EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intelligent Chinese patent medicine (CPM) recommendation framework: Integrating large language models, retrieval-augmented generation, and the largest CPM dataset

Suyang Qin, Yifan Wang, Tangming Cui, Jinge Ma, Xin Zhou, Xinglin Guo, Chuchu Zhang, Chongyun Zhou, Rongjuan Guo, Haiyan Li

Pharmacological Research · 2025-09 · 219 · 107883

DOI: 10.1016/j.phrs.2025.107883 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacological Research, 2025-09. Verfasst von Suyang Qin und 9 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China. Hauptthemen laut MEDLINE: Medicine, Chinese Traditional, Nonprescription Drugs, Drugs, Chinese Herbal. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology of the People's Republic of China, National Key Research and Development Program of China, China Academy of Chinese Medical Sciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Chinese patent medicines (CPMs), a vital component of healthcare systems in China and worldwide, has been increasingly utilized in clinical practice. However, approximately 70 % of CPMs are prescribed by Western medicine physicians who lack expertise in traditional Chinese medicine syndrome differentiation and treatment. Here, in this study, we constructed RAG-CPMF, an intelligent CPM recommendation framework integrating large language models (LLMs), retrieval-augmented generation (RAG), and the largest CPM dataset. Specifically, we first applied the Multi-LLMs Validation method, significantly reducing the manual proofreading workload involved in structured data extraction. Furthermore, based on this approach, we successfully established the largest CPM dataset (https://gitee.com/tcmdoc/cpm) with continuous on-line updates. Afterwards, we combined the CPM dataset and the RAG architecture, along with effective integration of generative capacity from LLMs and external data retrieval; all of which contributed to the RAG-CPMF. Finally, the accuracy of RAG-CPMF was evaluated against clinical guidelines, demonstrating that this framework significantly improved CPM recommendation accuracy compared with general-purpose LLMs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Medicine, Chinese TraditionalNonprescription DrugsDrugs, Chinese HerbalHumansDatabases, FactualLanguageLarge Language Models

Stichwörter der Autor:innen

Chinese patent medicine (CPM) datasetLarge language models (LLMs)Multi-LLMs Validationguidelines evaluationintelligent CPM recommendation frameworkretrieval-augmented generation

Substanzen

Nonprescription DrugsDrugs, Chinese Herbal

Autor:innen und Institutionen

  • Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China.
  • School of Basic Medical Sciences Peking University, Beijing 100191, China.
  • Huzhou Traditional Chinese Medicine Hospital Affiliated to Zhejiang Chinese Medical University, Huzhou, Zhejiang 313000, China.
  • First Teaching Hospital of Tianjin University of Traditional Chinese Medicine, National Clinical Research Center for Chinese Medicine Acupuncture and Moxibustion, Tianjin 300381, China.
  • Psychosomatic Department, Dongfang Hospital, Beijing University of Chinese Medicine, Beijing 100078, China. Electronic address: dfguorongjuan@163.com.
  • Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China. Electronic address: li_haiyan01@126.com.

Förderung

  • Ministry of Science and Technology of the People's Republic of China
  • National Key Research and Development Program of China
  • China Academy of Chinese Medical Sciences

Zitieren

APA

Qin, S., Wang, Y., Cui, T., Ma, J., Zhou, X., Guo, X., Zhang, C., Zhou, C., Guo, R., & Li, H. (2025). Intelligent Chinese patent medicine (CPM) recommendation framework: Integrating large language models, retrieval-augmented generation, and the largest CPM dataset. Pharmacological Research, 219, 107883. https://doi.org/10.1016/j.phrs.2025.107883

Vancouver

Qin S, Wang Y, Cui T, Ma J, Zhou X, Guo X, et al. Intelligent Chinese patent medicine (CPM) recommendation framework: Integrating large language models, retrieval-augmented generation, and the largest CPM dataset. Pharmacological Research. 2025;219:107883. doi:10.1016/j.phrs.2025.107883

BibTeX
@article{Qin2025,
  author = {Qin, Suyang and Wang, Yifan and Cui, Tangming and Ma, Jinge and Zhou, Xin and Guo, Xinglin and Zhang, Chuchu and Zhou, Chongyun and Guo, Rongjuan and Li, Haiyan},
  title = {Intelligent Chinese patent medicine (CPM) recommendation framework: Integrating large language models, retrieval-augmented generation, and the largest CPM dataset},
  journal = {Pharmacological Research},
  year = {2025},
  volume = {219},
  pages = {107883},
  doi = {10.1016/j.phrs.2025.107883}
}
Kostenlos starten →