1. Identification of high-risk imaging features in hypertrophic cardiomyopathy using electrocardiography: A deep-learning approach.
- Author
-
Carrick RT, Ahamed H, Sung E, Maron MS, Madias C, Avula V, Studley R, Bao C, Bokhari N, Quintana E, Rajesh-Kannan R, Maron BJ, Wu KC, and Rowin EJ
- Subjects
- Humans, Male, Female, Middle Aged, Risk Assessment methods, Retrospective Studies, Death, Sudden, Cardiac prevention & control, Death, Sudden, Cardiac etiology, Risk Factors, Cardiomyopathy, Hypertrophic diagnosis, Cardiomyopathy, Hypertrophic physiopathology, Cardiomyopathy, Hypertrophic diagnostic imaging, Deep Learning, Electrocardiography, Magnetic Resonance Imaging, Cine methods
- Abstract
Background: Patients with hypertrophic cardiomyopathy (HCM) are at risk of sudden death, and individuals with ≥1 major risk markers are considered for primary prevention implantable cardioverter-defibrillators. Guidelines recommend cardiac magnetic resonance (CMR) imaging to identify high-risk imaging features. However, CMR imaging is resource intensive and is not widely accessible worldwide., Objective: The purpose of this study was to develop electrocardiogram (ECG) deep-learning (DL) models for the identification of patients with HCM and high-risk imaging features., Methods: Patients with HCM evaluated at Tufts Medical Center (N = 1930; Boston, MA) were used to develop ECG-DL models for the prediction of high-risk imaging features: systolic dysfunction, massive hypertrophy (≥30 mm), apical aneurysm, and extensive late gadolinium enhancement. ECG-DL models were externally validated in a cohort of patients with HCM from the Amrita Hospital HCM Center (N = 233; Kochi, India)., Results: ECG-DL models reliably identified high-risk features (systolic dysfunction, massive hypertrophy, apical aneurysm, and extensive late gadolinium enhancement) during holdout testing (c-statistic 0.72, 0.83, 0.93, and 0.76) and external validation (c-statistic 0.71, 0.76, 0.91, and 0.68). A hypothetical screening strategy using echocardiography combined with ECG-DL-guided selective CMR use demonstrated a sensitivity of 97% for identifying patients with high-risk features while reducing the number of recommended CMRs by 61%. The negative predictive value with this screening strategy for the absence of high-risk features in patients without ECG-DL recommendation for CMR was 99.5%., Conclusion: In HCM, novel ECG-DL models reliably identified patients with high-risk imaging features while offering the potential to reduce CMR testing requirements in underresourced areas., Competing Interests: Disclosures Dr Maron is a consultant for Cytokinetics, iRhythm, Imbria Pharmaceuticals, and Takeda Pharmaceuticals. Dr Rowin has received research funding from Pfizer and iRhythm. The remaining authors have nothing to disclose., (Copyright © 2024 Heart Rhythm Society. Published by Elsevier Inc. All rights reserved.)
- Published
- 2024
- Full Text
- View/download PDF