User login
DIFFUSE LUNG DISEASE AND LUNG TRANSPLANT NETWORK
Pulmonary Physiology and Rehabilitation Section
Several studies have explored automation of CPET interpretation, the most notable of which utilized machine learning.1
Recently, Schwendinger et al. investigated the ability of machine learning algorithms to not only categorize (pulmonary-vascular, mechanical-ventilatory, cardiocirculatory, and muscular), but also assign severity scores (0-6) to exercise limitations found in a group of 200 CPETs performed on adult patients referred to a lung clinic in Germany.2 Decision trees were constructed for each of the limitation categories by identifying variables with the lowest Root Mean Square Error (RMSE), which were comparable to agreement within expert interpretations. Combining decision trees allowed for a more comprehensive analysis with identification of multiple abnormalities in the same test.
A major limitation to the study is limited applicability to general patient populations without suspected lung disease. This bias is reflected in the decision tree for cardiovascular limitation that relied on VO2 peak and FEV1 alone. The authors were unable to construct a decision tree for muscular limitations due to a lack of identified cases.
Overall, these results suggest that refinement of machine learning algorithms built with larger heterogeneous data sets and expert interpretation can make CPETs accessible to the nonexpert clinician as long as test quality can be replicated across centers.
–Joseph Russo, MD
Fellow-in-Training
– Fatima Zeba, MD
Member-at-Large
References
1. Portella JJ, Andonian BJ, Brown DE, et al. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise testing. IEEE J Biomed Health Inform. 2022;26(8):4228-4237.
2. Schwendinger F, Biehler AK, Nagy-Huber M, et al. Using machine learning-based algorithms to identify and quantify exercise limitations in clinical practice: are we there yet? Med Sci Sports Exerc. 2024;56(2):159-169.
DIFFUSE LUNG DISEASE AND LUNG TRANSPLANT NETWORK
Pulmonary Physiology and Rehabilitation Section
Several studies have explored automation of CPET interpretation, the most notable of which utilized machine learning.1
Recently, Schwendinger et al. investigated the ability of machine learning algorithms to not only categorize (pulmonary-vascular, mechanical-ventilatory, cardiocirculatory, and muscular), but also assign severity scores (0-6) to exercise limitations found in a group of 200 CPETs performed on adult patients referred to a lung clinic in Germany.2 Decision trees were constructed for each of the limitation categories by identifying variables with the lowest Root Mean Square Error (RMSE), which were comparable to agreement within expert interpretations. Combining decision trees allowed for a more comprehensive analysis with identification of multiple abnormalities in the same test.
A major limitation to the study is limited applicability to general patient populations without suspected lung disease. This bias is reflected in the decision tree for cardiovascular limitation that relied on VO2 peak and FEV1 alone. The authors were unable to construct a decision tree for muscular limitations due to a lack of identified cases.
Overall, these results suggest that refinement of machine learning algorithms built with larger heterogeneous data sets and expert interpretation can make CPETs accessible to the nonexpert clinician as long as test quality can be replicated across centers.
–Joseph Russo, MD
Fellow-in-Training
– Fatima Zeba, MD
Member-at-Large
References
1. Portella JJ, Andonian BJ, Brown DE, et al. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise testing. IEEE J Biomed Health Inform. 2022;26(8):4228-4237.
2. Schwendinger F, Biehler AK, Nagy-Huber M, et al. Using machine learning-based algorithms to identify and quantify exercise limitations in clinical practice: are we there yet? Med Sci Sports Exerc. 2024;56(2):159-169.
DIFFUSE LUNG DISEASE AND LUNG TRANSPLANT NETWORK
Pulmonary Physiology and Rehabilitation Section
Several studies have explored automation of CPET interpretation, the most notable of which utilized machine learning.1
Recently, Schwendinger et al. investigated the ability of machine learning algorithms to not only categorize (pulmonary-vascular, mechanical-ventilatory, cardiocirculatory, and muscular), but also assign severity scores (0-6) to exercise limitations found in a group of 200 CPETs performed on adult patients referred to a lung clinic in Germany.2 Decision trees were constructed for each of the limitation categories by identifying variables with the lowest Root Mean Square Error (RMSE), which were comparable to agreement within expert interpretations. Combining decision trees allowed for a more comprehensive analysis with identification of multiple abnormalities in the same test.
