Deep learning on resting electrocardiogram to identify impaired heart rate recovery
Nathaniel Diamant, Paolo Di Achille, Lu‐Chen Weng, Emily S. Lau, Shaan Khurshid, Sam Friedman, Christopher Reeder, Pulkit Singh, Xin Wang, Gopal Sarma, Mercedeh Ghadessi, Johanna Mielke, Eren Elçi, Ivan Kryukov, Hanna M. Eilken, Andrea Derix, Patrick T. Ellinor, Christopher D. Anderson, Anthony Philippakis, Puneet Batra, Steven A. Lubitz, Jennifer E. Ho
Abstract
Background and Objective Postexercise heart rate recovery (HRR) is an important indicator of cardiac autonomic function and abnormal HRR is associated with adverse outcomes . We hypothesized that deep learning on resting electrocardiogram (ECG) tracings may identify individuals with impaired HRR. Methods We trained a deep learning model (convolutional neural network) to infer HRR based on resting ECG waveforms (HRR pred ) among UK Biobank participants who had undergone exercise testing. We examined the association of HRR pred with incident cardiovascular disease using Cox models , and investigated the genetic architecture of HRR pred in genome-wide association analysis. Results Among 56,793 individuals (mean age 57 years, 51% women), the HRR pred model was moderately correlated with actual HRR (r = 0.48, 95% confidence interval [CI] 0.47–0.48). Over a median follow-up of 10 years, we observed 2060 incident diabetes mellitus (DM) events, 862 heart failure events, and 2065 deaths. Higher HRR pred was associated with lower risk of DM (hazard ratio [HR] 0.79 per 1 standard deviation change, 95% CI 0.76–0.83), heart failure (HR 0.89, 95% CI 0.83–0.95), and death (HR 0.83, 95% CI 0.79–0.86). After accounting for resting heart rate , the association of HRR pred with incident DM and all-cause mortality were similar. Genetic determinants of HRR pred included known heart rate, cardiac conduction system, cardiomyopathy , and metabolic trait loci. Conclusion Deep learning–derived estimates of HRR using resting ECG independently associated with future clinical outcomes, including new-onset DM and all-cause mortality. Inferring postexercise heart rate response from a resting ECG may have potential clinical implications and impact on preventive strategies warrants future study.