Exploration and case analysis of the application of large language models in teaching medically unspecified diseases
Hu Mengjie
Ren Wen
Ren Jingjing
Abstract：This article explores the application of large language models(LLMs)in the teaching of medically unspecified diseases(MUD).Due to their atypical symptoms,the diagnosis and treatment of MUD pose significant challenges,and existing teaching methods struggle to effectively enhance the diagnostic and therapeutic capabilities of medical students and general practitioners.By developing a General Practice Standardized Patient System and an Auxiliary Diagnostic Model,LLMs provide new perspectives and tools for MUD teaching through simulated cases,personalized learning pathways and virtual patient interactions.Preliminary research indicates that these applications can significantly improve diagnostic accuracy and learning outcomes of general residents,particularly in the management of complex cases and boosting student confidence.Despite challenges related to data accuracy,ethical considerations and practical implementation,the potential of LLMs in advancing teaching quality and clinical practice cannot be overlooked.Future efforts should be focused on addressing these challenges to promote the progress of MUD education.
Keywords：medically unspecified diseasegeneral practiceartificial intelligenceresidentlarge language models
Publication Date：2025-04-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 277-282 )