A major limitation to the study is limited applicability to general patient populations without suspected lung disease. This bias is reflected in the decision tree for cardiovascular limitation that relied on VO2 peak and FEV1 alone. The authors were unable to construct a decision tree for muscular limitations due to a lack of identified cases.
Overall, these results suggest that refinement of machine learning algorithms built with larger heterogeneous data sets and expert interpretation can make CPETs accessible to the nonexpert clinician as long as test quality can be replicated across centers.
–Joseph Russo, MD
Fellow-in-Training
– Fatima Zeba, MD
Member-at-Large
References
1. Portella JJ, Andonian BJ, Brown DE, et al. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise testing. IEEE J Biomed Health Inform. 2022;26(8):4228-4237.
2. Schwendinger F, Biehler AK, Nagy-Huber M, et al. Using machine learning-based algorithms to identify and quantify exercise limitations in clinical practice: are we there yet? Med Sci Sports Exerc. 2024;56(2):159-169.
<!--$RCSfile: InCopy_agile.xsl,v $ $Revision: 1.35 $-->
<!--$RCSfile: drupal.xsl,v $ $Revision: 1.7 $-->
<root generator="drupal.xsl" gversion="1.7"> <header> <fileName>168017</fileName> <TBEID>0C050080.SIG</TBEID> <TBUniqueIdentifier>MD_0C050080</TBUniqueIdentifier> <newsOrJournal>News</newsOrJournal> <publisherName>Frontline Medical Communications</publisherName> <storyname/> <articleType>2</articleType> <TBLocation>QC Done-All Pubs</TBLocation> <QCDate>20240513T122255</QCDate> <firstPublished>20240530T131521</firstPublished> <LastPublished>20240530T131521</LastPublished> <pubStatus qcode="stat:"/> <embargoDate/> <killDate/> <CMSDate>20240530T131521</CMSDate> <articleSource/> <facebookInfo/> <meetingNumber/> <byline>Zeba and Russo</byline> <bylineText/> <bylineFull/> <bylineTitleText/> <USOrGlobal/> <wireDocType/> <newsDocType>News</newsDocType> <journalDocType/> <linkLabel/> <pageRange/> <citation/> <quizID/> <indexIssueDate/> <itemClass qcode="ninat:text"/> <provider qcode="provider:imng"> <name>IMNG Medical Media</name> <rightsInfo> <copyrightHolder> <name>Frontline Medical News</name> </copyrightHolder> <copyrightNotice>Copyright (c) 2015 Frontline Medical News, a Frontline Medical Communications Inc. company. All rights reserved. This material may not be published, broadcast, copied, or otherwise reproduced or distributed without the prior written permission of Frontline Medical Communications Inc.</copyrightNotice> </rightsInfo> </provider> <abstract/> <metaDescription>Cardiopulmonary exercise testing (CPET) is a clinically useful modality to discriminate between cardiac, pulmonary, and musculoskeletal limitations to physical </metaDescription> <articlePDF/> <teaserImage>301661</teaserImage> <teaser>Could automation of CPET interpretation extend its utility?</teaser> <title>Machine learning meets cardiopulmonary exercise testing</title> <deck/> <disclaimer/> <AuthorList/> <articleURL/> <doi/> <pubMedID/> <publishXMLStatus/> <publishXMLVersion>1</publishXMLVersion> <useEISSN>0</useEISSN> <urgency/> <pubPubdateYear/> <pubPubdateMonth/> <pubPubdateDay/> <pubVolume/> <pubNumber/> <wireChannels/> <primaryCMSID/> <CMSIDs/> <keywords/> <seeAlsos/> <publications_g> <publicationData> <publicationCode>chph</publicationCode> <pubIssueName/> <pubArticleType/> <pubTopics/> <pubCategories/> <pubSections/> </publicationData> </publications_g> <publications> <term canonical="true">6</term> </publications> <sections> <term>52072</term> <term canonical="true">39299</term> </sections> <topics> <term canonical="true">284</term> </topics> <links> <link> <itemClass qcode="ninat:picture"/> <altRep contenttype="image/jpeg">images/240129a9.jpg</altRep> <description role="drol:caption">Dr. Joseph Russo</description> <description role="drol:credit">CHEST</description> </link> <link> <itemClass qcode="ninat:picture"/> <altRep