EUVIMEDEUVIMED entdecken
Open Access

Construction and application of a traditional Chinese medicine syndrome differentiation and treatment model grounded in knowledge distillation and reinforcement learning

Xinyu Wang, Xiaohe Sun, Jilong Shen, Jiadong Xie, Yichu Xu, Tao Yang, Haibo Cheng, Kongfa Hu

Health Information Science and Systems · 13.05.2026 · 14 (1)

DOI: 10.1007/s13755-026-00451-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Health Information Science and Systems, online erschienen am 13.05.2026. Verfasst von Xinyu Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, 210023 China. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Innovative Research Group Project of the National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study endeavors to develop an intelligent diagnosis and treatment model for Traditional Chinese Medicine (TCM) syndrome differentiation and treatment, characterized by robust reasoning capabilities and exceptional reliability. This is achieved by harnessing clinical case data, employing knowledge distillation methodologies, and integrating Direct Policy Optimization (DPO) reinforcement learning techniques.

Methods

GPT-4o was employed as the teacher model to perform knowledge distillation on TCM clinical case data, thereby generating a high-quality instruction dataset for syndrome differentiation and treatment. The distilled data was subsequently fine-tuned by Low-Rank Adaptation (LoRA) method grounded in the Qwen2.5-7B model to improve its abilities of diagnosis and treatment, together with competencies of personalized syndrome differentiation and treatment. Furthermore, an additional dataset of clinical cases was leveraged to emulate the diagnosis and treatment preferences of TCM experts, with the DPO reinforcement learning technique being applied for ongoing refinement and enhancement.

Results

The recommended knowledge distillation approach maintained prescription recommendation performance comparable to direct training upon the reinforcement of the model's interpretability and generalization on external data. Aside from that, the DPO method ameliorated the stability of prediction results on the external dataset.

Conclusion

The TCM Large Language Model constructed with knowledge distillation and reinforcement learning strategies effectively enhances diagnosis and treatment reasoning and personalized syndrome differentiation and treatment competencies. This approach provides new research directions and technical support for intelligent TCM clinical decision-making.

Schlagwörter

Stichwörter der Autor:innen

Knowledge distillationLarge language model (LLM)Reinforcement learningTraditional Chinese medicine (TCM)syndrome differentiation and treatment

Autor:innen und Institutionen

  • School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, 210023 China.
  • Jiangsu Engineering Research Center for Smart Traditional, Chinese Medicine Health Services, Nanjing, 210023 China.
  • Tang Zhongying Research Center for Traditional Chinese Medicine Epidemic Diseases, Nanjing University of Chinese Medicine, Nanjing, 210023 China.
  • The First Clinical Medical College, Nanjing University of Chinese Medicine, Nanjing, 210023 China.
  • Jiangsu Provincial Research Institute of Chinese Medicine Schools, Nanjing, 210023 China.

Förderung

  • Innovative Research Group Project of the National Natural Science Foundation of China

Zitieren

APA

Wang, X., Sun, X., Shen, J., Xie, J., Xu, Y., Yang, T., Cheng, H., & Hu, K. (2026). Construction and application of a traditional Chinese medicine syndrome differentiation and treatment model grounded in knowledge distillation and reinforcement learning. Health Information Science and Systems, 14(1). https://doi.org/10.1007/s13755-026-00451-0

Vancouver

Wang X, Sun X, Shen J, Xie J, Xu Y, Yang T, et al. Construction and application of a traditional Chinese medicine syndrome differentiation and treatment model grounded in knowledge distillation and reinforcement learning. Health Information Science and Systems. 2026;14(1). doi:10.1007/s13755-026-00451-0

BibTeX
@article{Wang2026,
  author = {Wang, Xinyu and Sun, Xiaohe and Shen, Jilong and Xie, Jiadong and Xu, Yichu and Yang, Tao and Cheng, Haibo and Hu, Kongfa},
  title = {Construction and application of a traditional Chinese medicine syndrome differentiation and treatment model grounded in knowledge distillation and reinforcement learning},
  journal = {Health Information Science and Systems},
  year = {2026},
  volume = {14},
  number = {1},
  doi = {10.1007/s13755-026-00451-0}
}
Kostenlos starten →