice update detailing best practices for performing a high-quality upper endoscopy exam.

The update, authored by Satish Nagula, MD, of Icahn School of Medicine at Mount Sinai, New York, NY, and colleagues, includes nine pieces of best practice advice that address procedure optimization, evaluation of suspected premalignancy, and postprocedure follow-up evaluation.

Nagula_Satish_NY_web.jpg

“Defining what constitutes a high-quality esophagogastroduodenoscopy (EGD) poses somewhat of a challenge because the spectrum of indications and the breadth of benign and (pre)malignant disease pathology in the upper GI tract is very broad,” the update panelists wrote in Clinical Gastroenterology and Hepatology. “Standardizing the measures defining a high-quality upper endoscopic examination is one of the first steps for assessing quality.”
 

Preprocedure Recommendations

Dr. Nagula and colleagues first emphasized that EGD should be performed for an appropriate indication, citing a recent meta-analysis that found 21.7% of upper endoscopy procedures were performed for an inappropriate indication. Of note, diagnostic yields were 42% higher in procedures performed for an appropriate indication.

After ensuring an appropriate indication, the update also encourages clinicians to inform patients of the various benefits, risks, and alternatives of the procedure prior to providing consent.
 

Intraprocedure Recommendations

During the procedure, endoscopists should take several steps to ensure optimal visualization of tissues, according to the update.

First, a high-definition (HD) white-light endoscopy system should be employed.

“Although HD imaging is a standard feature of newer-generation endoscopes, legacy standard-definition scopes remain in use,” Dr. Nagula and colleagues noted. “Moreover, to provide true HD image resolution, each component of the system (eg, the endoscope video chip, the processor, the monitor, and transmission cables) must be HD compatible.”

This HD-compatible system should be coupled with image-enhancing technology to further improve lesion detection. In Barrett’s esophagus, the panelists noted, image enhancement can improve lesion detection as much as 20%.

They predicted that AI-assisted software may boost detection rates even higher: “Computer-aided detection and computer-aided diagnosis systems for upper endoscopy are still in the early phases of development but do show similar promise for improving the detection and characterization of upper GI tract neoplasia.”

Beyond selection of best available technologies, the update encourages more fundamental strategies to improve visualization, including mucosal cleansing and insufflation, with sufficient time spent inspecting the foregut mucosa via anterograde and retroflexed views.

Where appropriate, standardized biopsy protocols should be followed to evaluate and manage foregut conditions.
 

Postprocedure Recommendations

After the procedure, endoscopists should offer patients management recommendations based on the endoscopic findings and, if necessary, notify them that more recommendations may be forthcoming based on histopathology results, according to the update.

Similarly, endoscopists should follow established surveillance intervals for future procedures, with modifications made as needed, based on histopathology findings.
 

Document, Document, Document

Throughout the update, Dr. Nagula and colleagues repeatedly emphasize the importance of documentation, from preprocedural discussions with patients through planned surveillance schedules.

However, the recommendations are clear about “weighing the practical implications” of “onerous” documentation, particularly photodocumentation requirements. For instance, the authors note that “there are some scenarios in which more rigorous photodocumentation standards during upper endoscopy should be considered, such as patients with risk factors for neoplasia,” but at the very least “photodocumentation of any suspicious abnormalities, ideally with annotations, is strongly advised.”
 

Moving Toward Quality Standardization for Upper Endoscopy

“These best practice advice statements are intended to improve measurable clinical, patient-reported, and economic healthcare outcomes and are not meant to put an additional burden on endoscopists,” the panelists wrote. “Ideally, future research will set threshold indicators of adherence to these best practices that optimally are associated with these aforementioned objective outcomes.”

This update was commissioned and approved by AGA. The update panelists disclosed relationships with Covidien LP, Fujifilm USA, Mahana Therapeutics, and others.

Power-washing is no longer just for blasting grimy driveways and stripping flaky paint. It’s good for work inside the gut, too.

In a proof-of-concept study, a “novel systematically directed high-pressure liquid spray,” delivered via the ERBEJET flexible probe, showed promise for collecting cytology specimens from the stomachs of patients undergoing endoscopy for gastric cancer screening or surveillance, reported lead author Charles J. Lightdale, MD, of Columbia University Irving Medical Center, New York City, and colleagues.

“Systematic random biopsies (updated Sydney protocol) have been recommended to increase detection of gastric intestinal metaplasia (GIM) and dysplasia,” the investigators wrote in Techniques and Innovations in Gastrointestinal Endoscopy. “However, random biopsies can be laborious, time consuming, costly, and susceptible to sampling error owing to the large surface area of the stomach.”

