Virtual case reasoning and AI-assisted diagnostic instruction: an empirical study based on body interact and large language models

Збережено в:

Бібліографічні деталі
Опубліковано в::	BMC Medical Education vol. 25 (2025), p. 1-17
Автор:	Chen, Guihua
Інші автори:	Lin, Chuan, Zhang, Lijie, Luo, Zhao, Shin, Yu Seob, Li, Xianxin
Опубліковано:	Springer Nature B.V.
Предмети:	Hangzhou DeepSeek Artificial Intelligence Co Ltd OpenAI Language Emergency medical care Accuracy Medical education Interdisciplinary aspects Metabolism Chatbots Stroke Reflective teaching Coma Artificial intelligence Trauma Clinical decision making Illnesses Consciousness Bilingualism Large language models Fainting Computer Simulation Educational Quality Physicians Patients Neurology Relevance (Education) Educational Research Diagnostic Tests Measurement Techniques Individualized Instruction Program Evaluation Decision Making Medical Evaluation Diagnostic Teaching Evaluative Thinking Educational Assessment Comparative Education Comparative Analysis Physical Examinations Interdisciplinary Approach Learner Engagement
Онлайн доступ:	Citation/Abstract Full Text Full Text - PDF
Теги:	Додати тег Немає тегів, Будьте першим, хто поставить тег для цього запису!

Опис
Короткий огляд:	BackgroundIntegrating large language models (LLMs) with virtual patient platforms offers a novel approach to teaching clinical reasoning. This study evaluated the performance and educational value of combining Body Interact with two AI models, ChatGPT-4 and DeepSeek-R1, across acute care scenarios.MethodsThree standardized cases (coma, stroke, trauma) were simulated by two medical researchers. Structured case summaries were input into both models using identical prompts. Outputs were assessed for diagnostic and treatment consistency, alignment with clinical reasoning stages, and educational quality using expert scoring, AI self-assessment, text readability indices, and Grammarly analysis.ResultsChatGPT-4 performed best in stroke scenarios but was less consistent in coma and trauma cases. DeepSeek-R1 showed more stable diagnostic and therapeutic output across all cases. While both models received high expert and self-assessment scores, ChatGPT-4 produced more readable outputs, and DeepSeek-R1 demonstrated greater grammatical precision.ConclusionsOur findings suggest that ChatGPT-4 and DeepSeek-R1 each offer unique strengths for AI-assisted instruction. ChatGPT-4’s accessible language may better support early learners, whereas DeepSeek-R1 may be more aligned with formal clinical reasoning. Selecting models based on specific teaching goals can enhance the effectiveness of AI-driven medical education.
ISSN:	1472-6920
DOI:	10.1186/s12909-025-07872-7
Джерело:	Healthcare Administration Database