Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims

• URL: http://arxiv.org/abs/2605.02740v2
• Date: Tue, 05 May 2026 22:30:29 GMT
• Title: Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims
• Abstract summary: Administrative claims provide longitudinal records of healthcare utilization, expenditure, and detailed coding of diagnoses, procedures, and medications.<n>We present ReClaim, a generative transformer trained from scratch on 43.8 billion medical events from the MarketScan claims data spanning 2008-2022.
• Score: 31.673662680042337
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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.

Related papers

• TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories [4.659237660627583]
  TEDDY (Temporal Event Decoder for Disease in Youth) trained on 73 million ICD-10 diagnoses from 1.6 million children.<n>Across 797 disease-onset prediction tasks spanning 16 ICD-10 chapters, TEDDY achieved a median AUC of 72.0%.<n> Predictive signal remained detectable more than two years before first recorded diagnosis.
  arXiv  Detail & Related papers  (2026-07-15T16:17:28Z)
• Evidence-Grounded AI for Musculoskeletal Care [106.59121478639402]
  OrthoPilot is a clinical artificial intelligence system powered by a large language model (LLM)<n>It integrates hospital data streams with authoritative external knowledge for continuous musculoskeletal care.<n>In a full-pathway reader study against 81 orthopaedic physicians, OrthoPilot outperformed experts with 25 years of experience.
  arXiv  Detail & Related papers  (2026-07-14T09:03:26Z)
• Explainable Admission-Level Predictive Modeling for Prolonged Hospital Stay in Elderly Populations: Challenges in Low- and Middle-Income Countries [65.4286079244589]
  Prolonged length of stay (pLoS) is a significant factor associated with the risk of adverse in-hospital events.<n>We develop and explain a predictive model for pLos using admission-level patient and hospital administrative data.
  arXiv  Detail & Related papers  (2026-01-07T23:35:24Z)
• Rethinking Retrieval-Augmented Generation for Medicine: A Large-Scale, Systematic Expert Evaluation and Practical Insights [42.23030568766672]
  Large language models (LLMs) are transforming the landscape of medicine.<n>Retrieval-augmented generation (RAG) has been widely adopted to address these limitations.<n>We present the most comprehensive expert evaluation of RAG in medicine to date.
  arXiv  Detail & Related papers  (2025-11-10T06:00:12Z)
• Loss Given Default Prediction Under Measurement-Induced Mixture Distributions: An Information-Theoretic Approach [0.2538209532048866]
  Loss Given Default (LGD) modeling faces a fundamental data quality constraint.<n>90% of available training data consists of proxy estimates based on pre-distress balance sheets rather than actual recovery outcomes from completed bankruptcy proceedings.
  arXiv  Detail & Related papers  (2025-10-29T10:11:38Z)
• An Agentic System for Rare Disease Diagnosis with Traceable Reasoning [69.46279475491164]
  We introduce DeepRare, the first rare disease diagnosis agentic system powered by a large language model (LLM)<n>DeepRare generates ranked diagnostic hypotheses for rare diseases, each accompanied by a transparent chain of reasoning.<n>The system demonstrates exceptional diagnostic performance among 2,919 diseases, achieving 100% accuracy for 1013 diseases.
  arXiv  Detail & Related papers  (2025-06-25T13:42:26Z)
• Medical Hallucinations in Foundation Models and Their Impact on Healthcare [71.15392179084428]
  Hallucinations in foundation models arise from autoregressive training objectives.<n>Top-performing models exceeded 97% accuracy when augmented with chain-of-thought prompting.
  arXiv  Detail & Related papers  (2025-02-26T02:30:44Z)
• DeLLiriuM: A large language model for delirium prediction in the ICU using structured EHR [1.4699314771635081]
  Delirium is an acute confusional state that has been shown to affect up to 31% of patients in the intensive care unit (ICU) We develop and validate DeLLiriuM on ICU admissions from 104,303 patients pertaining to 195 hospitals across three large databases.
  arXiv  Detail & Related papers  (2024-10-22T18:56:31Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Predicting Treatment Adherence of Tuberculosis Patients at Scale [0.6873562466909032]
  Non-adherence to TB medication is a significant cause of mortality and morbidity. We formulate and solve the machine learning problem of early prediction of non-adherence based on a custom rank-based metric. Our findings indicate that risk stratification of non-adherent patients is a viable, deployable-at-scale ML solution.
  arXiv  Detail & Related papers  (2022-11-05T17:00:21Z)
• SANSformers: Self-Supervised Forecasting in Electronic Health Records with Attention-Free Models [48.07469930813923]
  This work aims to forecast the demand for healthcare services, by predicting the number of patient visits to healthcare facilities. We introduce SANSformer, an attention-free sequential model designed with specific inductive biases to cater for the unique characteristics of EHR data. Our results illuminate the promising potential of tailored attention-free models and self-supervised pretraining in refining healthcare utilization predictions across various patient demographics.
  arXiv  Detail & Related papers  (2021-08-31T08:23:56Z)
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data [81.00385374948125]
  We present UNcertaInTy-based hEalth risk prediction (UNITE) model. UNITE provides accurate disease risk prediction and uncertainty estimation leveraging multi-sourced health data. We evaluate UNITE on real-world disease risk prediction tasks: nonalcoholic fatty liver disease (NASH) and Alzheimer's disease (AD) UNITE achieves up to 0.841 in F1 score for AD detection, up to 0.609 in PR-AUC for NASH detection, and outperforms various state-of-the-art baselines by up to $19%$ over the best baseline.
  arXiv  Detail & Related papers  (2020-10-22T02:28:11Z)
• All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III) [0.0]
  This study was performed using 42,818 hospital admissions involving 35,348 patients. Over 75 million events across multiple data sources were processed, resulting in over 355 million tokens. It is possible to predict in-hospital mortality with much better confidence and higher reliability from models built using all sources of data.
  arXiv  Detail & Related papers  (2020-09-02T22:12:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.