Power-washing, in contrast, with the pressure dial turned to 10 bar, involves spraying the gut in a systematic fashion “using sweeping and painting motions” to dislodge cells from the mucosa. These specimens are then suctioned from the resultant pools of liquid, mixed 1:1 with 10% formalin, and shipped to the lab.
 

Boom! Cytology!

Just to be sure, however, the nine patients involved in the study also underwent standard-of-care biopsy collection from areas of interest, followed by random sampling according to the updated Sydney protocol. Two of the patients were power-washed again 12 months later for endoscopic surveillance.

Power-washing added 7-10 minutes to standard endoscopy time and generated 60-100 mL of liquid for collection. Post suction, a closer look at the gastric mucosa revealed “scattered superficial erosions,” while blood loss was deemed “minimal.” The procedure appeared well tolerated, with no aspiration or esophageal reflux during endoscopy, or adverse events reported by patients after 1 week of follow-up.

Cytopathology samples were deemed satisfactory and yielded “multiple strips and large clusters of cells.” These were sufficient to diagnose GIM in three patients and reactive glandular changes with inflammation in one patient, with findings confirmed on biopsy. In contrast, the power-washed cells from one patient were “highly suspicious” for dysplasia, but biopsies were negative.

Although the study was too small for a reliable comparison with the Sydney protocol, Dr. Lightdale and colleagues concluded that the power-wash approach deserves further investigation.

“Use of power-wash to obtain cytology has the potential to improve endoscopic screening and surveillance protocols for detecting GIM and dysplasia and to reduce morbidity and mortality from gastric cancer,” they wrote.

The investigators predicted that power-washing is likely safe in most patients, although it may be unsuitable for those with noncorrectable coagulopathies or in patients who cannot stop anticoagulants. Postsurgical patients, on the other hand, should tolerate the procedure just fine.

Patients with risk of gastric cancer “might be an important group” for evaluating the power-wash procedure, the investigators wrote, noting that combining the approach with artificial intelligence could one day yield even better results.

In the meantime, Dr. Lightdale and colleagues — like so many weekend warriors wielding a power-washer — are going to see if a different nozzle will take their work to the next level.

“We are actively studying a catheter with a broader stream and the potential to increase efficiency and decrease procedure time,” they wrote. “Another catheter design might allow for simultaneous spray and suction, so that cytology samples from specific regions of the stomach could be separately analyzed.”

This study was funded by Dalio Philanthropies, the Price Family Foundation, and the Frederic and Patricia Salerno Foundation. The investigators disclosed relationships with Boston Scientific, Interscope, Medtronic, and others.

Power-washing is no longer just for blasting grimy driveways and stripping flaky paint. It’s good for work inside the gut, too.

In a proof-of-concept study, a “novel systematically directed high-pressure liquid spray,” delivered via the ERBEJET flexible probe, showed promise for collecting cytology specimens from the stomachs of patients undergoing endoscopy for gastric cancer screening or surveillance, reported lead author Charles J. Lightdale, MD, of Columbia University Irving Medical Center, New York City, and colleagues.

“Systematic random biopsies (updated Sydney protocol) have been recommended to increase detection of gastric intestinal metaplasia (GIM) and dysplasia,” the investigators wrote in Techniques and Innovations in Gastrointestinal Endoscopy. “However, random biopsies can be laborious, time consuming, costly, and susceptible to sampling error owing to the large surface area of the stomach.”

Power-washing, in contrast, with the pressure dial turned to 10 bar, involves spraying the gut in a systematic fashion “using sweeping and painting motions” to dislodge cells from the mucosa. These specimens are then suctioned from the resultant pools of liquid, mixed 1:1 with 10% formalin, and shipped to the lab.
 

Boom! Cytology!

Just to be sure, however, the nine patients involved in the study also underwent standard-of-care biopsy collection from areas of interest, followed by random sampling according to the updated Sydney protocol. Two of the patients were power-washed again 12 months later for endoscopic surveillance.

Power-washing added 7-10 minutes to standard endoscopy time and generated 60-100 mL of liquid for collection. Post suction, a closer look at the gastric mucosa revealed “scattered superficial erosions,” while blood loss was deemed “minimal.” The procedure appeared well tolerated, with no aspiration or esophageal reflux during endoscopy, or adverse events reported by patients after 1 week of follow-up.

Cytopathology samples were deemed satisfactory and yielded “multiple strips and large clusters of cells.” These were sufficient to diagnose GIM in three patients and reactive glandular changes with inflammation in one patient, with findings confirmed on biopsy. In contrast, the power-washed cells from one patient were “highly suspicious” for dysplasia, but biopsies were negative.

