AIMS: Artificial intelligence models can estimate a person's age from ECG. The gap between the predicted ECG age and chronological age, predicted age deviation (), has been associated with cardiovascular risk factors and mortality. However, regression bias causesto correlate with chronological age itself, potentially distorting these associations. PAD PAD
OBJECTIVES: To investigate the bias introduced by age onby comparing associations betweenand a bias-corrected() with cardiovascular risk factors and survival outcomes. PAD PAD PAD PAD bc
METHODS AND RESULTS: 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.corresponded to the residual ofregressed on chronological age. Associations with risk factors were tested usingand 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],correlated with age (= -0.54) and showed inverse associations with most risk factors; conversely, higher(= 0.00) was associated with higher prevalence of risk factors. Kaplan-Meier revealed thatabove its MAE was linked to lower survival, whereasshowed the opposite. Multivariate Cox showed each 1-year increase in bothandwas associated with a 1.4% increased mortality hazard. PAD bc PAD χ PAD r PAD bc r PAD bc PAD PAD PAD bc2
CONCLUSION: is associated with cardiovascular risk factors and mortality, offering an age-independent biomarker of biological ageing. PAD bc
Longevity & Aging