Artificial intelligence electrocardiogram-predicted biological age gap and mortality: Capturing dynamic risk with multiple electrocardiograms
Authors' conclusion
Many patients demonstrate biological aging that diverges from chronological aging. AI-derived biological age from a single ECG predicted all-cause mortality, but multiple ECGs significantly increased predictive accuracy. Serial biological age estimates may enhance risk assessment and inform personalized care.
Study context
- Population
- Cardiology patients aged 20–90 years with ≥ 2 electrocardiograms (ECGs) recordedpatients (337,415 ECGs, median follow-up, 4.5 years)
- Participants
- 46,960 patients
- Exposure
- multiple-ECG model vs single-ECG model
- Outcome
- Biological aging rate
Main finding
As reported in the abstract
Mean biological aging rate
0.7 ± 4.1 years/y
Observational data: associations, not effects.
Further findings
| Outcome | multiple-ECG model | single-ECG model | P value |
|---|---|---|---|
| Model performance for all-cause mortality0.763 vs 0.747 | P = 0.002 | ||
| Log-likelihood ratio test value | 6280 | 5225 | |
| C-index | 0.763 | 0.747 |
All-cause mortality by biological age gap
- Increasing biological age gap was associated with a nonlinear mortality hazard increase, whereas negative gaps had a small protective effect
Improvement in predictive accuracy by number of ECGs per patient
- The improvement in predictive accuracy increased with more ECGs per patient, plateauing at ≥ 10 ECGs
Original publication
Artificial intelligence electrocardiogram-predicted biological age gap and mortality: Capturing dynamic risk with multiple electrocardiograms. Heart Rhythm. Published 12 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →