Using Large Language Models for Chronic Disease Management Tasks: Scoping Review
JMIR Medical Informatics · 29.09.2025 · 13 · e66905-e66905
DOI: 10.2196/66905 ↗Kurz gefasst
Scoping Review in der Zeitschrift JMIR Medical Informatics, online erschienen am 29.09.2025. Verfasst von Henry Mukalazi Serugunda und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, School of Computing and Informatics Technology, Makerere University, Kampala, Uganda. Hauptthemen laut MEDLINE: Disease Management, Language. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Chronic diseases present significant challenges in health care, requiring effective management to reduce morbidity and mortality. While digital technologies like wearable devices and mobile applications have been widely adopted, large language models (LLMs) such as ChatGPT are emerging as promising technologies with the potential to enhance chronic disease management. However, the scope of their current applications in chronic disease management and associated challenges remains underexplored.
Objective
This scoping review investigates LLM applications in chronic disease management, identifies challenges, and proposes actionable recommendations.
Methods
A systematic search for English-language primary studies on LLM use in chronic disease management was conducted across PubMed, IEEE Xplore, Scopus, and Google Scholar to identify articles published between January 1, 2023, and January 15, 2025. Of the 605 screened records, 29 studies met the inclusion criteria. Data on study objectives, LLMs used, health care settings, study designs, users, disease management tasks, and challenges were extracted and thematically analyzed using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines.
Results
LLMs were primarily used for patient-centered tasks, including patient education and information provision (18/29, 62%) of studies, diagnosis and treatment (6/29, 21%), self-management and disease monitoring (8/29, 28%), and emotional support and therapeutic conversations (4/29, 14%). Practitioner-centered tasks included clinical decision support (8/29, 28%) and medical predictions (6/29, 21%). Challenges identified include inaccurate and inconsistent LLM responses (18/29, 62%), limited datasets (6/29, 21%), computational and technical (6/29, 21%), usability and accessibility (9/29, 31%), LLM evaluation (5/29, 17%), and legal, ethical, privacy, and regulatory (10/29, 35%). While models like ChatGPT, Llama, and Bard demonstrated use in diabetes management and mental health support, performance issues were evident across studies and use cases.
Conclusions
LLMs show promising potential for enhancing chronic disease management across patient and practitioner-centered tasks. However, challenges related to accuracy, data scarcity, usability, and ethical concerns must be addressed to ensure patient safety and equitable use. Future studies should prioritize the integration of LLMs with low-resource platforms, wearable and mobile technologies, developing culturally and age-appropriate interfaces, and establishing robust regulatory and evaluation frameworks to support safe, effective, and inclusive use in health care.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Information Technology, School of Computing and Informatics Technology, Makerere University, Kampala, Uganda.
- School of Computer Science and School of Cyberspace, Xiangtan University, Engineering Building, 2nd Floor, Yuhu District, Xiangtan, Hunan, 411105, China, 86 73158292718 ext 186.
- Department of Information Systems, School of Computing and Informatics Technology, Makerere University, Kampala, Uganda.
- Department of Computer Science, Faculty of Computing and Library Science, Kabale University, Kabale, Uganda.
- Department of Networks, School of Computing and Informatics Technology, Makerere University, Kampala, Uganda.
- Department of Community Health and Behavioral Sciences, School of Public Health, College of Health Sciences, Makerere University, Kampala, Uganda.
ORCID-Profile: Henry Mukalazi Serugunda, Ouyang Jianquan, Hasifah Kasujja Namatovu, Paul Ssemaluulu, Nasser Kimbugwe, Christopher Garimoi Orach, Peter Waiswa
Zitieren
APA
Serugunda, H. M., Jianquan, O., Kasujja Namatovu, H., Ssemaluulu, P., Kimbugwe, N., Garimoi Orach, C., & Waiswa, P. (2025). Using Large Language Models for Chronic Disease Management Tasks: Scoping Review. JMIR Medical Informatics, 13, e66905-e66905. https://doi.org/10.2196/66905
Vancouver
Serugunda HM, Jianquan O, Kasujja Namatovu H, Ssemaluulu P, Kimbugwe N, Garimoi Orach C, et al. Using Large Language Models for Chronic Disease Management Tasks: Scoping Review. JMIR Medical Informatics. 2025;13:e66905-e66905. doi:10.2196/66905
BibTeX
@article{Serugunda2025,
author = {Serugunda, Henry Mukalazi and Jianquan, Ouyang and Kasujja Namatovu, Hasifah and Ssemaluulu, Paul and Kimbugwe, Nasser and Garimoi Orach, Christopher and Waiswa, Peter},
title = {Using Large Language Models for Chronic Disease Management Tasks: Scoping Review},
journal = {JMIR Medical Informatics},
year = {2025},
volume = {13},
pages = {e66905--e66905},
doi = {10.2196/66905}
}
EUVIMED