Large Language Models are Powerful Electronic Health Record Encoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hegselmann, Stefan, von Arnim, Georg, Rheude, Tillmann, Kronenberg, Noel, Sontag, David, Hindricks, Gerhard, Eils, Roland, Wild, Benjamin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913026482896896
author Hegselmann, Stefan
von Arnim, Georg
Rheude, Tillmann
Kronenberg, Noel
Sontag, David
Hindricks, Gerhard
Eils, Roland
Wild, Benjamin
author_facet Hegselmann, Stefan
von Arnim, Georg
Rheude, Tillmann
Kronenberg, Noel
Sontag, David
Hindricks, Gerhard
Eils, Roland
Wild, Benjamin
contents Electronic Health Records (EHRs) offer considerable potential for clinical prediction, but their complexity and heterogeneity challenge traditional machine learning. Domain-specific EHR foundation models trained on unlabeled EHR data have shown improved predictive accuracy and generalization. However, their development is constrained by limited data access and site-specific vocabularies. We convert EHR data into plain text by replacing medical codes with natural-language descriptions, enabling general-purpose Large Language Models (LLMs) to produce high-dimensional embeddings for downstream prediction tasks without access to private medical training data. LLM-based embeddings perform on par with a specialized EHR foundation model, CLMBR-T-Base, across 15 clinical tasks from the EHRSHOT benchmark. In an external validation using the UK Biobank, an LLM-based model shows statistically significant improvements for some tasks, which we attribute to higher vocabulary coverage and slightly better generalization. Overall, we reveal a trade-off between the computational efficiency of specialized EHR models and the portability and data independence of LLM-based embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17403
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Models are Powerful Electronic Health Record Encoders
Hegselmann, Stefan
von Arnim, Georg
Rheude, Tillmann
Kronenberg, Noel
Sontag, David
Hindricks, Gerhard
Eils, Roland
Wild, Benjamin
Machine Learning
Artificial Intelligence
Computation and Language
Electronic Health Records (EHRs) offer considerable potential for clinical prediction, but their complexity and heterogeneity challenge traditional machine learning. Domain-specific EHR foundation models trained on unlabeled EHR data have shown improved predictive accuracy and generalization. However, their development is constrained by limited data access and site-specific vocabularies. We convert EHR data into plain text by replacing medical codes with natural-language descriptions, enabling general-purpose Large Language Models (LLMs) to produce high-dimensional embeddings for downstream prediction tasks without access to private medical training data. LLM-based embeddings perform on par with a specialized EHR foundation model, CLMBR-T-Base, across 15 clinical tasks from the EHRSHOT benchmark. In an external validation using the UK Biobank, an LLM-based model shows statistically significant improvements for some tasks, which we attribute to higher vocabulary coverage and slightly better generalization. Overall, we reveal a trade-off between the computational efficiency of specialized EHR models and the portability and data independence of LLM-based embeddings.
title Large Language Models are Powerful Electronic Health Record Encoders
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.17403