cs.LGNov 11, 2026

Curiosity-0826-4B: Generative Medical Event Sequence Modeling Across Pediatric and Adult Populations

Authors: Mani Nagarathnam, Luke Benham, Paul Blazek, John Cashy, Kevin Chung, John Muenning, Hank Voeller, Shane Waxler, 

Organizations: Epic Systems · Department of Medicine, Stanford School of Medicine · The Children’s Hospital of Philadelphia · Department of Biomedical Informatics and Data Science, Yale University · 

Abstract

We introduce Curiosity-0826-4B, an updated version of the generative medical event foundation model trained on Epic Cosmos that simulates patient timelines to produce zero-shot clinical predictions. Curiosity-0826-4B incorporates a broader patient population and richer clinical event representations, while generally matching or exceeding Curiosity-0226-1B, the largest model in the previous Curiosity-0226 series, on evaluated tasks supported by both models. Laboratory value prediction improved, with MAE 18--46% lower than that of Curiosity-0226-1B. We evaluated prediction of disease events across pediatric cohorts aged 2--17 years. AUROCs for new asthma diagnosis (0.742--0.785) and asthma exacerbation (0.829--0.852) were comparable to those in the adult reference cohort, while AUROCs for sickle cell crisis (0.820--0.847) were lower than in adults (0.915). Explicit representation of documented death enabled new mortality prediction tasks among adults across hospice, inpatient, and ambulatory settings (AUROC 0.821--0.942). Scaling-law analysis guided compute-optimal initial pretraining followed by continued pretraining with context extension. The resulting Curiosity-0826-4B model has more parameters (4.3B versus 1B) and a longer context window (16K versus 8K). It processes 56% fewer training tokens and requires 2.2 times the training floating point operations (FLOPs) compared with its predecessor. By extending a common zero-shot prediction strategy to pediatric patients and additional outcomes, Curiosity-0826-4B broadens opportunities to develop clinical and operational applications without training separate task-specific models. Further validation should assess local calibration, performance across patient subgroups and event frequencies, timeline completion rates, and generalization to new settings, alongside prospective evaluation of clinical and operational utility.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

    Aug 17, 2026Simon Ellershaw, Christopher Tomlinson, Zeljko Kraljevic +6EHR Foundation ModelsNext-Event Prediction

  2. Training Large Language Models to Predict Clinical Events

    May 12, 2026Benjamin Turtel, Paul Wilczewski, Kris SkotheimHealthcareLanguage Model Calibration

  3. TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories

    Jul 15, 2026Matthew Brady Neeley, Jorge Botas, Johnathan Jia +5EHR Foundation ModelsClinical Prediction