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

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

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 differen...

Full description

Saved in:
Bibliographic Details
Main Authors: Suyang Qin, Yifan Wang, Tangming Cui, Jinge Ma, Xin Zhou, Xinglin Guo, Chuchu Zhang, Chongyun Zhou, Rongjuan Guo, Haiyan Li
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Pharmacological Research
Subjects:
Large language models (LLMs)
Multi-LLMs Validation
Chinese patent medicine (CPM) dataset
retrieval-augmented generation
intelligent CPM recommendation framework
guidelines evaluation
Online Access:http://www.sciencedirect.com/science/article/pii/S1043661825003081
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1096-1186

Similar Items