arXiv Machine Learning

A Comparative Framework for Evaluating Foundation Models on Tabular Data: A Case Study in Healthcare

arXiv:2609. 22154v1 Announce Type: new Abstract: Tabular data is the most common format in clinical practice, encompassing laboratory results, medication records, diagnostic codes, and patient demographics.

arXiv Computation and Language
Aug 25

Scaling Electronic Health Record Foundation Models for Population Health Management

The paper introduces Scaling Electronic Health Record Foundation Models for Population Health Management, a large‑scale model trained on billions of medical events from over 5 million patients in Taiwan and the United States. By aligning ICD codes across different health systems, the model achieves strong scaling and generalization across 11 chronic disease prediction tasks, outperforming tree‑based, general, and biomedical language models with high sensitivity at 99% specificity. It also demonstrates superior few‑shot performance on the EHRShot benchmark and shows that cross‑system alignment provides a stronger pretraining signal than single‑site duplication in data‑limited scenarios.

By Liwen Sun, Hao-Ren Yao, Ophir Frieder, Xiang Qian, Chenyan Xiong
arXiv AI
Sep 3

General Demographic Pre-trained Models for Enhancing Predictive Performance Across Diseases and Population

The paper introduces the General Demographic Pre-trained (GDP) model, a lightweight foundation model that learns representations from the two most common clinical attributes—age and sex. By optimizing encoding and visit‑reordering strategies, GDP embeddings are shown to improve predictive performance when concatenated with raw features across various disease and geographic cohorts. The model outperforms several state‑of‑the‑art tabular foundation models and tree‑based algorithms, demonstrating that enriched demographic embeddings can enhance classification tasks while remaining fully compatible with standard classifiers.

By Li-Chin Chen, Ji-Tian Sheu, Yuh-Jue Chuang
arXiv AI
Aug 11

FoMoH: A clinically meaningful foundation model evaluation for structured electronic health records

arXiv:2505. 16941v4 Announce Type: replace-cross Abstract: Foundation models (FMs) promise to address core limitations of traditional supervised machine learning: (i) reliance on large amounts of labeled data, (ii) task specificity, and (iii) poor transportability.

By Vincent Jeanselme, Zilin Jing, Aparajita Kashyap, Chao Pang, Florent Pollet, Young Sang Choi, Xinzhuo Jiang, Yuta Kobayashi, Yanwei Li, Sara Matijevic, Karthik Natarajan, Shalmali Joshi
arXiv AI
Jun 2

Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints

arXiv:2604. 01841v2 Announce Type: replace Abstract: Clinical prediction from structured electronic health records (EHRs) is challenging due to high dimensionality, heterogeneity, class imbalance, and distribution shift.

By Minh-Khoi Pham, Thang-Long Nguyen Ho, Thao Thi Phuong Dao, Tai Tan Mai, Minh-Triet Tran, Marie E. Ward, Una Geary, Rob Brennan, Nick McDonald, Martin Crane, Marija Bezbradica
arXiv AI
Sep 17

Rethinking How We Evaluate Methodological Progress in Health AI

The study re‑implements 12 AI algorithms for electronic health records within a unified framework and evaluates them on MIMIC‑IV and NWICU datasets. It compares expert‑authored clinically meaningful tasks with randomly generated tasks, finding that pairwise algorithm comparisons transfer well across task families and datasets, yet clinically meaningful tasks show stronger task‑method interactions. The results also reveal that newer algorithms do not consistently outperform older ones, with gradient‑boosted trees remaining highly competitive when combined with modern EHR representations.

By Florent Pollet, Matthew McDermott
arXiv AI
Aug 18

Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

arXiv:2608. 16273v1 Announce Type: cross Abstract: Foresight-England (Foresight-E) is the first national-scale generative foundation model of electronic health records (EHRs), developed as a research pilot strictly for COVID-19 research.

By Simon Ellershaw, Christopher Tomlinson, Zeljko Kraljevic, Spiros Denaxas, Harry Hemingway, Cathie Sudlow, Angela M. Wood, Anoop D. Shah, Richard Dobson
arXiv AI
4d ago

Synthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark

Synthetic Hospital is an open, fully synthetic longitudinal electronic health record benchmark created from public medical education material. It contains 1,268 patients and 5,602 encounters, with every diagnosis, finding, and temporal relation grounded in standard ontologies and traceable back to its source. Physicians could not reliably distinguish its records from real charts, and current frontier AI models perform significantly below human experts on tasks such as reconstructing problem lists and summarizing charts.

By Christine Park, Valerie Chen, Tim Dettmers
arXiv Machine Learning
Aug 14

CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility

arXiv:2608. 12805v1 Announce Type: new Abstract: Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification.

By Akanta Das, Al Amin Farhad, Mrinmoy Sarkar Anto, David Rehkopf, Ayin Vala, Tanmoy Sarkar Pias