Construction of a Path for Evaluating the Efficacy of Traditional Chinese Medicine Driven by the Integration of Big Data and Multidisciplinary Technologies
10.13288/j.11-2166/r.2026.20.001
- VernacularTitle:大数据与多学科技术融合驱动下中医药疗效评价路径的构建
- Author:
Hongyan CUI
1
;
Yuhan FENG
1
;
Rui LI
1
;
Yanan LIU
2
;
Ruixia ZHAO
1
;
Mingyi SHAO
1
Author Information
1. First Affiliated Hospital of Henan University of Traditional Chinese Medicine，Zhengzhou，450003
2. Henan University of Traditional Chinese Medicine
- Publication Type:Journal Article
- Keywords:
traditional Chinese medicine efficacy evaluation;
big data;
artificial intelligence;
omics technology;
systems biology
- From:
Journal of Traditional Chinese Medicine
2026;67(20):2149-2154
- CountryChina
- Language:Chinese
-
Abstract:
By systematically analyzing the bottlenecks in current traditional Chinese medicine （TCM） efficacy evaluation， this study addresses the limitations of TCM efficacy assessment methods in terms of individualization， holism， and complexity representation. Drawing on the concepts and methodologies of evidence-based medicine and systems biology， this paper proposes a new evaluation path by integrating multidisciplinary technologies such as big data， artificial intelligence （AI）， omics techniques， and bioinformatics， and encompassing from foundational data， individualized evaluation， and mechanistic analysis to evidence translation. The path first integrates real-world data， multi-omics profiling， and dynamic monitoring via smart devices to construct a high-dimensional dynamic data foundation. Subsequently， leveraging this foundation， it combines digital twins， dynamic symptom networks， and reinforcement learning to develop a dynamic efficacy evaluation method based on individual self-reference， enabling a shift from group mean comparisons to individual potential outcome comparisons. Furthermore， adopting the systems biology paradigm， it employs dynamic omics monitoring and deep learning models to dissect the synergistic mechanisms of TCM compound prescriptions from network regulation， emergent effects， and dynamic evolution dimensions. Finally， it enhances real-world evidence strength through target trial emulation and causal inference， achieving model iteration via incremental learning. This path aims to advance efficacy evaluation from "point validation" to "systematic characterization" and from "outcome assessment" to "process mechanism elucidation，" providing methodological support for the modernization of TCM.