contenttype="image/jpeg">images/240129aa.jpg</altRep> <description role="drol:caption">Dr. Fatima Zeba</description> <description role="drol:credit">CHEST</description> </link> </links> </header> <itemSet> <newsItem> <itemMeta> <itemRole>Main</itemRole> <itemClass>text</itemClass> <title>Machine learning meets cardiopulmonary exercise testing</title> <deck/> </itemMeta> <itemContent> <h3>DIFFUSE LUNG DISEASE AND LUNG TRANSPLANT NETWORK<br/><br/>Pulmonary Physiology and Rehabilitation Section</h3> <p><span class="tag metaDescription">Cardiopulmonary exercise testing (CPET) is a clinically useful modality to discriminate between cardiac, pulmonary, and musculoskeletal limitations to physical exertion. However, it is relatively underutilized due to the lack of local expertise necessary for accurate interpretation.</span> Several studies have explored automation of CPET interpretation, the most notable of which utilized machine learning.<sup>1</sup></p> <p>Recently, Schwendinger et al. investigated the ability of machine learning algorithms to not only categorize (pulmonary-vascular, mechanical-ventilatory, cardiocirculatory, and muscular), but also assign severity scores (0-6) to exercise limitations found in a group of 200 CPETs performed on adult patients referred to a lung clinic in Germany.<sup>2</sup> Decision trees were constructed for each of the limitation categories by identifying variables with the lowest Root Mean Square Error (RMSE), which were comparable to agreement within expert interpretations. Combining decision trees allowed for a more comprehensive analysis with identification of multiple abnormalities in the same test. [[{"fid":"301661","view_mode":"medstat_image_flush_right","fields":{"format":"medstat_image_flush_right","field_file_image_alt_text[und][0][value]":"Joseph Russo, MD, Fellow-in-Training","field_file_image_credit[und][0][value]":"CHEST","field_file_image_caption[und][0][value]":"Dr. Joseph Russo"},"type":"media","attributes":{"class":"media-element file-medstat_image_flush_right"}}]]A major limitation to the study is limited applicability to general patient populations without suspected lung disease. This bias is reflected in the decision tree for cardiovascular limitation that relied on VO<sub>2</sub> peak and FEV<sub>1</sub> alone. The authors were unable to construct a decision tree for muscular limitations due to a lack of identified cases. [[{"fid":"301662","view_mode":"medstat_image_flush_right","fields":{"format":"medstat_image_flush_right","field_file_image_alt_text[und][0][value]":"Fatima Zeba, MD, Member-at-Large","field_file_image_credit[und][0][value]":"CHEST","field_file_image_caption[und][0][value]":"Dr. Fatima Zeba"},"type":"media","attributes":{"class":"media-element file-medstat_image_flush_right"}}]]<br/><br/>Overall, these results suggest that refinement of machine learning algorithms built with larger heterogeneous data sets and expert interpretation can make CPETs accessible to the nonexpert clinician as long as test quality can be replicated across centers. <br/><br/><br/><br/>– <em>Joseph Russo, MD<br/><br/>Fellow-in-Training <br/><br/>– Fatima Zeba, MD<br/><br/>Member-at-Large <br/><br/><br/><br/></em><b>References</b><br/><br/>1. Portella JJ, Andonian BJ, Brown DE, et al. Using machine learning to identify organ system specific limitations to exercise via cardiopulmonary exercise testing.<em> IEEE J Biomed Health Inform. </em>2022;26(8):4228-4237.<br/><br/>2. Schwendinger F, Biehler AK, Nagy-Huber M, et al. Using machine learning-based algorithms to identify and quantify exercise limitations in clinical practice: are we there yet?<em> Med Sci Sports Exerc. </em>2024;56(2):159-169.</p> </itemContent> </newsItem> <newsItem> <itemMeta> <itemRole>teaser</itemRole> <itemClass>text</itemClass> <title/> <deck/> </itemMeta> <itemContent> </itemContent> </newsItem> </itemSet></root>
