Artificial intelligence in acupuncture: bridging traditional knowledge and precision integrative medicine

Abstract

The integration of artificial intelligence (AI) into acupuncture research is accelerating the transformation of this traditional, experience-based practice into a data-driven, precision discipline. This review synthesizes recent advances in AI-enabled outcome prediction techniques, encompassing deep learning, meta-analytic modeling, natural language processing (NLP), computer vision, and neuroimaging-based analysis. For instance, convolutional neural networks (CNNs) have been successfully applied to classify tongue images and detect ZHENG patterns, while transformer-based NLP models enable automated extraction of clinical knowledge from classical texts. These technologies improve diagnostic objectivity, standardize treatment planning, and facilitate individualized care by enabling longitudinal efficacy modeling and real-time monitoring. Despite their potential, current implementations are constrained by limited and heterogeneous datasets, annotation variability, and gaps in clinical validation. We analyze key methodological innovations and challenges, and recommend future directions including the construction of federated multimodal data platforms, development of explainable AI frameworks, and promotion of open science practices. This convergence of AI and acupuncture presents a unique opportunity to enhance scientific rigor, clinical utility, and global integration of acupuncture within the paradigm of precision integrative medicine.