Heart failure & cardiomyopathies
Predicting 1-Year Mortality After Pediatric Heart Transplantation Using Machine Learning: A Systematic Review and Meta-Analysis
Authors' conclusion
ML-based models outperform traditional approaches and capture evolving risk profiles across eras, supporting their integration into pediatric HT risk stratification to enhance accuracy and equity in transplant decision-making.
Study context
- Population
- Children undergoing heart transplantation; studies applying machine learning (ML) methods to predict 1-year mortality after pediatric HT
- Participants
- 33,286 children5 studies
- Comparison
- ML-based models predicting 1-year mortality after pediatric HT
- Outcome
- Pooled ML performance for 1-year mortality
- Follow-up
- 1 year
Methodological detailsrandom-effects meta-analysis, era-stratified Kaplan-Meier analyses
- Random-effects meta-analysis
- Era-stratified Kaplan-Meier analyses
Pooled result
As reported in the abstract
Area under the receiver-operating characteristic curve
0.86
95% CI 0.82–0.90
Sensitivity
90%
95% CI 88.2–92.1
Specificity
91%
95% CI 89.1–93.0
Diagnostic OR
142
95% CI 122.2–178.8
Further pooled results
Temporal shift in risk predictors
- Shift from ischemic time and pulmonary vascular resistance to extracorporeal membrane oxygenation/ventricular assist device dependence, donor-recipient mismatch, and socioeconomic factors
Original publication
Predicting 1-Year Mortality After Pediatric Heart Transplantation Using Machine Learning: A Systematic Review and Meta-Analysis. JACC Adv. Published 12 December 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →