Artificial intelligence-enabled classification of hypertrophic heart diseases using electrocardiograms

Julian S Haimovich; Nate Diamant; Shaan Khurshid; Paolo Di Achille; Christopher Reeder; Sam Friedman; Pulkit Singh; Walter Spurlock; Patrick T Ellinor; Anthony Philippakis; Puneet Batra; Jennifer E Ho; Steven A Lubitz

doi:10.1016/j.cvdhj.2023.03.001

Artificial intelligence-enabled classification of hypertrophic heart diseases using electrocardiograms

Cardiovasc Digit Health J. 2023 Mar 7;4(2):48-59. doi: 10.1016/j.cvdhj.2023.03.001. eCollection 2023 Apr.

Authors

Julian S Haimovich^{1

2

3}, Nate Diamant⁴, Shaan Khurshid^{2

3

5}, Paolo Di Achille⁴, Christopher Reeder⁴, Sam Friedman⁴, Pulkit Singh⁴, Walter Spurlock⁴, Patrick T Ellinor^{2

3

5}, Anthony Philippakis^{5

6}, Puneet Batra⁴, Jennifer E Ho⁷, Steven A Lubitz^{2

3

5}

Affiliations

¹ Department of Medicine, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.
² Cardiovascular Research Center, Massachusetts General Hospital, Boston, Massachusetts.
³ Cardiovascular Disease Initiative, Broad Institute of MIT and Harvard, Cambridge, Massachusetts.
⁴ Data Sciences Platform, Broad Institute of MIT and Harvard, Cambridge, Massachusetts.
⁵ Demoulas Center for Cardiac Arrhythmias, Massachusetts General Hospital, Boston, Massachusetts.
⁶ Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, Massachusetts.
⁷ CardioVascular Institute and Division of Cardiology, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts.

Abstract

Background: Differentiating among cardiac diseases associated with left ventricular hypertrophy (LVH) informs diagnosis and clinical care.

Objective: To evaluate if artificial intelligence-enabled analysis of the 12-lead electrocardiogram (ECG) facilitates automated detection and classification of LVH.

Methods: We used a pretrained convolutional neural network to derive numerical representations of 12-lead ECG waveforms from patients in a multi-institutional healthcare system who had cardiac diseases associated with LVH (n = 50,709), including cardiac amyloidosis (n = 304), hypertrophic cardiomyopathy (n = 1056), hypertension (n = 20,802), aortic stenosis (n = 446), and other causes (n = 4766). We then regressed LVH etiologies relative to no LVH on age, sex, and the numerical 12-lead representations using logistic regression ("LVH-Net"). To assess deep learning model performance on single-lead data analogous to mobile ECGs, we also developed 2 single-lead deep learning models by training models on lead I ("LVH-Net Lead I") or lead II ("LVH-Net Lead II") from the 12-lead ECG. We compared the performance of the LVH-Net models to alternative models fit on (1) age, sex, and standard ECG measures, and (2) clinical ECG-based rules for diagnosing LVH.

Results: The areas under the receiver operator characteristic curve of LVH-Net by specific LVH etiology were cardiac amyloidosis 0.95 [95% CI, 0.93-0.97], hypertrophic cardiomyopathy 0.92 [95% CI, 0.90-0.94], aortic stenosis LVH 0.90 [95% CI, 0.88-0.92], hypertensive LVH 0.76 [95% CI, 0.76-0.77], and other LVH 0.69 [95% CI 0.68-0.71]. The single-lead models also discriminated LVH etiologies well.

Conclusion: An artificial intelligence-enabled ECG model is favorable for detection and classification of LVH and outperforms clinical ECG-based rules.

Keywords: Artificial intelligence; Cardiac amyloidosis; Electrocardiography; Hypertrophic cardiomyopathy; Hypertrophic heart disease.