ZHAO Tao,WEI Changfa,LIU Huina,et al.Exploration on application of ChatGPT in scientific research work of traditional Chinese medicine[J].Shanghai Journal of Traditional Chinese Medicine,2025,59(11):1-8.
ZHAO Tao,WEI Changfa,LIU Huina,et al.Exploration on application of ChatGPT in scientific research work of traditional Chinese medicine[J].Shanghai Journal of Traditional Chinese Medicine,2025,59(11):1-8. DOI: 10.16305/j.1007-1334.2025.z20241006001.
Exploration on application of ChatGPT in scientific research work of traditional Chinese medicine
To explore the application value and models of ChatGPT in scientific research of traditional Chinese medicine (TCM), and to demonstrate its practical applications.
Methods
2
This paper outlines the development trends of ChatGPT and related models, analyzing its application in TCM scientific research through four modes: general tool usage, interactive dialogue, API integration, and code generation. Based on these modes, practical applications of ChatGPT in TCM research were implemented in areas such as medical case structuring, named entity recognition, scientific data acquisition and analysis, and the assessment of TCM postgraduate exam questions.
Results
2
ChatGPT has shown significant effects in TCM research, excelling in tasks such as medical case structuring, named entity recognition, and scientific data acquisition and analysis. However, its ability to answer professional TCM questions, such as those in the past papers of the National Graduate Entrance Exam for
Comprehensive Traditional Chinese Medicine
, requires further improvement.
Conclusions
2
ChatGPT demonstrates enormous potential in the field of TCM, offering efficient and convenient solutions for researchers. With continuous advancements in technology, large language models like ChatGPT are expected to play an increasingly important role in TCM scientific research in the future.
LI Y X , LI Z H , ZHANG K , et al . ChatDoctor: a medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge [J]. Cureus , 2023 , 15 ( 6 ): e40895 .
ZHANG H B , CHEN J Y , JIANG F , et al . HuatuoGPT, towards taming language model to be a doctor [J/OL]. arXiv , 2023 [ 2024-09-01 ]. https://arxiv.org/pdf/2305.15075 https://arxiv.org/pdf/2305.15075 .
XIONG H L , WANG S , ZHUY T , et al . DoctorGLM: fine-tuning your Chinese doctor is not a herculean task [J/OL]. arXiv , 2023 [ 2024-09-01 ]. https://arxiv.org/abs/2304.01097 https://arxiv.org/abs/2304.01097 .
WANG H C , LIU C , XI N W , et al . HuaTuo: tuning LLaMA model with Chinese medical knowledge [J/OL]. arXiv , 2023 [ 2024-09-01 ]. https://arxiv.org/abs/2304.06975 https://arxiv.org/abs/2304.06975 .
CHEN Y R , WANG Z Y , XING X F , et al . BianQue: balancing the questioning and suggestion ability of health LLMs with multi-turn health conversations polished by ChatGPT [J/OL]. arXiv , 2023 [ 2024-09-01 ]. https://arxiv.org/abs/2310.15896 https://arxiv.org/abs/2310.15896 .
LIAO Y S , JIANG S Y , WANG Y , et al . MING-MOE: enhancing medical multi-task learning in large language models with sparse mixture of low-rank adapter experts [J/OL]. arXiv , 2024 [ 2024-09-01 ]. https://arxiv.org/abs/2404.09027 https://arxiv.org/abs/2404.09027 .
LIU Y , LE-CONG T , WIDYASARI R , et al . Refining ChatGPT-generated code: characterizing and mitigating code quality issues [J/OL]. arXiv , 2023 [ 2024-09-01 ]. https://arxiv.org/abs/2307.12596 https://arxiv.org/abs/2307.12596 .
LEE P Y , SALIM H , ABDULLAH A , et al . Use of ChatGPT in medical research and scientific writing [J]. Malays Fam Physician , 2023 , 18 : 58 .
MA Y K , LIU Y , ZHANG D Z , et al . A multigranularity text driven named entity recognition CGAN model for traditional Chinese medicine literatures [J]. Comput Intell Neurosci , 2022 , 2022 : 1495841 .
WENG H , CHEN J L , OU A H , et al . Leveraging representation learning for the construction and application of a knowledge graph for traditional Chinese medicine: framework development study [J]. JMIR Med Inform , 2022 , 10 ( 9 ): e38414 .
ZOU S L , LIU Z Y , WANG K Q , et al . A study on pharmaceutical text relationship extraction based on heterogeneous graph neural networks [J]. Math Biosci Eng , 2023 , 21 ( 1 ): 1489 - 1507 .
BRANUM C , SCHIAVENATO M . Can ChatGPT accurately answer a PICOT question? Assessing AI response to a clinical question [J]. Nurse Educ , 2023 , 48 ( 5 ): 231 - 233 .
XU W X , WANG L , ZHANG M C , et al . A joint entity relation extraction method for document level traditional Chinese medicine texts [J]. Artif Intell Med , 2024 , 154 : 102915 .
LI K C , BU Z J , SHAHJALAL M , et al . Performance of ChatGPT on Chinese master's degree entrance examination in clinical medicine [J]. PLoS One , 2024 , 19 : e0301702 .
TSENG L W , LU Y C , TSENG L C , et al . Performance of ChatGPT-4 on Taiwanese traditional Chinese medicine licensing examinations: cross-sectional study [J]. JMIR Med Educ , 2025 , 11 : e58897 .
ABDULLAH H M A , NAEEM N K , MALKANA G A , et al . Exploring the ethical implications of ChatGPT in medical education: privacy, accuracy, and professional integrity in a cross-sectional survey [J]. Cureus , 2024 , 16 ( 12 ): e75895 .
OZKAN E , TEKIN A , OZKAN M C , et al . Global health care professionals’ perceptions of large language model use in practice: cross-sectional survey study [J]. JMIR Med Educ , 2025 , 11 : e58801 .
SANDMANN S , HEGSELMANN S , FUJARSKI M , et al . Benchmark evaluation of DeepSeek large language models in clinical decision-making [J]. Nat Med , 2025 , 31 ( 8 ): 2546 - 2549 .
TORDJMAN M , LIU Z , YUCE M , et al . Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning [J]. Nat Med , 2025 , 31 ( 8 ): 2550 - 2555 .
A method for generating dietary recommendations following "food and medicine homology" principle of traditional Chinese medicine using retrieval‑augmented large language models
Constructing an artificial intelligence technology system for real⁃world traditional Chinese medicine clinical study: key values, research issues, and development directions
Research progress on acupuncture clinical diagnosis and treatment technologies based on artificial intelligence
Application prospects and challenges of generative artificial intelligence in standardization of traditional Chinese medicine
Research on entity and relation extraction from traditional Chinese medicine knowledge graphs based on GPTs
Related Author
GONG Fan
LIU Bo
SHA Hangyu
HUANG Hui
LIU Runfeng
LIU Xuan
JING Shenqi
WU Tianxing
Related Institution
Information Department, Jiangsu Province Hospital (First Affiliated Hospital with Nanjing Medical University)
MOE Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University
Department of Endocrinology, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine
Informatization Office, Shanghai University of Traditional Chinese Medicine
School of Computer Science and Engineering, Southeast University