Cardiac age detected by machine learning applied to the surface ECG of healthy subjects: Creation of a benchmark

• Published in: Journal of electrocardiology Vol. 72; pp. 49 - 55
• Main Authors: van der Wall, Hein E.C., Hassing, Gert-Jan, Doll, Robert-Jan, van Westen, Gerard J.P., Cohen, Adam F., Selder, Jasper L., Kemme, Michiel, Burggraaf, Jacobus, Gal, Pim
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.05.2022; Elsevier Science Ltd
• Subjects: Adolescent; Adult; Aged; Aging; Artificial intelligence; Benchmarking; Cardiovascular; Cardiovascular disease; Child; Child, Preschool; ECG; Electrocardiography; Electrocardiography - methods; Female; Healthy Volunteers; Humans; Infant; Machine Learning; Male; Middle Aged; Neural networks; Neural Networks, Computer; Regression analysis; Young Adult; Aging; ECG; Healthy volunteers; Artificial intelligence; Machine learning
• ISSN: 0022-0736; 1532-8430; 1532-8430
• DOI: 10.1016/j.jelectrocard.2022.03.001

The aim of the present study was to develop a neural network to characterize the effect of aging on the ECG in healthy volunteers. Moreover, the impact of the various ECG features on aging was evaluated. A total of 6228 healthy subjects without structural heart disease were included in this study. A neural network regression model was created to predict age of the subjects based on their ECG; 577 parameters derived from a 12‑lead ECG of each subject were used to develop and validate the neural network; A tenfold cross-validation was performed, using 118 subjects for validation each fold. Using SHapley Additive exPlanations values the impact of the individual features on the prediction of age was determined. Of 6228 subjects tested, 1808 (29%) were females and mean age was 34 years, range 18–75 years. Physiologic age was estimated as a continuous variable with an average error of 6.9 ± 5.6 years (R2 = 0.72 ± 0.04). The correlation was slightly stronger for men (R2 = 0.74) than for women (R2 = 0.66). The most important features on the prediction of physiologic age were T wave morphology indices in leads V4 and V5, and P wave amplitude in leads AVR and II. The application of machine learning to the ECG using a neural network regression model, allows accurate estimation of physiologic cardiac age. This technique could be used to pick up subtle age-related cardiac changes, but also estimate the reversing of these age-associated effects by administered treatments.