A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency

• URL: http://arxiv.org/abs/2604.22348v1
• Date: Fri, 24 Apr 2026 08:32:47 GMT
• Title: A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency
• Abstract summary: Self-supervised foundation models have emerged as a promising approach for leveraging large-scale unlabeled healthcare records.<n>In natural language processing, scaling laws suggest that larger models achieve predictably lower pretraining losses.<n>We evaluated the relationship between model scale and downstream task performance for structured medical foundation models.
• Score: 2.107969466194361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical risk prediction using longitudinal medical data supports individualized care. Self-supervised foundation models have emerged as a promising approach for leveraging large-scale unlabeled healthcare records. In natural language processing, scaling laws suggest that larger models achieve predictably lower pretraining losses, supporting the foundation model paradigm. However, for structured medical data, characterized by a limited vocabulary and sparse observations, whether increasing model size consistently improves downstream predictions is unclear, as most studies evaluate only a single model scale. In this study, we evaluated the relationship between model scale and downstream task performance for structured medical foundation models. Using a random sample (2.3 million patients, 32 hospitals) from a nationwide 519-hospital Japanese claims database, we pretrained encoder-only Transformers at five scales (2.2M-101M parameters) for disease incidence and medication prediction. Downstream performance saturated at task-dependent thresholds: disease prediction benefited from larger models (32M-101M), whereas medication prediction saturated at 11M, reducing pretraining time by 178 h. Across all tasks, the best-performing model consistently outperformed a Light Gradient Boosting Machine baseline in the area under the precision-recall curve. These findings indicate that, unlike the monotonically decreasing pretraining loss, the optimal model size varied depending on task characteristics. This task-dependent saturation provides practical guidance for balancing predictive performance and computational cost in structured medical foundation models.

Related papers

• Bootstrapping-based Regularisation for Reducing Individual Prediction Instability in Clinical Risk Prediction Models [2.1127261244588156]
  We propose a novel bootstrapping-based regularisation framework that embeds the bootstrapping process directly into the training of deep neural networks.<n>This approach constrains prediction variability across resampled datasets, producing a single model with inherent stability properties.<n>We evaluated models constructed using the proposed regularisation approach against conventional and ensemble models.
  arXiv  Detail & Related papers  (2026-02-11T20:47:30Z)
• The Patient is not a Moving Document: A World Model Training Paradigm for Longitudinal EHR [3.9541492005870604]
  We introduce SMB-Structure, a world model for structured EHR that grounds a joint-embedding prediction architecture (JEPA) with next-token prediction (SFT)<n>We validate across two large-scale cohorts: Memorial Sloan Kettering (23,319 oncology patients; 323,000+ patient-years) and INSPECT (19,402 pulmonary embolism patients)
  arXiv  Detail & Related papers  (2026-01-29T18:49:37Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• Analysis of heart failure patient trajectories using sequence modeling [2.5101181751229915]
  Mamba architecture outperformed an advanced Transformer (Transformer++) based on Llama in handling long context lengths.<n>Llama achieves the highest predictive discrimination, best calibration, and showed robustness across all tasks, followed by Mambas.<n>This paper presents a first ablation study with systematic design choices for input tokenization, model configuration and temporal data preprocessing.
  arXiv  Detail & Related papers  (2025-11-20T22:43:25Z)
• Generative Medical Event Models Improve with Scale [11.04430289614517]
  We present the largest scaling-law study of medical event data.<n>We pretrained a series of compute-optimal models with up to 1 billion parameters.<n>We studied 78 real-world tasks, including diagnosis prediction, disease prognosis, and healthcare operations.
  arXiv  Detail & Related papers  (2025-08-16T17:00:51Z)
• Zero-shot Medical Event Prediction Using a Generative Pre-trained Transformer on Electronic Health Records [8.575985305475355]
  Generative pre-trained transformers (GPT) can leverage Longitudinal Data in EHRs to predict future events.<n> fine-tuning of these models can enhance task-specific performance, but it becomes costly when applied to many clinical prediction tasks.<n>A pretrained foundation model can be used in zero-shot forecasting setting, offering a scalable alternative to fine-tuning separate models for each outcome.
  arXiv  Detail & Related papers  (2025-03-07T19:26:47Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Learning Sample Difficulty from Pre-trained Models for Reliable Prediction [55.77136037458667]
  We propose to utilize large-scale pre-trained models to guide downstream model training with sample difficulty-aware entropy regularization. We simultaneously improve accuracy and uncertainty calibration across challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-20T07:29:23Z)
• Clinical Deterioration Prediction in Brazilian Hospitals Based on Artificial Neural Networks and Tree Decision Models [56.93322937189087]
  An extremely boosted neural network (XBNet) is used to predict clinical deterioration (CD) The XGBoost model obtained the best results in predicting CD among Brazilian hospitals' data.
  arXiv  Detail & Related papers  (2022-12-17T23:29:14Z)
• Density-Aware Personalized Training for Risk Prediction in Imbalanced Medical Data [89.79617468457393]
  Training models with imbalance rate (class density discrepancy) may lead to suboptimal prediction. We propose a framework for training models for this imbalance issue. We demonstrate our model's improved performance in real-world medical datasets.
  arXiv  Detail & Related papers  (2022-07-23T00:39:53Z)
• Identifying and mitigating bias in algorithms used to manage patients in a pandemic [4.756860520861679]
  Logistic regression models were created to predict COVID-19 mortality, ventilator status and inpatient status using a real-world dataset. Models showed a 57% decrease in the number of biased trials. After calibration, the average sensitivity of the predictive models increased from 0.527 to 0.955.
  arXiv  Detail & Related papers  (2021-10-30T21:10:56Z)
• 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)

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.