Integrating Text and Time-Series into (Large) Language Models to Predict Medical Outcomes

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Larbi, Iyadh Ben Cheikh, Ravichandran, Ajay Madhavan, Burchardt, Aljoscha, Roller, Roland
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914041757171712
author Larbi, Iyadh Ben Cheikh
Ravichandran, Ajay Madhavan
Burchardt, Aljoscha
Roller, Roland
author_facet Larbi, Iyadh Ben Cheikh
Ravichandran, Ajay Madhavan
Burchardt, Aljoscha
Roller, Roland
contents Large language models (LLMs) excel at text generation, but their ability to handle clinical classification tasks involving structured data, such as time series, remains underexplored. In this work, we adapt instruction-tuned LLMs using DSPy-based prompt optimization to process clinical notes and structured EHR inputs jointly. Our results show that this approach achieves performance on par with specialized multimodal systems while requiring less complexity and offering greater adaptability across tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_13696
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Integrating Text and Time-Series into (Large) Language Models to Predict Medical Outcomes
Larbi, Iyadh Ben Cheikh
Ravichandran, Ajay Madhavan
Burchardt, Aljoscha
Roller, Roland
Computation and Language
Large language models (LLMs) excel at text generation, but their ability to handle clinical classification tasks involving structured data, such as time series, remains underexplored. In this work, we adapt instruction-tuned LLMs using DSPy-based prompt optimization to process clinical notes and structured EHR inputs jointly. Our results show that this approach achieves performance on par with specialized multimodal systems while requiring less complexity and offering greater adaptability across tasks.
title Integrating Text and Time-Series into (Large) Language Models to Predict Medical Outcomes
topic Computation and Language
url https://arxiv.org/abs/2509.13696