ReClaim：用全国医保理赔数据预训练医疗基础模型
Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
研究团队提出 ReClaim，基于 MarketScan 数据库中超过 2 亿参保人的 438 亿条理赔记录从零预训练生成式基础模型，联合学习诊断、手术、用药与费用信息，训练数据截止 2022 年底。
Authors:Fan Ma, Yuntian Liu, Xiang Lan, Weipeng Zhou, Jun Ni, Mauro Giuffrè, Lingfei Qian, Xueqing Peng, Yujia Zhou, Ruey-Ling Weng, Huan He, Lu Li, Huiyuan Wang, Qingyu Chen, Andrew Loza, Laila Rasmy, Degui Zhi, Yuan Lu, Chenjie Zeng, Joshua C Denny, Lee Schwamm, Daniella Meeker, Brian Ondov, Lucila Ohno-Machado, Yong Chen, Hua Xu
Abstract:Real-world data increasingly inform regulatory and clinical decisions. Administrative claims, among their major sources, continuously track care and its cost across providers throughout enrollment, yet remain largely unexplored for healthcare foundation models. Here we present ReClaim, a family of generative foundation models built on 43.8 billion claims records from more than 200 million enrollees in the MarketScan Research Databases. ReClaim learns diagnoses, procedures, medications and expenditure jointly through pre-training from scratch, then specializes for downstream prediction tasks through post-training, with a training cutoff at the end of 2022. In predicting more than 1,000 diseases, ReClaim achieved a mean ROC-AUC of 0.769, outperforming disease-specific gradient-boosted models (0.663) and a transformer-based baseline (0.694), and retained this advantage when generalizing to two independent cross-domain electronic health record datasets. ReClaim also outperformed gradient-boosted models in forecasting next-year expenditure and in identifying high-need, high-cost enrollees. ReClaim maintained its advantage in disease prediction and expenditure forecasting on post-cutoff data (2023-2024). Beyond prediction, ReClaim representations used as covariates resulted in improved effect estimates compared with algorithm-derived covariates, when benchmarked against results expected from randomized controlled trials. Together, these results establish nationwide insurance claims as a scalable substrate for healthcare foundation models supporting disease prediction, expenditure forecasting and confounding adjustment in real-world evidence studies. Code is available at this https URL.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.02740 [cs.AI] |
| (or arXiv:2605.02740v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02740 arXiv-issued DOI via DataCite |
Submission history
From: Fan Ma [view email]
[v1]
Mon, 4 May 2026 15:38:31 UTC (6,961 KB)
[v2]
Tue, 5 May 2026 22:30:29 UTC (6,961 KB)
[v3]
Fri, 30 Oct 2026 20:48:02 UTC (6,774 KB)
来源：arXiv cs.CL · arxiv.org