{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["5(9)"],"submitter":["Bergquist JA"],"pubmed_abstract":["<h4>Background</h4>Artificial intelligence-machine learning (AI-ML) has demonstrated the ability to extract clinically useful information from electrocardiograms (ECGs) not available using traditional interpretation methods. There exists an extensive body of AI-ML research in fields outside of cardiology including several open-source AI-ML architectures that can be translated to new problems in an \"off-the-shelf\" manner.<h4>Objective</h4>We sought to address the limited investigation of which if any of these off-the-shelf architectures could be useful in ECG analysis as well as how and when these AI-ML approaches fail.<h4>Methods</h4>We applied 6 off-the-shelf AI-ML architectures to detect low left ventricular ejection fraction (LVEF) in a cohort of ECGs from 24,868 patients. We assessed L"],"journal":["Heart rhythm O2"],"pagination":["644-654"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC11524967"],"repository":["biostudies-literature"],"pubmed_title":["Performance of off-the-shelf machine learning architectures and biases in low left ventricular ejection fraction detection."],"pmcid":["PMC11524967"],"pubmed_authors":["Bergquist JA","MacLeod RS","Brundage J","Torre M","Shah R","Bunch TJ","Steinberg BA","Lyons A","Zenger B","Ye X","Tasdizen T","Ranjan R"],"additional_accession":[]},"is_claimable":false,"name":"Performance of off-the-shelf machine learning architectures and biases in low left ventricular ejection fraction detection.","description":"<h4>Background</h4>Artificial intelligence-machine learning (AI-ML) has demonstrated the ability to extract clinically useful information from electrocardiograms (ECGs) not available using traditional interpretation methods. There exists an extensive body of AI-ML research in fields outside of cardiology including several open-source AI-ML architectures that can be translated to new problems in an \"off-the-shelf\" manner.<h4>Objective</h4>We sought to address the limited investigation of which if any of these off-the-shelf architectures could be useful in ECG analysis as well as how and when these AI-ML approaches fail.<h4>Methods</h4>We applied 6 off-the-shelf AI-ML architectures to detect low left ventricular ejection fraction (LVEF) in a cohort of ECGs from 24,868 patients. We assessed L","dates":{"release":"2024-01-01T00:00:00Z","publication":"2024 Sep","modification":"2025-04-26T16:59:48.799Z","creation":"2025-04-06T15:25:18.325Z"},"accession":"S-EPMC11524967","cross_references":{"pubmed":["39493911"],"doi":["10.1016/j.hroo.2024.07.009"]}}