| 394 | 0 | 61 |
| 下载次数 | 被引频次 | 阅读次数 |
图神经网络是人工智能前沿技术之一，具有处理图结构数据的强大能力。在中医诊疗领域，辨证论治涉及复杂的辨证推演、方药配伍等，表现为“病-证-症-方-药”之间的复杂联系，呈现显著的图结构特征。通过分析中医诊疗数据的图结构特征，讨论中医诊疗数据的图结构转化，以及中医诊疗图神经网络应用场景等，初步探析了图神经网络在中医药领域应用思路。将图神经网络用于中医诊疗领域，需要针对不同的数据类型和应用场景进行建模，解决初始图构建、知识学习和特征学习等，进而为下游的证候预测、方药推荐等提供支持。
Abstract：Graph neural networks are one of the frontier technologies in artificial intelligence, with the powerful ability to process graph-structured data.In the field of traditional Chinese medicine diagnosis and treatment, syndrome differentiation and treatment involves complex syndrome inference, prescription compatibility, etc.,which manifest as complex relationships of“disease-syndrome-symptom-prescription-medicine”,showing significant graph structure characteristics.This paper analyzed the graph structure characteristics of traditional Chinese medicine diagnosis and treatment data, discussed the graph structure transformation of traditional Chinese medicine diagnosis and treatment data and the application scenarios of traditional Chinese medicine graph neural network, and preliminarily explored the application ideas of graph neural network in the field of traditional Chinese medicine.Applying graph neural networks to the field of traditional Chinese medicine diagnosis and treatment requires modeling for different data types and application scenarios, solving initial graph construction, knowledge learning and features, etc.,and then providing support for downstream syndrome prediction, prescription recommendation, etc.
[1] 周荣易，马丙祥，韩新民，等.论中西医的整体观念[J].中华中医药杂志，2019,34(7):2854-2858.
[2] 吴朦，李菲，呼思乐，等.2020—2021年中医理论方法论研究进展[J].中国中医基础医学杂志，2022,28(10):1549-1552,1721.
[3] 王丽婷，刘长松，魏玮，等.中医学术客观化、智能化传承的思考及初步实现[J].中医杂志，2021,62(12):1036-1039.
[4] 王博，张莹莹，王念，等.复杂网络控制理论在方剂作用机制研究中的价值[J].北京中医药大学学报，2022,45(2):116-119.
[5] 白春清.中医专家系统三十年[J].医学信息(上旬刊),2011,24(2):550-552.
[6] 张玉洁，白如江，许海云，等.融合多自然语言处理任务的中医辅助诊疗方案研究——以糖尿病为例[J].数据分析与知识发现，2022(1):122-133.
[7] 刘福栋，姜晓晨，王桂彬，等.机器学习方法在中医学传承研究中的应用及思考[J].中医杂志，2022,63(8):720-724,738.
[8] 樊佳赛，杜艺菲，许佳颖，等.基于中医证候和机器学习构建慢性心力衰竭中西医结合预后模型[J].基础医学与临床，2022,42(8):1169-1175.
[9] 万治，邹逊，张家齐，等.基于视觉和深度学习的智能化中医检测系统[J].数字通信世界，2022(6):39-42.
[10] GAO W Q,CHENG N,XIN G J,et al.TCM2Vec:a detached feature extraction deep learning approach of traditional Chinese medicine for formula efficacy prediction[J].Multimed Tools Appl,2023,82(17):26987-27004.
[11] WU L F,CUI P,PEI J,et al.Graph neural networks:foundation,frontiers and applications[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Washington DC,USA.ACM,2022:4840-4841.
[12] FAN W Q,MA Y,LI Q,et al.Graph neural networks for social recommendation[C]//The World Wide Web Conference.San Francisco,CA,USA.ACM,2019:417-426.
[13] LI Y,ZHANG G Y,WANG P,et al.Graph neural networks in biomedical data:a review[J].Curr Bioinform,2022,17(6):483-492.
[14] 李璐，马捷，孙恒宇，等.面向中医诊疗知识库的医案元数据模型构建研究[J].图书情报工作，2021,65(2):4-16.
[15] KIPF T N,WELLING M.Semi-supervised classification with graph convolutional networks[J].arXiv E Prints,2016:arXiv:1609.02907.
[16] HAMILTON W L,YING R,LESKOVEC J.Inductive representation learning on large graphs[EB/OL].2017:1706.02216.https://arxiv.
[17]et al.Graph attention networks[EB/OL].2017:1710.10903.https://arxiv.org/abs/1710.10903v3.
[18] KIPF T N,WELLING M.Variational graph auto-encoders[EB/OL].2016:1611.07308.https://arxiv.org/abs/1611.07308v1.
[19] XU K,HU W H,LESKOVEC J,et al.How powerful are graph neural networks?[EB/OL].2018:1810.00826.https://arxiv.org/abs/1810.00826v3.
[20] WANG X,JI H Y,SHI C,et al.Heterogeneous graph attention network[C]//The World Wide Web Conference.San Francisco,CA,USA.ACM,2019:2022-2032.
[21] PEROZZI B,AL-RFOU R,SKIENA S.DeepWalk:online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York USA.ACM,2014:701-710.
[22] GROVER A,LESKOVEC J.node2vec:scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco California USA.ACM,2016:855-864.
[23] TANG J,QU M,WANG MZ,et al.LINE:large-scale information network embedding[EB/OL].2015:1503.03578.https://arxiv.org/abs/1503.03578v1.
[24] 孙肇阳，吕桂娇，郭义，等.中医诊疗复杂巨系统的人工神经网络建模原理[J].中华中医药杂志，2022,37(10):5841-5844.
[25] TENG S H,FU A M,LU W K,et al.TCM syndrome classification using graph convolutional network[J].Eur J Integr Med,2023,62:102288.
[26] RUAN C Y,WU Y P,YANG Y,et al.Semantic-aware graph convolutional networks for clinical auxiliary diagnosis and treatment of traditional Chinese medicine[J].IEEE Access,2021,9:8797-8807.
[27] YANG X Y,DING C S.SMRGAT:a traditional Chinese herb recommendation model based on a multi-graph residual attention network and semantic knowledge fusion[J].J Ethnopharmacol,2023,315:116693.
[28] YANG Y,RAO Y L,YU M H,et al.Multi-layer information fusion based on graph convolutional network for knowledge-driven herb recommendation[J].Neural Netw,2022,146:1-10.
基本信息:
DOI：10.13193/j.issn.1673-7717.2025.05.004
中图分类号:TP183;R24
引用信息:
[1]张舒雅,杨涛,胡孔法.图神经网络在中医诊疗领域的应用思路探析[J].中华中医药学刊,2025,43(05):18-21+261.DOI:10.13193/j.issn.1673-7717.2025.05.004.
基金信息:
国家自然科学基金项目(82174276,82074580); 国家重点研发计划项目(2022YFC3500201); 中国博士后科学基金面上项目(2021M701674); 江苏省重点研发计划项目(BE2022712); 江苏省博士后科研资助计划项目(2021K457C); 江苏高校“青蓝工程”项目(2024); 江苏省研究生科研创新计划项目(KYCX23＿2080)