Article

Disease Risk Prediction Using Structured EHR Data: Can Generalist Large Language Models Match Specialized Clinical Foundation Models? A Comparative Evaluation with Fine-Tuning

2026-05-01

Abstract excerpt

<h4>Background</h4> Electronic health records (EHRs) with clinical decision support tools are now ubiquitous in healthcare organizations. Clinical foundation models (CFMs) pretrained on large-scale, heterogeneous structured EHR data have emerged as a powerful approach to improve predictive performance and generalizability. Meanwhile, large language models (LLMs) pretrained on broad data sources are being applied...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6d1fa544-f1d5-54d7-964d-381f1a874efd
DOI: 10.64898/2026.04.24.26351503

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Disease Risk Prediction Using Structured EHR Data: Can Generalist Large Language Models Match Specialized Clinical Foundation Models? A Comparative Evaluation with Fine-TuningDOI 10.64898/2026.04.24.26351503Read

Large language models improve transferability of electronic health record-based predictions across countries and coding systemsSemantic proximity Read

Leveraging Pretrained Large Language Model for Prognosis of Type 2 Diabetes Using Longitudinal Medical RecordsSemantic proximity Read

PANCDetect: Early Detection of Pancreatic Cancer from Multimodal EHR data with LLM EmbeddingsSemantic proximity Read

Language-model-based patient embedding using electronic health records facilitates phenotyping, disease forecasting, and progression analysisSemantic proximity Read

Generalist Foundation Models Are Not Clinical Enough for Hospital OperationsSemantic proximity Read

Large Language Models Improve Cancer Survival Prediction Using Real-World Clinical NotesSemantic proximity Read

ExCaPT: Explainable Cancer Prediction with Transformer-based modelsSemantic proximity Read

Enformer: An encoder-decoder generative model to enhance prediction of disease outcomes using electronic health recordsSemantic proximity Read

EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution ShiftSemantic proximity Read

Can GPT Be Used as an Alternative Prediction Model to Traditional Machine Learning and Neural Networks on Low-Volume Clinical Data?Semantic proximity Read

Longitudinal Masked Representation Learning for Pulmonary Nodule Diagnosis from Language Embedded EHRsSemantic proximity Read

Predicting Behavioral Determinants of Health from Clinical Text Using Transformer Models and BiLSTMSemantic proximity Read