Artificial Intelligence–Derived Electrocardiographic Age Predicts Mortality in Adults With Congenital Heart Disease

Abstract

BACKGROUND: Artificial intelligence (AI) can be used to estimate age from the electrocardiogram (AI-ECG age). The difference between AI-ECG age and chronological age (delta-age) is an independent predictor of mortality in the general population. OBJECTIVES: The purpose of this study was to assess the relationship between delta-age and mortality among adults with congenital heart disease (ACHD). METHODS: A previously validated neural network was used to analyze standard digital 12-lead ECGs in a cohort of ACHD (age >18 years) between 1992 and 2023. A single ECG from each patient, collected during the first visit to the ACHD clinic, was analyzed to compute the delta-age. The relationship between the delta-age and mortality was evaluated using Cox proportional hazard models adjusting for influential clinical factors. RESULTS: Of 5,780 subjects tested (50% females), the mean chronological age was 39.1 ± 15.0 years. AI-ECG age was 52.3 ± 16.6 years. CHD complexity was classified as mild, moderate, and severe in 7.4%, 73.9%, and 18.7% of patients, respectively. Patients with severe CHD had the highest median delta-age of 15.8 (IQR: 3.5-31.2) years followed by moderate 11.5 (IQR: 3.5-21.3) years and simple 6.7 (IQR: 0.3-14.2) years. During a median follow-up of 6.4 years (IQR: 1.58-13.7 years), 839 (14.5%) patients died. After adjusting for chronologic age, CHD complexity, and other clinical variables, delta-age was associated with increased mortality risk (HR: 1.06 [1.03-1.09] per 5-year increment in delta-age, P < 0.05). CONCLUSIONS: Delta-age, the difference between AI-ECG and chronological age, is an independent predictor of all-cause mortality in ACHD.

Ähnliche Arbeiten