TEDDY: A Pediatric Foundation Model for Disease Risk Prediction from ICD-Coded Diagnostic Histories
Researchers introduce TEDDY, a 1.84-million-parameter decoder transformer trained on 73 million ICD-10 diagnoses from 1.6 million children at a single pediatric institution. TEDDY achieved a median AUC of 72.0% across 797 disease-onset prediction tasks, outperforming several larger and commonly used baseline models. The model demonstrated strong performance even for rare diseases and could detect predictive signals more than two years before diagnosis.
Why it matters: This work shows that compact generative models can provide accurate, early risk predictions for a wide range of pediatric diseases, including rare conditions, without requiring massive datasets or very large models.
Full story at: arXiv Machine Learning ↗