AI System Improves Pediatric Health Risk Stratification

Researchers at Hunan University of Arts and Science published in JMIR Med Inform in 2026 developed and validated an AI-driven multimodal framework to stratify pediatric health risks using a retrospective cohort of over 40,000 children aged 2–8. A BERT-based model achieved AUC-ROC 0.85 (95% CI 0.82–0.88), sensitivity 0.78, and specificity 0.80, aligning with expert assessment in 78 of 100 cases.