Pediatric anesthesia & critical care
Prediction of neurological outcome after pediatric cardiac arrest using heart rate variability and machine learning
Authors' conclusion
Using machine learning, HRV features within 24 h after pediatric cardiac arrest predict unfavorable outcome with AUROC 0.8. Adding clinical variables did not improve model performance.
Study context
- Population
- Children receiving post-arrest care in the PICU at the Children's Hospital of Philadelphia, 2020–202351% unfavorable outcome
- Participants
- 75 children
- Comparison
- Heart rate variability (HRV) + arrest characteristics vs HRV + age
- Outcome
- Prediction of unfavorable neurological outcome:
- Pediatric Cerebral Performance Category 4-6
- Increase >1 from baseline
Methodological detailsmachine learning (Extreme Gradient Boosting), cross-validation, single-centre
- Machine learning (Extreme Gradient Boosting)
- Cross-validation
- Single-centre
Performance
As reported in the abstract
Unfavorable neurological outcome (AUROC) · first 24 h after ROSC
HRV + age
0.80
AUROC · 95% CI 0.68–0.88
HRV + arrest characteristics
0.83
AUROC · CI 0.73–0.92
P > 0.41
Further findings
Performance across sequential 6-h epochs
- Performance similar across the 6-h epochs
- p's > 0.1
Original publication
Prediction of neurological outcome after pediatric cardiac arrest using heart rate variability and machine learning. Resuscitation. Published 5 January 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →