Artificial intelligence-predicted ECG age gap as a biomarker: bias-adjusted correlation with mortality and cardiovascular risk factors

Artificial intelligence models can estimate a person’s age from ECG. The gap between the predicted ECG age and chronological age, predicted age deviation (PAD), has been associated with cardiovascular risk factors and mortality. However, regression bias causes PAD to correlate with chronological age itself, potentially distorting these associations.

To investigate the bias introduced by age on PAD by comparing associations between PAD and a bias-corrected PAD (PAD_bc) with cardiovascular risk factors and survival outcomes.

ECG and cardiovascular risk data from Ziekenhuis Oost-Limburg (2002–23) were linked to mortality data from the Belgian National Registry. A neural network was trained to predict age from ECGs. PAD_bc corresponded to the residual of PAD regressed on chronological age. Associations with risk factors were tested using χ² and ANOVA. Survival was analysed with Kaplan–Meier curves and Cox proportional hazards models. We included 1 258 993 ECGs from 234 586 patients, split 40:10:50 into training, validation, and test sets by patient. In the test set [mean age 56.4 ± 16.9 years, mean absolute error (MAE) 7.9], PAD correlated with age (r = −0.54) and showed inverse associations with most risk factors; conversely, higher PAD_bc (r = 0.00) was associated with higher prevalence of risk factors. Kaplan–Meier revealed that PAD_bc above its MAE was linked to lower survival, whereas PAD showed the opposite. Multivariate Cox showed each 1-year increase in both PAD and PAD_bc was associated with a 1.4% increased mortality hazard.

PAD_bc is associated with cardiovascular risk factors and mortality, offering an age-independent biomarker of biological ageing.