User login
TOPLINE:
Artificial intelligence (AI)–guided screening using digital stethoscopes doubled the detection of left ventricular systolic dysfunction (LVSD) in pregnant and postpartum women in Nigeria. Cardiomyopathy during pregnancy and post partum is challenging to diagnose because of symptom overlap with normal pregnancy changes. AI-guided screening showed a significant improvement in diagnosis rates, compared with usual care.
METHODOLOGY:
- Researchers conducted an open-label, randomized clinical trial involving 1232 pregnant and postpartum women in Nigeria.
- Participants were randomized to either AI-guided screening using digital stethoscopes and 12-lead ECGs or usual care.
- The primary outcome was the identification of LVSD confirmed by echocardiography.
- Secondary outcomes were AI model performance across subgroups and the effectiveness of AI in identifying various levels of LVSD.
TAKEAWAY:
- AI-guided screening using digital stethoscopes detected LVSD in 4.1% of participants, compared with 2.0% of controls (P = .032).
- The 12-lead AI-ECG model detected LVSD in 3.4% of participants in the intervention arm, compared with 2.0% of those in the control arm (P = .125).
- No serious adverse events related to study participation were reported.
- The study highlighted the potential of AI-guided screening to improve the diagnosis of pregnancy-related cardiomyopathy.
IN PRACTICE:
“Delays in the diagnosis of cardiomyopathy during the peripartum period is associated with poorer outcomes as such, it is imperative that we are able to identify cardiac dysfunction early so that appropriate care can be initiated to reduce associated adverse maternal and infant outcomes,” wrote the authors of the study.
SOURCE:
This study was led by Demilade A. Adedinsewo, MBchB, Mayo Clinic in Jacksonville, Florida. It was published online in Nature Medicine.
LIMITATIONS:
The study’s pragmatic design and enrollment at teaching hospitals with echocardiography capabilities limited generalizability. Two thirds of participants were in the third trimester or postpartum at study entry, which limited follow-up visits. The study did not require completion of all seven visits, which led to potential attrition bias. The selected cutoff for LVSD (left ventricular ejection fraction < 50%) did not match the original model specifications, which potentially affected results.
DISCLOSURES:
Dr. Adedinsewo disclosed receiving grants from the Mayo Clinic BIRCWH program funded by the National Institutes of Health. Two coauthors reported holding patents for AI algorithms licensed to Anumana, AliveCor, and Eko Health. Additional disclosures are noted in the original article.
This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.
TOPLINE:
Artificial intelligence (AI)–guided screening using digital stethoscopes doubled the detection of left ventricular systolic dysfunction (LVSD) in pregnant and postpartum women in Nigeria. Cardiomyopathy during pregnancy and post partum is challenging to diagnose because of symptom overlap with normal pregnancy changes. AI-guided screening showed a significant improvement in diagnosis rates, compared with usual care.
METHODOLOGY:
- Researchers conducted an open-label, randomized clinical trial involving 1232 pregnant and postpartum women in Nigeria.
- Participants were randomized to either AI-guided screening using digital stethoscopes and 12-lead ECGs or usual care.
- The primary outcome was the identification of LVSD confirmed by echocardiography.
- Secondary outcomes were AI model performance across subgroups and the effectiveness of AI in identifying various levels of LVSD.
TAKEAWAY:
- AI-guided screening using digital stethoscopes detected LVSD in 4.1% of participants, compared with 2.0% of controls (P = .032).
- The 12-lead AI-ECG model detected LVSD in 3.4% of participants in the intervention arm, compared with 2.0% of those in the control arm (P = .125).
- No serious adverse events related to study participation were reported.
- The study highlighted the potential of AI-guided screening to improve the diagnosis of pregnancy-related cardiomyopathy.
IN PRACTICE:
“Delays in the diagnosis of cardiomyopathy during the peripartum period is associated with poorer outcomes as such, it is imperative that we are able to identify cardiac dysfunction early so that appropriate care can be initiated to reduce associated adverse maternal and infant outcomes,” wrote the authors of the study.
SOURCE:
This study was led by Demilade A. Adedinsewo, MBchB, Mayo Clinic in Jacksonville, Florida. It was published online in Nature Medicine.
LIMITATIONS:
The study’s pragmatic design and enrollment at teaching hospitals with echocardiography capabilities limited generalizability. Two thirds of participants were in the third trimester or postpartum at study entry, which limited follow-up visits. The study did not require completion of all seven visits, which led to potential attrition bias. The selected cutoff for LVSD (left ventricular ejection fraction < 50%) did not match the original model specifications, which potentially affected results.
DISCLOSURES:
Dr. Adedinsewo disclosed receiving grants from the Mayo Clinic BIRCWH program funded by the National Institutes of Health. Two coauthors reported holding patents for AI algorithms licensed to Anumana, AliveCor, and Eko Health. Additional disclosures are noted in the original article.
This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.
TOPLINE:
Artificial intelligence (AI)–guided screening using digital stethoscopes doubled the detection of left ventricular systolic dysfunction (LVSD) in pregnant and postpartum women in Nigeria. Cardiomyopathy during pregnancy and post partum is challenging to diagnose because of symptom overlap with normal pregnancy changes. AI-guided screening showed a significant improvement in diagnosis rates, compared with usual care.
METHODOLOGY:
- Researchers conducted an open-label, randomized clinical trial involving 1232 pregnant and postpartum women in Nigeria.
- Participants were randomized to either AI-guided screening using digital stethoscopes and 12-lead ECGs or usual care.
- The primary outcome was the identification of LVSD confirmed by echocardiography.
- Secondary outcomes were AI model performance across subgroups and the effectiveness of AI in identifying various levels of LVSD.
TAKEAWAY:
- AI-guided screening using digital stethoscopes detected LVSD in 4.1% of participants, compared with 2.0% of controls (P = .032).
- The 12-lead AI-ECG model detected LVSD in 3.4% of participants in the intervention arm, compared with 2.0% of those in the control arm (P = .125).
- No serious adverse events related to study participation were reported.
- The study highlighted the potential of AI-guided screening to improve the diagnosis of pregnancy-related cardiomyopathy.
IN PRACTICE:
“Delays in the diagnosis of cardiomyopathy during the peripartum period is associated with poorer outcomes as such, it is imperative that we are able to identify cardiac dysfunction early so that appropriate care can be initiated to reduce associated adverse maternal and infant outcomes,” wrote the authors of the study.
SOURCE:
This study was led by Demilade A. Adedinsewo, MBchB, Mayo Clinic in Jacksonville, Florida. It was published online in Nature Medicine.
LIMITATIONS:
The study’s pragmatic design and enrollment at teaching hospitals with echocardiography capabilities limited generalizability. Two thirds of participants were in the third trimester or postpartum at study entry, which limited follow-up visits. The study did not require completion of all seven visits, which led to potential attrition bias. The selected cutoff for LVSD (left ventricular ejection fraction < 50%) did not match the original model specifications, which potentially affected results.
DISCLOSURES:
Dr. Adedinsewo disclosed receiving grants from the Mayo Clinic BIRCWH program funded by the National Institutes of Health. Two coauthors reported holding patents for AI algorithms licensed to Anumana, AliveCor, and Eko Health. Additional disclosures are noted in the original article.
This article was created using several editorial tools, including AI, as part of the process. Human editors reviewed this content before publication. A version of this article first appeared on Medscape.com.