Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
Fan Ma, Yuntian Liu, Xiang Lan, Weipeng Zhou, Jun Ni, Mauro Giuffr\`e, 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, Lucila Ohno-Machado, Yong Chen, Hua Xu
Why It Matters
What makes this one worth your time
This research has the potential to transform how real-world evidence is generated and utilized in healthcare decision-making, impacting regulatory evaluations and clinical practices.
ReClaim leverages vast medical claims data to enhance disease prediction and healthcare expenditure forecasting.
Summary
The paper introduces ReClaim, a generative transformer model trained on extensive medical claims data to predict disease onset and forecast healthcare expenditures, demonstrating significant performance improvements over existing models.
Key contributions
- Development of ReClaim, a generative transformer model specifically for medical claims data.
- Demonstration of significant performance gains in disease prediction and healthcare expenditure forecasting compared to existing models.
- Validation of the model's effectiveness across multiple datasets and evaluation methods.
Notable insights
- The model's performance improved with scale, indicating that larger models can better capture complex healthcare dynamics.
- ReClaim's ability to generalize across time periods and data sources suggests its robustness in real-world applications.
Possible limitations
- Not stated in the abstract.
Abstract
arXiv:2605.02740v2 Announce Type: replace-cross Abstract: 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.