首页|期刊导航|中华中医药学刊|图神经网络在中医药领域应用现状与前景展望

图神经网络在中医药领域应用现状与前景展望OA

Current Status and Prospects of Application of Graph Neural Networks in The Field of Traditional Chinese Medicine

中文摘要英文摘要

随着人工智能的兴起与高速发展,深度学习作为人工智能领域中的重要一环已在材料学、生物医学、文学艺术等多方面、多领域取得了大量成果,体现了极高的泛用性与价值.图神经网络(Graph Neural Networks,GNN)作为一种新兴的深度学习方法,克服了以往深度学习只能在欧式数据框架下的缺点,展现出其在处理非欧式复杂数据,尤其是图数据时的强大能力,显示出其巨大的潜力.当前,图神经网络已被较广泛地应用于医疗领域,并初步运用于中医药临床与基础研究,在中医处方推荐、疾病证候诊断、中药靶点预测等方面取得了一定的成果.通过对图神经网络在中医药领域的应用现状进行梳理,结合目前图神经网络技术的特点展望该技术在中医药领域的未来发展,认为图神经网络在临床诊断、处方施治、中药研究、典籍利用等方面具有广阔的应用前景.以期为之后的基于图神经网络的中医药相关研究提供思路与启发,使中医学能够与时俱进,提升智能化与客观化,更好地为人民医疗卫生与祖国健康事业服务.

With the rise and rapid development of artificial intelligence,deep learning,as an important part of the field of ar-tificial intelligence,has achieved significant results in various fields such as materials science,biomedicine,literature,and art,demonstrating high versatility and value.As an emerging deep learning method,Graph Neural Network(GNN)overcomes the lim-itation of traditional deep learning that can only be applied to Euclidean data frameworks,demonstrating its powerful ability to handle non-Euclidean complex data especially graph data,and demonstrating its enormous potential.Currently,GNN has been widely applied in the medical field and has been preliminarily applied in clinical and basic researches of traditional Chinese medi-cine.They have achieved certain results in traditional Chinese medicine prescription recommendation,symptom diagnosis and tar-get prediction of traditional Chinese medicine.By reviewing the current application status of GNN in the field of traditional Chi-nese medicine and combining the characteristics of current GNN technology,it looks forward to the future development of this technology in the field of traditional Chinese medicine.It is believed that GNN has broad application prospects in clinical diagno-sis,prescription treatment,traditional Chinese medicine research and utilization of classics.It is to provide ideas and inspiration for future research on Traditional Chinese Medicine based on graph neural networks so that traditional Chinese medicine can keep pace with the times,enhance intelligence and objectivity,and better serve the people's medical and health care and health cause of the motherland.

祁嘉文;刘毅

成都中医药大学基础医学院,四川成都 611137成都中医药大学基础医学院,四川成都 611137

医药卫生

深度学习图神经网络中医学

deep learningGraph Neural Networktraditional Chinese medicine

《中华中医药学刊》 2026 (1)

24-29,6

国家重点研发计划项目(2018YFC1704104)四川省中医药管理局中医药科研专项课题重点项目(2024zd024)成都中医药大学"杏林学者"学科人才科研提升计划项目(XKTD2022014)

10.13193/j.issn.1673-7717.2026.01.005

评论