AI Aging Estimates Linked to Mortality Risk

Artificial intelligence models applied to standard 12-lead electrocardiograms (ECGs) can estimate a patient’s biological age, a metric that has been linked to all-cause mortality and the presence of medical comorbidities.

Research published on October 3, 2025, indicates that this AI-derived biological age, referred to as AI-ECG age, serves as a predictor of mortality. The findings suggest that biological aging often diverges from chronological aging, and tracking this divergence can provide a more accurate assessment of a patient’s health risks.

Biological Age Versus Chronological Age

While chronological age is the standard measurement used in clinical practice, it does not account for the individual variations in physiological decline and the rates at which different people age.

According to a review in The Lancet, AI has transformed the ability to estimate biological age by identifying patterns that chronological age fails to capture. This allows for a more personalized understanding of how a patient’s body is aging relative to their birth date.

Data from May 14, 2025, suggests that AI-estimated ECG-age correlates well with the occurrence of medical comorbidities. This indicates that the AI-derived age may be a more effective indicator of a patient’s actual health status than their chronological age.

Improving Predictive Accuracy with Serial Testing

The use of a single ECG is capable of predicting all-cause mortality through AI-derived biological age estimates. However, research indicates that the accuracy of these predictions increases significantly when multiple ECGs are used.

The use of serial biological age estimates may enhance risk assessment for patients. By monitoring changes in biological age over time via multiple ECGs, clinicians may be better able to inform personalized care strategies.

The Broader Role of AI Imaging Biomarkers

The development of AI-ECG age is part of a wider trend in medical research utilizing AI to identify imaging biomarkers of aging. Beyond the heart, AI is being used to estimate biological age across several other physiological systems.

Current AI developments in age prediction include the analysis of the following imaging techniques:

• Brain imaging
• Chest imaging
• Abdominal imaging
• Bone imaging
• Facial imaging

These tools collectively aim to capture the physiological decline of an individual more accurately than traditional age-based metrics.

By integrating these AI-driven biological age estimates, medical professionals may be able to better identify patients at higher risk for mortality and comorbidities, regardless of their chronological age.