Salvato in:
Dettagli Bibliografici
Autori principali: Yildiz, Yusuf, Nenadic, Goran, Jani, Meghna, Jenkins, David A.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.18246
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908631993155584
author Yildiz, Yusuf
Nenadic, Goran
Jani, Meghna
Jenkins, David A.
author_facet Yildiz, Yusuf
Nenadic, Goran
Jani, Meghna
Jenkins, David A.
contents Objective: Large language models (LLMs) are attracting increasing interest in healthcare. This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks, with a focus on their ability to process longitudinal electronic health record (EHR) data. Findings: LLMs show promise in handling multimodal and longitudinal EHR data and can support multi-outcome predictions for diverse health conditions. However, methodological, validation, infrastructural, and regulatory chal- lenges remain. These include inadequate methods for time-to-event modelling, poor calibration of predictions, limited external validation, and bias affecting underrepresented groups. High infrastructure costs and the absence of clear regulatory frameworks further prevent adoption. Implications: Further work and interdisciplinary collaboration are needed to support equitable and effective integra- tion into the clinical prediction. Developing temporally aware, fair, and explainable models should be a priority focus for transforming clinical prediction workflow.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18246
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Will Large Language Models Transform Clinical Prediction?
Yildiz, Yusuf
Nenadic, Goran
Jani, Meghna
Jenkins, David A.
Computers and Society
Computation and Language
Objective: Large language models (LLMs) are attracting increasing interest in healthcare. This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks, with a focus on their ability to process longitudinal electronic health record (EHR) data. Findings: LLMs show promise in handling multimodal and longitudinal EHR data and can support multi-outcome predictions for diverse health conditions. However, methodological, validation, infrastructural, and regulatory chal- lenges remain. These include inadequate methods for time-to-event modelling, poor calibration of predictions, limited external validation, and bias affecting underrepresented groups. High infrastructure costs and the absence of clear regulatory frameworks further prevent adoption. Implications: Further work and interdisciplinary collaboration are needed to support equitable and effective integra- tion into the clinical prediction. Developing temporally aware, fair, and explainable models should be a priority focus for transforming clinical prediction workflow.
title Will Large Language Models Transform Clinical Prediction?
topic Computers and Society
Computation and Language
url https://arxiv.org/abs/2505.18246