Performance of off-the-shelf machine learning architectures and biases in low left ventricular ejection fraction detection
Year: 2024
Type: article
Abstract: Background: 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. Objective: 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. Methods: 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 LVEF classification and explored patient characteristics associated with inaccurate (false positive or false negative) LVEF prediction. Results: We found that all of these network architectures produced LVEF detection area under the receiver-operating characteristic curve values above 0.9 (averaged over 5 instances per network), with the ResNet 18 network performing the highest (average area under the receiver-operating characteristic curve of 0.917). We also observed that some patient-specific characteristics such as race, sex, and presence of several comorbidities were associated with lower LVEF prediction performance. Conclusions: This demonstrates the ability of off-the-shelf AI-ML architectures to detect clinically useful information from ECGs with performance matching contemporary custom-build AI-ML architectures. We also highlighted the presence of possible biases in these AI-ML approaches in the context of patient characteristics. These findings should be considered in the pursuit of efficient and equitable deployment of AI-ML technologies moving forward.
Source: Heart Rhythm O2
Institution: University of Utah
Language: English
Topic: ECG Monitoring and Analysis
Subfield: Cardiology and Cardiovascular Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,150
Funders: American Heart Association, Pfizer, Sanofi, Foundation for Cardiovascular Research, Boston Scientific Corporation, Janssen Scientific Affairs, National Institutes of Health, National Heart, Lung, and Blood Institute, National Institute of General Medical Sciences, National Institute of Biomedical Imaging and Bioengineering, National Center for Research Resources, National Center for Advancing Translational Sciences, Biosense Webster
Awards: University of Utah Center for Clinical and Translational Science-UL1, Center for Integrative Biomedical Computing, Integration of Uncertainty Quantification with SCIRun Bioelectric Field Simulation Pipeline, Center for Integrative Biomedical Computing Legacy Transition, STudying Effectiveness in Patient-centered care, G7608249155, Optimizing Outcomes for Patients with Heart Failure and Atrial Fibrillation, Novel Characterization and Detection Techniques for Acute Myocardial Ischemia, University of Utah Center for Clinical and Translational Science-UL1, G9000154966, Overcoming explainability and data availability barriers to broad application of ECG ML screening with a system-wide ECG dataset, CTSA UM1 Program at University of Utah, Training in Cardiovascular Research
OpenAlex ID: W4400723247