Current applications and challenges in large language models for patient care: a systematic review
importance 6/10
ai assisted
Artificial Intelligence in Healthcare and Education clinical care stage: research
Problem
Information on how large language models are used and limited in patient care was unsystematized.
Why it matters
LLMs could personalize patient education and broaden access to medical knowledge across specialties.
What the AI did
A systematic review of 89 studies (2022-2023) across 29 medical specialties synthesized LLM applications and limitations in patient care.
Results
89 studies across 29 medical specialties included; most investigated Generative Pre-trained models
Impact
Maps current LLM applications and limitations in patient care; no single solved outcome demonstrated.
Record
| Venue | Communications Medicine |
|---|---|
| Published | 2025 |
| Work type | review |
| Authors | Felix Busch, Lena Hoffmann, Christopher Rueger, Elon H. C. van Dijk, Rawen Kader, Esteban Ortiz‐Prado, Marcus R. Makowski, Luca Saba et al. |
| Citations | 342 (OpenAlex, at import time) |
| References | 148 |
| Model or method | Generative Pre-trained (GPT) models, per truncated abstract |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1038/s43856-024-00717-2 |
| Open access | gold |
| Keywords | large language models, patient care, systematic review, GPT, clinical applications |
Importance rating
6
significant — thousands to millions affected
LLMs promise personalized patient education and broadened access to medical knowledge; review covers 89 studies across 29 specialties, indicating wide cross-medicine scope.