Accepted for/Published in: JMIR Medical Informatics
Date Submitted: Sep 26, 2024
Date Accepted: May 23, 2025
Using Large Language Models for Chronic Disease Management Tasks: A Scoping Review
ABSTRACT
Background:
chronic diseases present significant challenges in healthcare, requiring effective management to reduce morbidity and mortality. The use of Large Language Models (LLMs) such as ChatGPT in chronic disease management is an emerging area of interest with the potential to enhance chronic disease management tasks. This study investigated the application and challenges of using LLMs for chronic disease management.
Objective:
This study, aimed at exploring: i. The tasks in chronic disease management performed by LLMs. ii. The challenges associated with using LLMs for chronic disease management.
Methods:
A search for relevant literature was conducted across PubMed, IEEE Xplore, and Google Scholar to identify articles published between 1st January 2023 and 30th March 2024 and yielded only 14 relevant articles
Results:
From the 14 included articles, seven studies used experimental design methodology (n=7), three qualitative research designs (n=3), three quantitative studies (n=3), one used a cross-sectional study design (n=1) and one used a comparative Study (n=1). The findings reveal that LLMs are used for; (i) patient-centered tasks including diagnosis and treatment, medical education, disease monitoring, and self-management, and (ii) practitioner-centered tasks including clinical decision support and medical predictions.
Conclusions:
The increasing interest in utilizing LLMs like ChatGPT for chronic disease management tasks is evident from the findings of this scoping review. Although LLMs have the potential to support disease management tasks for both patients and healthcare practitioners, addressing the identified challenges is crucial to ensure patient safety and ethical use. There is a need for regulatory oversight and standards to guide LLM development, evaluation, and ethical use. Future research should also focus on seamlessly integrating LLMs including multimodal LLMs into healthcare systems, wearable devices, and mobile health applications to increase LLM accuracy levels and information sharing. Clinical Trial: not applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.