Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language Models
Bibliographic record
Abstract
Background: Traditional Chinese medicine (TCM) clinical decision-making involves complex integration of syndrome differentiation, constitutional assessment, and individualized treatment selection, creating challenges for standardization and quality assurance. While large language models (LLMs) demonstrate capabilities in medical knowledge integration and clinical reasoning, their application to TCM remains largely unexplored, particularly regarding syndrome differentiation principles and prescription formulation. Objective: This study evaluated 5 contemporary LLMs in TCM clinical decision-making and assessed human-artificial intelligence (AI) collaboration compared with independent approaches. Specific objectives were to benchmark LLM performance in TCM knowledge assessment, evaluate clinical case analysis capabilities, identify the optimal model, and assess the quality, efficiency, and acceptability of human-AI collaboration. Methods: In total, 5 mainstream LLMs were evaluated-Claude 3.7 Sonnet-Extended (Anthropic), ChatGPT 4.5 (OpenAI), Grok3-DeepSearch (xAI), Gemini 2.0 Flash Thinking Experimental (Google), and DeepSeek-R1 (DeepSeek). The evaluation consisted of four phases, (1) TCM knowledge assessment using 160 standardized questions, (2) clinical case analysis of 30 cases representing different disease systems and complexity levels, (3) optimal model selection using weighted scoring (40% knowledge and 60% clinical analysis), and (4) clinical application assessment involving 10 TCM practitioners and 2 experts comparing physician-only, AI-only, and human-AI collaboration across 5 clinical cases. Statistical analysis included descriptive statistics, reliability analysis, comparative testing, and regression analysis. Results: DeepSeek-R1 demonstrated superior performance across both evaluation domains, achieving 96.7% accuracy in knowledge assessment and 17.31/20 (SD 2.65) in clinical case analysis, significantly outperforming other models (P<.001). Human-AI collaboration achieved significant improvements compared with physician-only decision-making, with 16.1% quality enhancement (33.62 vs 28.97; P<.001) and 66.1% time reduction (162.6 s vs 479.2 s; P<.001). System usability was rated favorably (System Usability Scale score=76.8; P=.002), with high acceptance rates (74.25% adoption, 24% modification, and 1.75% rejection). AI assistance provided the greatest benefits in prescription formulation and medication selection (P<.001). Conclusions: LLMs, particularly DeepSeek-R1, demonstrate substantial capabilities in TCM knowledge assessment and clinical case analysis. Human-AI collaboration significantly enhanced clinical decision-making quality and efficiency while maintaining high physician acceptance. These findings provide compelling evidence for the clinical value of AI-assisted decision-making in TCM, suggesting potential solutions to current challenges in knowledge standardization, clinical training, and health care delivery efficiency. Strategic implementation of AI assistance could significantly enhance the quality, efficiency, and accessibility of TCM care while preserving fundamental principles of individualized treatment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.014 | 0.049 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".