Article

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

2025-02-04

Abstract excerpt

Variation in medical practices and reporting standards across healthcare systems limits the transferability of prediction models based on structured electronic health record (EHR) data. We introduce GRASP, a novel transformer-based architecture that enhances the generalizability of EHR-based prediction by embedding medical codes into a unified semantic space using a large language model. We applied GRASP to predic...

Topics

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

Identifiers and source

Literature Corpus work: e5c30a33-aa2e-5758-aa02-a2a268705002
DOI: 10.1101/2025.02.03.25321597

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Large language models improve transferability of electronic health record-based predictions across countries and coding systemsDOI 10.1101/2025.02.03.25321597Read

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

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

Large Language Models Facilitate the Generation of Electronic Health Record Phenotyping AlgorithmsSemantic proximity Read

GEN-KnowRD: Reframing AI for Rare Disease RecognitionSemantic proximity Read

Extraction of Human Phenotype Ontology (HPO) Concepts from Clinical Notes Utilizing Large Language Models (LLM) with Model Context Protocol (MCP)Semantic proximity Read

Targeted use of large language models for EHR-based computable phenotyping.Semantic proximity Read

Reframing AI for Rare Disease RecognitionSemantic proximity Read

Automatic ICD coding using LLMs: a systematic reviewSemantic proximity Read

Longitudinal modeling of multimorbidity trajectories using large language modelsSemantic proximity Read

Large language models facilitate the generation of electronic health record phenotyping algorithms.Semantic proximity Read

Comparing natural language processing representations of disease sequences for prediction in the electronic healthcare recordSemantic proximity Read

Towards understanding the disease landscape of clinical trials in Germany: Ontology and embedding-based pipelines versus Large Language Models for ICD-10 HarmonizationSemantic proximity Read