Artificial Intelligence–Derived Electrocardiographic Age Predicts Mortality in Adults With Congenital Heart Disease
Authors' conclusion
Delta-age, the difference between AI-ECG and chronological age, is an independent predictor of all-cause mortality in ACHD.
Study context
- Population
- Adults with congenital heart disease (ACHD) (age >18 years), 1992–2023subjects tested (50% females)
- Participants
- 5,780 adults
- Exposure
- Relationship between delta-age and mortality
- Outcome
- Chronological age and AI-ECG age
Methodological detailsCox proportional hazard models adjusting for influential clinical factors
- Cox proportional hazard models adjusting for influential clinical factors
Main finding
As reported in the abstract
Mean chronological age
39.1 ± 15.0 years
AI-ECG age
52.3 ± 16.6 years
Observational data: associations, not effects.
Further findings
CHD complexity
| Outcome | HR (CI) | P value | |
|---|---|---|---|
| Mortality risk per 5-year increment in delta-ageIncreased mortality risk | 1.06 (1.03–1.09) | P < 0.05 | |
| 0.512Hazard ratio (log scale) |
Median, years
| Outcome | Mild | Moderate | Severe | |
|---|---|---|---|---|
| Delta-age by CHD complexity | Not reported in the abstract | 11.5 (IQR 3.5–21.3) | 15.8 (IQR 3.5–31.2) | mild: not reported in the abstract |
- Delta-age by CHD complexity: simple median 6.7 (IQR 0.3–14.2) years
- Mortality risk per 5-year increment in delta-age: adjusted for chronologic age, CHD complexity, and other clinical variables
Death · median follow-up of 6.4 years (IQR: 1.58-13.7 years)
- Patients died
- 839 (14.5%)
Original publication
Artificial Intelligence–Derived Electrocardiographic Age Predicts Mortality in Adults With Congenital Heart Disease. JACC Adv. Published 14 May 2025. doi:10.
Summarised from the published abstract; every number is checked against it