From Empirical Wisdom to Computational Intelligence: A Knowledge-Data Dual-Driven Paradigm for Modernizing Traditional Chinese Medicine

The integration of Artificial Intelligence (AI) with traditional Chinese medicine (TCM) presents a unique epistemological challenge posed by the tension between TCM’s holistic, experiential paradigm and AI’s data-driven logic. This paper introduces and defends a “Knowledge-Data Dual-Driven” paradigm as a foundational framework for the authentic modernization of TCM. The paradigm involves two synergistic pathways: first, formalizing implicit TCM wisdom into explicit, computable structures using large-scale knowledge graphs (KGs) and TCM-specific large language models (LLMs); second, objectifying diagnostic information by digitizing the “four diagnostic methods” to construct a multimodal “TCM Phenomics”. The integration of these pillars via hybrid AI architectures (e.g., KG-grounded LLMs) aims to create next-generation intelligent diagnostic systems that are accurate, interpretable, and theoretically grounded. However, critical challenges persist, including data heterogeneity, model interpretability, and clinical integration bottlenecks. Overcoming these requires steadfast interdisciplinary collaboration to develop human-centered AI that augments, rather than replaces, clinical decision-making. The ultimate vision lies in leveraging computational intelligence to amplify TCM’s empirical wisdom, enabling more precise, personalized, and scientifically grounded healthcare within an integrative framework.