Related Experiment Video
Updated: Jul 13, 2026
05:56
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
3.3K
Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language
Weiwei Liu1, Shuchang Miao2, Qun Ma1
1Department of Preventive Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.
JMIR Formative Research
|March 12, 2026
Summary
Large language models (LLMs) show promise in Traditional Chinese Medicine (TCM) clinical decision-making, with DeepSeek-R1 excelling in knowledge and case analysis. Human-AI collaboration significantly improves TCM care quality and efficiency.
Area of Science:
- Integrative Medicine
- Artificial Intelligence in Healthcare
- Traditional Chinese Medicine (TCM)
Background:
- Traditional Chinese Medicine (TCM) clinical decision-making faces challenges in standardization and quality assurance due to its complex nature.
- Large language models (LLMs) offer potential for integrating medical knowledge and clinical reasoning, but their application in TCM is underexplored.
Purpose of the Study:
- To evaluate the performance of five contemporary LLMs in TCM clinical decision-making.
- To assess the benefits of human-artificial intelligence (AI) collaboration compared to independent approaches in TCM.
- To identify the optimal LLM and evaluate the quality, efficiency, and acceptability of human-AI collaboration.
Main Methods:
- Five mainstream LLMs were evaluated on TCM knowledge using 160 standardized questions and clinical case analysis of 30 cases.
- Optimal model selection was based on weighted scoring (40% knowledge, 60% clinical analysis).
- Human-AI collaboration was assessed by 10 TCM practitioners and 2 experts across 5 clinical cases, comparing physician-only, AI-only, and collaborative approaches.
Main Results:
- DeepSeek-R1 demonstrated superior performance with 96.7% accuracy in knowledge assessment and high scores in clinical case analysis (P<.001).
- Human-AI collaboration significantly enhanced decision-making quality by 16.1% and reduced time by 66.1% (P<.001).
- AI assistance showed greatest benefits in prescription formulation and medication selection, with high user acceptance (76.8 System Usability Scale score).
Conclusions:
- LLMs, particularly DeepSeek-R1, possess significant capabilities for TCM knowledge assessment and clinical case analysis.
- Human-AI collaboration substantially improves TCM clinical decision-making quality and efficiency, with high physician acceptance.
- AI-assisted decision-making offers a promising solution to enhance TCM standardization, training, and healthcare delivery efficiency.
Related Concept Videos
01:26Pharmacokinetic Models: Comparison and Selection Criterion
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
01:27Language and Cognition
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.