Although the study was too small for a reliable comparison with the Sydney protocol, Dr. Lightdale and colleagues concluded that the power-wash approach deserves further investigation.

“Use of power-wash to obtain cytology has the potential to improve endoscopic screening and surveillance protocols for detecting GIM and dysplasia and to reduce morbidity and mortality from gastric cancer,” they wrote.

The investigators predicted that power-washing is likely safe in most patients, although it may be unsuitable for those with noncorrectable coagulopathies or in patients who cannot stop anticoagulants. Postsurgical patients, on the other hand, should tolerate the procedure just fine.

Patients with risk of gastric cancer “might be an important group” for evaluating the power-wash procedure, the investigators wrote, noting that combining the approach with artificial intelligence could one day yield even better results.

In the meantime, Dr. Lightdale and colleagues — like so many weekend warriors wielding a power-washer — are going to see if a different nozzle will take their work to the next level.

“We are actively studying a catheter with a broader stream and the potential to increase efficiency and decrease procedure time,” they wrote. “Another catheter design might allow for simultaneous spray and suction, so that cytology samples from specific regions of the stomach could be separately analyzed.”

This study was funded by Dalio Philanthropies, the Price Family Foundation, and the Frederic and Patricia Salerno Foundation. The investigators disclosed relationships with Boston Scientific, Interscope, Medtronic, and others.

Power-washing is no longer just for blasting grimy driveways and stripping flaky paint. It’s good for work inside the gut, too.

In a proof-of-concept study, a “novel systematically directed high-pressure liquid spray,” delivered via the ERBEJET flexible probe, showed promise for collecting cytology specimens from the stomachs of patients undergoing endoscopy for gastric cancer screening or surveillance, reported lead author Charles J. Lightdale, MD, of Columbia University Irving Medical Center, New York City, and colleagues.

“Systematic random biopsies (updated Sydney protocol) have been recommended to increase detection of gastric intestinal metaplasia (GIM) and dysplasia,” the investigators wrote in Techniques and Innovations in Gastrointestinal Endoscopy. “However, random biopsies can be laborious, time consuming, costly, and susceptible to sampling error owing to the large surface area of the stomach.”

Power-washing, in contrast, with the pressure dial turned to 10 bar, involves spraying the gut in a systematic fashion “using sweeping and painting motions” to dislodge cells from the mucosa. These specimens are then suctioned from the resultant pools of liquid, mixed 1:1 with 10% formalin, and shipped to the lab.
 

Boom! Cytology!

Just to be sure, however, the nine patients involved in the study also underwent standard-of-care biopsy collection from areas of interest, followed by random sampling according to the updated Sydney protocol. Two of the patients were power-washed again 12 months later for endoscopic surveillance.

Power-washing added 7-10 minutes to standard endoscopy time and generated 60-100 mL of liquid for collection. Post suction, a closer look at the gastric mucosa revealed “scattered superficial erosions,” while blood loss was deemed “minimal.” The procedure appeared well tolerated, with no aspiration or esophageal reflux during endoscopy, or adverse events reported by patients after 1 week of follow-up.

Cytopathology samples were deemed satisfactory and yielded “multiple strips and large clusters of cells.” These were sufficient to diagnose GIM in three patients and reactive glandular changes with inflammation in one patient, with findings confirmed on biopsy. In contrast, the power-washed cells from one patient were “highly suspicious” for dysplasia, but biopsies were negative.

Although the study was too small for a reliable comparison with the Sydney protocol, Dr. Lightdale and colleagues concluded that the power-wash approach deserves further investigation.

“Use of power-wash to obtain cytology has the potential to improve endoscopic screening and surveillance protocols for detecting GIM and dysplasia and to reduce morbidity and mortality from gastric cancer,” they wrote.

The investigators predicted that power-washing is likely safe in most patients, although it may be unsuitable for those with noncorrectable coagulopathies or in patients who cannot stop anticoagulants. Postsurgical patients, on the other hand, should tolerate the procedure just fine.

Patients with risk of gastric cancer “might be an important group” for evaluating the power-wash procedure, the investigators wrote, noting that combining the approach with artificial intelligence could one day yield even better results.

In the meantime, Dr. Lightdale and colleagues — like so many weekend warriors wielding a power-washer — are going to see if a different nozzle will take their work to the next level.

“We are actively studying a catheter with a broader stream and the potential to increase efficiency and decrease procedure time,” they wrote. “Another catheter design might allow for simultaneous spray and suction, so that cytology samples from specific regions of the stomach could be separately analyzed.”

This study was funded by Dalio Philanthropies, the Price Family Foundation, and the Frederic and Patricia Salerno Foundation. The investigators disclosed relationships with Boston Scientific, Interscope, Medtronic, and others.