1. Deep learning and the electrocardiogram: review of the current state-of-the-art
- Author
-
Akhil Vaid, Adam Russak, Benjamin S. Glicksberg, Jagat Narula, Edgar Argulian, Jessica K De Freitas, Riccardo Miotto, Felix Richter, Girish N. Nadkarni, Shan Zhao, Sulaiman Somani, Fayzan Chaudhry, and Nidhi Naik
- Subjects
Artificial intelligence ,Cardiovascular medicine ,Big data ,Cardiology ,Reviews ,030204 cardiovascular system & hematology ,Machine Learning ,03 medical and health sciences ,Electrocardiography ,0302 clinical medicine ,Deep Learning ,Physiology (medical) ,Health care ,Medicine ,ECG analysis ,Humans ,Generalizability theory ,AcademicSubjects/MED00200 ,Deep learning ,030304 developmental biology ,0303 health sciences ,business.industry ,Event (computing) ,Data science ,Electrocardiogram ,Improved performance ,ComputingMethodologies_PATTERNRECOGNITION ,State (computer science) ,Cardiology and Cardiovascular Medicine ,business - Abstract
In the recent decade, deep learning, a subset of artificial intelligence and machine learning, has been used to identify patterns in big healthcare datasets for disease phenotyping, event predictions, and complex decision making. Public datasets for electrocardiograms (ECGs) have existed since the 1980s and have been used for very specific tasks in cardiology, such as arrhythmia, ischemia, and cardiomyopathy detection. Recently, private institutions have begun curating large ECG databases that are orders of magnitude larger than the public databases for ingestion by deep learning models. These efforts have demonstrated not only improved performance and generalizability in these aforementioned tasks but also application to novel clinical scenarios. This review focuses on orienting the clinician towards fundamental tenets of deep learning, state-of-the-art prior to its use for ECG analysis, and current applications of deep learning on ECGs, as well as their limitations and future areas of improvement.
- Published
- 2020