Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909016155750400 |
|---|---|
| author | Ma, Fan Liu, Yuntian Lan, Xiang Zhou, Weipeng Ni, Jun Giuffrè, Mauro Qian, Lingfei Peng, Xueqing Zhou, Yujia Weng, Ruey-Ling He, Huan Li, Lu Wang, Huiyuan Chen, Qingyu Loza, Andrew Rasmy, Laila Zhi, Degui Lu, Yuan Zeng, Chenjie Denny, Joshua C Schwamm, Lee Meeker, Daniella Ohno-Machado, Lucila Chen, Yong Xu, Hua |
| author_facet | Ma, Fan Liu, Yuntian Lan, Xiang Zhou, Weipeng Ni, Jun Giuffrè, Mauro Qian, Lingfei Peng, Xueqing Zhou, Yujia Weng, Ruey-Ling He, Huan Li, Lu Wang, Huiyuan Chen, Qingyu Loza, Andrew Rasmy, Laila Zhi, Degui Lu, Yuan Zeng, Chenjie Denny, Joshua C Schwamm, Lee Meeker, Daniella Ohno-Machado, Lucila Chen, Yong Xu, Hua |
| contents | Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, a generative transformer trained from scratch on 43.8 billion medical events from more than 200 million enrollees in the MarketScan claims data spanning 2008-2022. ReClaim models longitudinal trajectories across diagnoses, procedures, medications, and expenditure, and was scaled to 140 million, 700 million, and 1.7 billion parameters. Across over 1,000 disease-onset prediction tasks, ReClaim achieved a mean AUC of 75.6%, substantially outperforming disease-specific LightGBM (66.3%) and the transformer-based Delphi model (69.4%), with the largest gains for rare diseases. These advantages held across retrospective and prospective evaluations and in external validation on two independent datasets. Performance improved monotonically with scale, and post-training added 13.8 percentage points over pre-training alone. Beyond disease prediction, ReClaim captured financial outcomes and improved real-world evidence (RWE) analyses: for healthcare expenditure forecasting it increased explained variance from 0.28 to 0.37 relative to LightGBM, and in a target trial emulation it reduced systematic bias by 72% on average relative to Delphi. Together, these results establish administrative claims as a scalable substrate for healthcare foundation models and show that learned representations generalize across time periods and data sources, supporting disease surveillance, expenditure forecasting, and RWE generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02740 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims Ma, Fan Liu, Yuntian Lan, Xiang Zhou, Weipeng Ni, Jun Giuffrè, Mauro Qian, Lingfei Peng, Xueqing Zhou, Yujia Weng, Ruey-Ling He, Huan Li, Lu Wang, Huiyuan Chen, Qingyu Loza, Andrew Rasmy, Laila Zhi, Degui Lu, Yuan Zeng, Chenjie Denny, Joshua C Schwamm, Lee Meeker, Daniella Ohno-Machado, Lucila Chen, Yong Xu, Hua Artificial Intelligence Computation and Language Evidence derived from large-scale real-world data (RWD) is increasingly informing regulatory evaluation and healthcare decision-making. Administrative claims provide population-scale, longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications, yet their potential as a substrate for healthcare foundation models remains largely unexplored. Here we present ReClaim, a generative transformer trained from scratch on 43.8 billion medical events from more than 200 million enrollees in the MarketScan claims data spanning 2008-2022. ReClaim models longitudinal trajectories across diagnoses, procedures, medications, and expenditure, and was scaled to 140 million, 700 million, and 1.7 billion parameters. Across over 1,000 disease-onset prediction tasks, ReClaim achieved a mean AUC of 75.6%, substantially outperforming disease-specific LightGBM (66.3%) and the transformer-based Delphi model (69.4%), with the largest gains for rare diseases. These advantages held across retrospective and prospective evaluations and in external validation on two independent datasets. Performance improved monotonically with scale, and post-training added 13.8 percentage points over pre-training alone. Beyond disease prediction, ReClaim captured financial outcomes and improved real-world evidence (RWE) analyses: for healthcare expenditure forecasting it increased explained variance from 0.28 to 0.37 relative to LightGBM, and in a target trial emulation it reduced systematic bias by 72% on average relative to Delphi. Together, these results establish administrative claims as a scalable substrate for healthcare foundation models and show that learned representations generalize across time periods and data sources, supporting disease surveillance, expenditure forecasting, and RWE generation. |
| title | Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.02740 |