EUVIMEDObjevte EUVIMED
Open access

Large Language Model Evaluation in Traditional Chinese Medicine for Stroke: Quantitative Benchmarking Study

Hulin Long iD, Yang Deng iD, Yaoguang Guo iD, Zifan Shen iD, Yuzhu Zhang iD, Ji Bao iD, Yang He iD

JMIR Formative Research · 2025-12-11 · 9 · e81545

DOI: 10.2196/81545 ↗

At a glance

Journal article in JMIR Formative Research, published online on 2025-12-11. Written by Hulin Long and 6 co-authors. Institution: Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, Sichuan Province, China. Major MEDLINE topics: Medicine, Chinese Traditional, Stroke, Benchmarking, Language. Cited 6 times so far (Crossref); 17 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

The application of large language models (LLMs) in medicine is rapidly advancing. However, evaluating LLM capabilities in specialized domains such as traditional Chinese medicine (TCM), which possesses a unique theoretical system and cognitive framework, remains a sizable challenge.

Objective

This study aimed to provide an empirical evaluation of different LLM types in the specialized domain of TCM stroke.

Methods

The Traditional Chinese Medicine-Stroke Evaluation Dataset (TCM-SED), a 203-question benchmark, was systematically constructed. The dataset includes 3 paradigms (short-answer questions, multiple-choice questions, and essay questions) and covers multiple knowledge dimensions, including diagnosis, pattern differentiation and treatment, herbal formulas, acupuncture, interpretation of classical texts, and patient communication. Gold standard answers were established through a multiexpert cross-validation and consensus process. The TCM-SED was subsequently used to comprehensively test 2 representative LLM models: GPT-4o (a leading international general-purpose model) and DeepSeek-R1 (a large model primarily trained on Chinese corpora).

Results

The test results revealed a differentiation in model capabilities across cognitive levels. In objective sections emphasizing precise knowledge recall, DeepSeek-R1 comprehensively outperformed GPT-4o, achieving an accuracy lead of more than 17% in the multiple-choice section (96/137, 70.1% vs 72/137, 52.6%, respectively). Conversely, in the essay section, which tested knowledge integration and complex reasoning, GPT-4o’s performance notably surpassed that of DeepSeek-R1. For instance, in the interpretation of classical texts category, GPT-4o achieved a scoring rate of 90.5% (181/200), far exceeding DeepSeek-R1 (147/200, 73.5%).

Conclusions

This empirical study demonstrates that Chinese-centric models have a substantial advantage in static knowledge tasks within the TCM domain, whereas leading general-purpose models exhibit stronger dynamic reasoning and content generation capabilities. The TCM-SED, developed as the benchmark for this study, serves as an effective quantitative tool for evaluating and selecting appropriate LLMs for TCM scenarios. It also offers a valuable data foundation and a new research direction for future model optimization and alignment.

Subjects

MeSH terms (MEDLINE)

Medicine, Chinese TraditionalStrokeBenchmarkingLanguageHumansLarge Language Models

Author keywords

artificial intelligenceevaluation datasetlarge language modelsmodel evaluationstroketraditional Chinese medicine

Authors and institutions

  • Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, Sichuan Province, China.
  • Institute of Clinical Pathology, West China Hospital of Sichuan University, Chengdu, China.
  • Physical Education Institute, Southwest Medical University, Luzhou, China.
  • Chengdu University of Traditional Chinese Medicine, Chengdu, China.

ORCID profiles: Hulin Long, Yang Deng, Yaoguang Guo, Zifan Shen, Yuzhu Zhang, Ji Bao, Yang He

Cite

APA

Long, H., Deng, Y., Guo, Y., Shen, Z., Zhang, Y., Bao, J., & He, Y. (2025). Large Language Model Evaluation in Traditional Chinese Medicine for Stroke: Quantitative Benchmarking Study. JMIR Formative Research, 9, e81545. https://doi.org/10.2196/81545

Vancouver

Long H, Deng Y, Guo Y, Shen Z, Zhang Y, Bao J, et al. Large Language Model Evaluation in Traditional Chinese Medicine for Stroke: Quantitative Benchmarking Study. JMIR Formative Research. 2025;9:e81545. doi:10.2196/81545

BibTeX
@article{Long2025,
  author = {Long, Hulin and Deng, Yang and Guo, Yaoguang and Shen, Zifan and Zhang, Yuzhu and Bao, Ji and He, Yang},
  title = {Large Language Model Evaluation in Traditional Chinese Medicine for Stroke: Quantitative Benchmarking Study},
  journal = {JMIR Formative Research},
  year = {2025},
  volume = {9},
  pages = {e81545},
  doi = {10.2196/81545}
}
Start for free →