MétaCan
Menu
Back to cohort
Record W4414600727 · doi:10.2196/66905

Using Large Language Models for Chronic Disease Management Tasks: Scoping Review

2025· article· en· W4414600727 on OpenAlexvenueno aff
Henry Mukalazi Serugunda, Jianquan Ouyang, Hasifah Kasujja Namatovu, Paul Mukasa Ssemaluulu, Nasser Kimbugwe, Christopher Garimoi Orach, Peter Waiswa

Bibliographic record

VenueJMIR Medical Informatics · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
Fundersnot available
KeywordsChronic diseaseDisease managementWearable computerRisk managementPatient safetyDiseaseHealth careMEDLINE

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Systematic review · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.780
Threshold uncertainty score0.365

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.145
GPT teacher head0.510
Teacher spread0.365 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSystematic review
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations11
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Medical InformaticsSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207