Multi-center retrospective cohort study applying deep learning to electrocardiograms to identify left heart valvular dysfunction
Open Access
- 14 February 2023
- journal article
- research article
- Published by Springer Nature in Communications Medicine
- Vol. 3 (1) , 1-12
Abstract
Background: Aortic Stenosis and Mitral Regurgitation are common valvular conditions representing a hidden burden of disease within the population. The aim of this study was to develop and validate deep learning-based screening and diagnostic tools that can help guide clinical decision making. Methods: In this multi-center retrospective cohort study, we acquired Transthoracic Echocardiogram reports from five Mount Sinai hospitals within New York City representing a demographically diverse cohort of patients. We developed a Natural Language Processing pipeline to extract ground-truth labels about valvular status and paired these to Electrocardiograms (ECGs). We developed and externally validated deep learning models capable of detecting valvular disease, in addition to considering scenarios of clinical deployment. Results: We use 617,338 ECGs paired to transthoracic echocardiograms from 123,096 patients to develop a deep learning model for detection of Mitral Regurgitation. Area Under Receiver Operating Characteristic curve (AUROC) is 0.88 (95% CI:0.88–0.89) in internal testing, and 0.81 (95% CI:0.80–0.82) in external validation. To develop a model for detection of Aortic Stenosis, we use 617,338 Echo-ECG pairs for 128,628 patients. AUROC is 0.89 (95% CI: 0.88-0.89) in internal testing, going to 0.86 (95% CI: 0.85-0.87) in external validation. The model’s performance increases leading up to the time of the diagnostic echo, and it performs well in validation against requirement of Transcatheter Aortic Valve Replacement procedures. Conclusions: Deep learning based tools can increase the amount of information extracted from ubiquitous investigations such as the ECG. Such tools are inexpensive, can help in earlier disease detection, and potentially improve prognosis.Keywords
Funding Information
- U.S. Department of Health & Human Services | NIH | National Center for Advancing Translational Sciences (U54 TR001433-05)
This publication has 28 references indexed in Scilit:
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?IEEE Transactions on Medical Imaging, 2016
- Are We Doing Too Many Inpatient Echocardiograms?JACC, 2016
- Tradeoffs between accuracy measures for electronic health care data algorithmsJournal of Clinical Epidemiology, 2012
- Epidemiology of valvular heart disease in the adultNature Reviews Cardiology, 2011
- Long-term survival in asymptomatic patients with severe degenerative mitral regurgitation: A propensity score–based comparison between an early surgical strategy and a conservative treatment approachThe Journal of Thoracic and Cardiovascular Surgery, 2009
- Youden Index and Optimal Cut‐Point Estimated from Observations Affected by a Lower Limit of DetectionBiometrical Journal, 2008
- Evaluation of a screening protocol using auscultation and portable echocardiography to detect asymptomatic rheumatic heart disease in Tongan schoolchildrenNature Clinical Practice Cardiovascular Medicine, 2008
- Effect of teaching and type of stethoscope on cardiac auscultatory performanceAmerican Heart Journal, 2006
- ECG Signal Processing2005
- 12-Lead ECG System1995