arXiv cs.AI· Mani Nagarathnam, Luke Benham, Paul Blazek, John Cashy, Kevin Chung, John Muenning, Hank Voeller, Shane Waxler, Davis White, Alison Callahan, Kevin Dysart, Andrew Loza, Michal A. Mankowski, Mattheus Ramsis, Nigam H. Shah, Karen K. Wong, Rahul Shah·· 3 小时前AI 评分42
Curiosity-0826-4B：覆盖儿科与成人人群的生成式医疗事件序列基础模型
Curiosity-0826-4B: Generative Medical Event Sequence Modeling Across Pediatric and Adult Populations
AI 导读
基于 Epic Cosmos 训练的生成式医疗事件基础模型 Curiosity-0826-4B 发布，通过模拟患者时间线实现零样本临床预测，参数规模从 1B 增至 4.3B，上下文窗口从 8K 扩展至 16K。
正文 · 原文
Authors:Mani Nagarathnam, Luke Benham, Paul Blazek, John Cashy, Kevin Chung, John Muenning, Hank Voeller, Shane Waxler, Davis White, Alison Callahan, Kevin Dysart, Andrew Loza, Michal A. Mankowski, Mattheus Ramsis, Nigam H. Shah, Karen K. Wong, Rahul Shah
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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.15710 [cs.LG] |
| (or arXiv:2611.15710v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15710 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Rahul Shah [view email]
[v1]
Wed, 11 Nov 2026 16:53:05 UTC (502 KB)
来源：arXiv cs.AI · arxiv.org