EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access

Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language Models

Weiwei Liu iD, Shuchang Miao iD, Qun Ma iD, Yuxin Li iD, Yinxiang Deng iD, Xiaoqiu Wang iD, Xinwei Zhang iD, Nuosha Ma iD, Hanchi Miao iD, Yang Si iD, Qingxia Shi iD, Lin Zhu iD und 2 weitere

JMIR Formative Research · 02.03.2026 · 10 · e80167-e80167

DOI: 10.2196/80167 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift JMIR Formative Research, online erschienen am 02.03.2026. Verfasst von Weiwei Liu und 13 weiteren Autor:innen. Beteiligte Einrichtung: Department of Preventive Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China. Hauptthemen laut MEDLINE: Large Language Models, Medicine, Chinese Traditional, Clinical Decision-Making. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsMedicine, Chinese TraditionalClinical Decision-MakingHumansArtificial Intelligence

Stichwörter der Autor:innen

artificial intelligenceclinical decision makingclinical decision supportdigital healthhuman-AI collaborationlarge language modelsmedical informaticstraditional Chinese medicine

Autor:innen und Institutionen

  • Department of Preventive Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.
  • The First School of Clinical Medicine, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.
  • Affiliated Hospital of Nanjing University of Chinese Medicine, No. 155, Hanzhong Road, Qinhuai District, Nanjing, China, 86 13809023858.
  • Department of Rheumatology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.

ORCID-Profile: Weiwei Liu, Shuchang Miao, Qun Ma, Yuxin Li, Yinxiang Deng, Xiaoqiu Wang, Xinwei Zhang, Nuosha Ma, Hanchi Miao, Yang Si, Qingxia Shi, Lin Zhu, Hongtao Shang, Yue Wang

Zitieren

APA

Liu, W., Miao, S., Ma, Q., Li, Y., Deng, Y., Wang, X., Zhang, X., Ma, N., Miao, H., Si, Y., Shi, Q., Zhu, L., Shang, H., & Wang, Y. (2026). Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language Models. JMIR Formative Research, 10, e80167-e80167. https://doi.org/10.2196/80167

Vancouver

Liu W, Miao S, Ma Q, Li Y, Deng Y, Wang X, et al. Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language Models. JMIR Formative Research. 2026;10:e80167-e80167. doi:10.2196/80167

BibTeX
@article{Liu2026,
  author = {Liu, Weiwei and Miao, Shuchang and Ma, Qun and Li, Yuxin and Deng, Yinxiang and Wang, Xiaoqiu and Zhang, Xinwei and Ma, Nuosha and Miao, Hanchi and Si, Yang and Shi, Qingxia and Zhu, Lin and Shang, Hongtao and Wang, Yue},
  title = {Digitally Assisted Clinical Decision-Making in Traditional Chinese Medicine: Comparative Study of 5 Large Language Models},
  journal = {JMIR Formative Research},
  year = {2026},
  volume = {10},
  pages = {e80167--e80167},
  doi = {10.2196/80167}
}
Kostenlos starten →