A Weighted Voting Approach for Traditional Chinese Medicine Formula Classification Using Large Language Models: Algorithm Development and Validation Study
JMIR Medical Informatics · 2025
DOI: 10.2196/69286 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Zhe Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences; School of Basic Medicine, Peking Union Medical College, Beijing, China. Hauptthemen laut MEDLINE: Medicine, Chinese Traditional, Algorithms, Language, Drugs, Chinese Herbal. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Several clinical cases and experiments have demonstrated the effectiveness of traditional Chinese medicine (TCM) formulas in treating and preventing diseases. These formulas contain critical information about their ingredients, efficacy, and indications. Classifying TCM formulas based on this information can effectively standardize TCM formulas management, support clinical and research applications, and promote the modernization and scientific use of TCM. To further advance this task, TCM formulas can be classified using various approaches, including manual classification, machine learning, and deep learning. Additionally, large language models (LLMs) are gaining prominence in the biomedical field. Integrating LLMs into TCM research could significantly enhance and accelerate the discovery of TCM knowledge by leveraging their advanced linguistic understanding and contextual reasoning capabilities.
Objective
The objective of this study is to evaluate the performance of different LLMs in the TCM formula classification task. Additionally, by employing ensemble learning with multiple fine-tuned LLMs, this study aims to enhance classification accuracy.
Methods
The data for the TCM formula were manually refined and cleaned. We selected 10 LLMs that support Chinese for fine-tuning. We then employed an ensemble learning approach that combined the predictions of multiple models using both hard and weighted voting, with weights determined by the average accuracy of each model. Finally, we selected the top 5 most effective models from each series of LLMs for weighted voting (top 5) and the top 3 most accurate models of 10 for weighted voting (top 3).
Results
A total of 2441 TCM formulas were curated manually from multiple sources, including the Coding Rules for Chinese Medicinal Formulas and Their Codes, the Chinese National Medical Insurance Catalog for proprietary Chinese medicines, textbooks of TCM formulas, and TCM literature. The dataset was divided into a training set of 1999 TCM formulas and test set of 442 TCM formulas. The testing results showed that Qwen-14B achieved the highest accuracy of 75.32% among the single models. The accuracy rates for hard voting, weighted voting, weighted voting (top 5), and weighted voting (top 3) were 75.79%, 76.47%, 75.57%, and 77.15%, respectively.
Conclusions
This study aims to explore the effectiveness of LLMs in the TCM formula classification task. To this end, we propose an ensemble learning method that integrates multiple fine-tuned LLMs through a voting mechanism. This method not only improves classification accuracy but also enhances the existing classification system for classifying the efficacy of TCM formula.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences; School of Basic Medicine, Peking Union Medical College, Beijing, China.
- Institute for Medical Informatics, Statistics and Epidemiology, University of Leipzig, Leipzig, Germany.
- School of Medical Information, Changchun University of Chinese Medicine, Changchun, China.
- Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, No 16, Nanxiao Street, Dongzhimen, Beijing, 100010, China, 86 010 64089639.
- Institute for Computer Science, University of Leipzig, Leipzig, Germany.
ORCID-Profile: Zhe Wang, Keqian Li, Suyuan Peng, Lihong Liu, Xiaolin Yang, Keyu Yao, Heinrich Herre, Yan Zhu
Zitieren
APA
Wang, Z., Li, K., Peng, S., Liu, L., Yang, X., Yao, K., Herre, H., & Zhu, Y. (2025). A Weighted Voting Approach for Traditional Chinese Medicine Formula Classification Using Large Language Models: Algorithm Development and Validation Study. JMIR Medical Informatics. https://doi.org/10.2196/69286
Vancouver
Wang Z, Li K, Peng S, Liu L, Yang X, Yao K, et al. A Weighted Voting Approach for Traditional Chinese Medicine Formula Classification Using Large Language Models: Algorithm Development and Validation Study. JMIR Medical Informatics. 2025. doi:10.2196/69286
BibTeX
@article{Wang2025,
author = {Wang, Zhe and Li, Keqian and Peng, Suyuan and Liu, Lihong and Yang, Xiaolin and Yao, Keyu and Herre, Heinrich and Zhu, Yan},
title = {A Weighted Voting Approach for Traditional Chinese Medicine Formula Classification Using Large Language Models: Algorithm Development and Validation Study},
journal = {JMIR Medical Informatics},
year = {2025},
doi = {10.2196/69286}
}
EUVIMED