Large language models in traditional Chinese medicine: a systematic review

Abstract

Objective: Generative artificial intelligence (AI) technology, represented by large language models (LLMs), has gradually been developed for traditional Chinese medicine (TCM); however, challenges remain in effectively enhancing AI applications for TCM. Therefore, this study is the first systematic review to analyze LLMs in TCM retrospectively, focusing on and summarizing the evidence of their performance in generative tasks.
Methods: We extensively searched electronic databases for articles published until June 2024 to identify publicly available studies on LLMs in TCM. Two investigators independently selected and extracted the related information and evaluation metrics. Based on the available data, this study used descriptive analysis for a comprehensive systematic review of LLM technology related to TCM.
Results: Ten studies published between 2023 and 2024 met our eligibility criteria and were included in this review, including 40% LLMs in the TCM vertical domain, 40% containing TCM data, and 20% honoring the TCM contribution, with a foundational model parameter range from 1.8 to 33 billion. All included studies used manual or automatic evaluation metrics to evaluate model performance and fully discussed the challenges and contributions through an overview of LLMs in TCM.
Conclusions: LLMs have achieved significant advantages in TCM applications and can effectively address intelligent TCM tasks. Further in-depth development of LLMs is needed in various vertical TCM fields, including clinical and fundamental research. Focusing on the functional segmentation development direction of generative AI technologies in TCM application scenarios to meet the practical needs-oriented demands of TCM digitalization is essential.

Keywords

Generative artificial intelligence / Intelligence clinical applications / Large language model / Systematic review / Traditional Chinese medicine

Conflict of interest statement

The authors declare no conflict of interest.

Funding

This work was supported by the National Multidisciplinary Innovation Team of Traditional Chinese Medicine (ZYYCXTD-D-202204), China Postdoctoral Science Foundation (2023M742627), Postdoctoral Fellowship Program of CPSF (GZC20231928), Foundation of State Key Laboratory of Component-based Chinese Medicine (CBCM2023201).

Author contributions

Zhe Chen and Junhua Zhang conceived the manuscript. Zhe Chen drafted the manuscript, analyzed the data, and interpreted the review. Zhe Chen and Hui Wang filtered the articles and performed data extraction. Chunxiang Liu and Chengxian Li summarized the models and performed the assessment. Fengwen Yang, Dong Zhang, Alice Josephine Fauci, and Junhua Zhang provided critical version of the manuscript. All authors contributed to the revision of the manuscript and approved the final manuscript.

Ethical approval of studies and informed consent

Not applicable.

Acknowledgments

None.

Data availability

All data can be available from the corresponding author with a reasonable request.

References

[1] Thirunavukarasu AJ, Ting DSJ, Elangovan K, et al. Large language models in medicine. Nat Med 2023; 29(8):1930-1940.

[2] Zhu L, Mou W, Lai Y, et al. Language and cultural bias in AI: comparing the performance of large language models developed in different countries on traditional Chinese medicine highlights the need for localized models. J Transl Med 2024; 22(1):319.

[3] Wang Z, Li K, Ren Q, Yao K, Zhu Y. Traditional Chinese medicine formula classification using large language models. Paper presented at: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 5-8 Dec. 2023. 4647-4654.

[4] Singhal K, Azizi S, Tu T, et al. Large language models encode clinical knowledge. Nature 2023; 620(7972):172-180.

[5] Moor M, Banerjee O, Abad ZSH, et al. Foundation models for generalist medical artificial intelligence. Nature 2023; 616(7956):259-265.

[6] Tan Y, Zhang Z, Li M, et al. MedChatZH: a tuning LLM for traditional Chinese medicine consultations. Comput Biol Med 2024; 172:108290.

[7] Cyranoski D. Why Chinese medicine is heading for clinics around the world. Nature 2018; 561(7724):448-450.

[8] Zhang HY, Wang X, Meng ZP, et al. Qibo: a large language model for traditional Chinese medicine. arXiv preprint arXiv:240316056 2024.

[9] Liu C, Sun K, Zhou Q, et al. CPMI-ChatGLM: parameter-efficient fine-tuning ChatGLM with Chinese patent medicine instructions. Sci Rep 2024; 14(1):6403.

[10] Mondal H, Komarraju S, Sathyanath D, et al. Assessing the capability of large language models in naturopathy consultation. Cureus 2024; 16(5):e59457.

[11] Li YZ, Huang SH, Qi JX, et al. Exploring the comprehension of ChatGPT in traditional Chinese medicine knowledge. arXiv preprint arXiv:240309164 2024.

