Applications, Challenges, and Future Directions of Large Language Models in Health Care Communication: Scoping Review

Clinical Snapshot

Key Findings

• P Value: Not reported — no inferential statistics applied to synthesised outcomes

• Effect Size: Not applicable — scoping review with descriptive synthesis only; no pooled effect sizes calculated

• Primary Outcome: Mapping of LLM applications in health care communication into four patterns: (1) transforming medical information (n=30 studies), (2) facilitating dynamic interaction (n=38 studies), (3) empowering communication capabilities (n=10 studies), and (4) optimising clinical workflows (n=18 studies)

• Nnt Or Sensitivity: Not applicable — no therapeutic, diagnostic, or prognostic effect measures reported; the review identifies a paradigm shift from 'static information processing' to 'dynamic intelligent interaction' as the overarching qualitative finding

• Confidence Interval: Not applicable — no meta-analytic synthesis performed

Clinical Application

LLM deployment in health care communication is technically feasible and already occurring across multiple domains, but the review identifies four major implementation barriers: technical reliability (accuracy, hallucination, consistency), social trust and adoption (patient and clinician acceptance), interaction and access barriers (digital literacy, equity, language), and clinical integration challenges (workflow fit, liability, governance). Feasibility at scale remains unproven given the absence of rigorous longitudinal implementation studies in the current evidence base. In Australia, LLM deployment in health care communication intersects with several regulatory and policy frameworks. The TGA has issued guidance on Software as a Medical Device (SaMD), under which LLMs used for clinical decision support or patient triage may require regulatory oversight. The RACGP has acknowledged AI tools in general practice but has not yet issued specific LLM communication guidelines. PBS implications are indirect — LLMs may influence prescribing communication and medication adherence support, but are not currently PBS-listed interventions. The Australian Digital Health Agency's National Digital Health Strategy 2023–2028 provides a relevant policy context for LLM integration into My Health Record and telehealth platforms. Health equity considerations are particularly salient in Australia given the needs of Aboriginal and Torres Strait Islander communities, rural and remote populations, and culturally and linguistically diverse (CALD) patients — groups for whom LLM communication tools may introduce additional access and cultural safety risks not addressed in this review's predominantly non-Australian evidence base. Clinicians, patients, and the general public interacting with health care systems where LLM-based communication tools may be deployed; particularly relevant to primary care, chronic disease management, patient education, and clinical documentation contexts

Abstract

BACKGROUND: Effective health care communication is crucial in the medical field. However, effective communication in clinical practice still faces numerous obstacles, and large language models (LLMs) offer various possibilities for improving the quality of medical communication. To date, there are no published reviews on the use of LLMs in health care communication. OBJECTIVE: This review sought to summarize the applications and challenges of LLMs in health care communication and to identify directions for future research. METHODS: A comprehensive literature search was conducted in PubMed, Embase, Web of Science, and the Cochrane Library from January 2018 to November 2025. The search and selection process followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline and the PRISMA-S (Preferred Reporting Items for Systematic Reviews and Meta-Analyses literature search extension) checklist. Eligible studies used LLMs to facilitate health care communication among the public, patients, and clinicians. Following rigorous data extraction and cross-checking, we conducted a quantitative analysis of characteristics of the included literature. Furthermore, using communication accommodation theory as a framework, we identified application patterns of LLMs in health care communication and summarized current challenges and future directions. RESULTS: Ninety-six studies were included in this review, all published between 2023 and 2025, summarizing 4 patterns of LLM application in health care communication: transforming medical information (n=30), facilitating dynamic interaction (n=38), empowering communication capabilities (n=10), and optimizing clinical workflows (n=18). The role of LLMs in health care communication is undergoing a paradigm shift from "static information processing" to "dynamic intelligent interaction." Although they show great promise for practical applications, current evaluation methods and dimensions exhibit significant heterogeneity. Furthermore, LLMs still face multiple challenges in their practical application in health care communication, including technical reliability issues, social trust and adoption, interaction and access barriers, and clinical integration challenges. CONCLUSIONS: Unlike previous studies that merely touched upon the challenges and future directions, this scoping review uses communication accommodation theory to systematically map the application patterns and developmental landscape of LLM-mediated health care communication. Health care communication powered by LLMs holds significant innovation potential and is currently still in the early stages of rapid development. Future research should focus on optimizing model performance, strengthening ethical governance frameworks, enhancing human-machine collaboration models, and ensuring responsible application of LLMs in health care through rigorous empirical validation.

References

1. 1.Chang, J., Peng, R., Chen, X., Zhu, Y., Miao, R., Cao, Z., & Feng, H. (2026). Applications, challenges, and future directions of large language models in health care communication: Scoping review. Journal of Medical Internet Research. https://doi.org/10.2196/84726