College
Rowan-Virtua School of Osteopathic Medicine
Keywords
Artificial Intelligence, Electrocardiogram, Heart Failure
Date of Presentation
5-1-2025 12:00 AM
Poster Abstract
Many studies have presented an artificial intelligence (AI) model to read electrocardiograms (ECGs) for the purpose of detecting or classifying the severity of heart failure. While most literature suggests that these AI-ECG models are effective at detecting or classifying heart failure, their efficacy in comparison to the current standards of care is not well researched. Furthermore, the barriers to implementation and the risks of these systems have not been studied and compiled. This literature review aims to outline the efficacy of AI-ECG models, determine how effective AI-ECG is in comparison to the standards of care, and outline the barriers to clinical implementation.
Disciplines
Cardiology | Cardiovascular Diseases | Diagnosis | Health and Medical Administration | Health Information Technology | Medicine and Health Sciences
Included in
Cardiology Commons, Cardiovascular Diseases Commons, Diagnosis Commons, Health and Medical Administration Commons, Health Information Technology Commons
Artificial Intelligence in Detecting Heart Failure - A Systematic Review
Many studies have presented an artificial intelligence (AI) model to read electrocardiograms (ECGs) for the purpose of detecting or classifying the severity of heart failure. While most literature suggests that these AI-ECG models are effective at detecting or classifying heart failure, their efficacy in comparison to the current standards of care is not well researched. Furthermore, the barriers to implementation and the risks of these systems have not been studied and compiled. This literature review aims to outline the efficacy of AI-ECG models, determine how effective AI-ECG is in comparison to the standards of care, and outline the barriers to clinical implementation.