[12] Zhang Y, Hao Y. Traditional Chinese medicine knowledge graph construction based on large language models. Periodical 2024; 13(7):1395.

[13] Yu P, Song K, He F, et al. TCMD: a traditional Chinese medicine QA dataset for evaluating large language models. arXiv preprint arXiv:240604941 2024.

[14] Chen Z, Zhang D, Liu C, et al. Traditional Chinese medicine diagnostic prediction model for holistic syndrome differentiation based on deep learning. Integr Med Res 2024; 13(1):101019.

[15] Yue W, Wang X, Zhu W, et al. TCMBench: a comprehensive benchmark for evaluating large language models in traditional Chinese medicine. arXiv preprint arXiv:240601126 2024.

[16] Page MJ, McKenzie JE, Bossuyt PM, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021; 372:n71.

[17] Yang G, Liu X, Shi J, et al. TCM-GPT: efficient pre-training of large language models for domain adaptation in traditional Chinese medicine. Comput Methods Programs Biomed 2024; 6:100158.

[18] Liao Y, Jiang S, Wang Y, et al. MING-MOE: enhancing medical multi-task learning in large language models with sparse mixture of low-rank adapter experts. arXiv preprint arXiv:240409027 2024.

[19] Zhang H, Chen J, Jiang F, et al. Huatuogpt, towards taming language model to be a doctor. arXiv preprint arXiv:230515075 2023.

[20] Wang R, Duan Y, Lam C, et al. Ivygpt: interactive Chinese pathway language model in medical domain. arXiv preprint arXiv:2307.10512 2023.

[21] Yang S, Zhao H, Zhu S, et al. Zhongjing: enhancing the Chinese medical capabilities of large language model through expert feedback and real-world multi-turn dialogue. arXiv preprint2023:arXiv:2308.03549 2023.

[22] Wang H, Liu C, Xi N, et al. Tuning llama model with Chinese medical knowledge. arXiv preprint 2023;arXiv:230406975.

[23] Chen Y, Wang Z, Xing X, et al. Bianque: balancing the questioning and suggestion ability of health llms with multi-turn health conversations polished by chatgpt. arXiv preprint 2023;arXiv:231015896.

[24] Aydin Temel F, Cagcag Yolcu O, Turan NG. Artificial intelligence and machine learning approaches in composting process: a review. Bioresour Technol 2023; 370:128539.

[25] Lu MY, Chen B, Williamson DFK, et al. A multimodal generative AI copilot for human pathology. Nature 2024; 634(8033):466-473.

[26] Zaretsky J, Kim JM, Baskharoun S, et al. Generative artificial intelligence to transform inpatient discharge summaries to patient-friendly language and format. JAMA Netw Open 2024; 7(3):e240357.

[27] Tan S, Xin X, Wu D. ChatGPT in medicine: prospects and challenges: a review article. Int J Surg 2024; 110(6):3701-3706.

[28] Martin KD, Zimmermann J. Artificial intelligence and its implications for data privacy. Curr Opin Psychol 2024; 58:101829.

[29] Price WN 2nd, Cohen IG. Privacy in the age of medical big data. Nat Med 2019; 25(1):37-43.

[30] Wang Y, Shi X, Li L, et al. The impact of artificial intelligence on traditional Chinese medicine. Am J Chin Med 2021; 49(6):1297-1314.

[31] Sauerbrei A, Kerasidou A, Lucivero F, et al. The impact of artificial intelligence on the person-centred, doctor-patient relationship: some problems and solutions. BMC Med Inform Decis Mak 2023; 23(1):73.

[32] Garrett BL, Rudin C. Interpretable algorithmic forensics. Proc Natl Acad Sci USA 2023; 120(41):e2301842120.

[33] Chakraborty C, Bhattacharya M, Islam MA, et al. ChatGPT indicates the path and initiates the research to open up the black box of artificial intelligence. Int J Surg 2023; 109(12):4367-4368.

[34] Liu X, Gong T. Artificial intelligence and evidence-based research will promote the development of traditional medicine. Acupunct Herb Med 2024; 4(1):134-135.

[35] Peng C, Yang X, Chen A, et al. A study of generative large language model for medical research and healthcare. NPJ Digital Med 2023; 6(1):210.

[36] Bao YF, Ding HK, Zhang ZH, et al. Intelligent acupuncture: data-driven revolution of traditional Chinese medicine. Acupunct Herb Med 2023; 3(4):271-284.