Exclusive:Real world clinical research of Traditional Chinese Medicine

Application of graph neural network in mental and nervous system diseases and its enlightenment in the field of Traditional Chinese Medicine

  • LAI Keyun ,
  • LAI Changsheng ,
  • HE Liyun ,
  • WANG Guangjun ,
  • CHEN Xiao
Expand
  • 1. Department of Clinical Medicine of Traditional Chinese and Western Medicine, Shaanxi University of Traditional Chinese Medicine, Xianyang 712046, China
    2. Yulin Red Cross Hospital, Yulin 537000, China
    3. Institute of Clinical Basic Medicine of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100080, China
    4. Institute of Acupuncture and Moxibustion, China Academy of Chinese Medical Sciences, Beijing 100700, China
    5. Xi'an Traditional Chinese Medical Encephalopathy Hospital, Xi'an 710032, China

Received date: 2023-02-18

  Revised date: 2023-03-23

  Online published: 2023-08-15

Abstract

Graph neural network (GNN) is another major development after convolutional neural network, and it belongs to an emerging deep learning method in the field of artificial intelligence. It mainly preserves the topological information in graph data through end-to-end learning from graph to prediction, and overcomes the defect that traditional deep learning cannot be applied to non-Euclidean data. This paper demonstrates the advantages of GNN for processing complex non-Euclidean data through the application progress of GNN in brain-related mental and nervous system diseases. GNN shows great potential in the medical field, furthermore, the network structure of the syndrome differentiation system of Traditional Chinese Medicine (TCM) is similar to the structure of the brain active area, and it is highly compatible with the schematic unstructured data processed by GNN, so GNN has great application prospect in the field of TCM. This article summarizes the application of GNN in the field of TCM and brain-related mental and nervous system diseases, and analyzes the advantages of TCM diagnosis and treatment models from the theoretical level, in order to explore and build a GNN-based model for fitting with the thinking mode of "syndrome differentiation and treatment" and realizing the objective diagnosis in TCM. It provides new means for solving the problems of complex relationship representation in TCM and mining the individual characteristics of patients. And it also provides a favorable tool for revealing the potential mechanism of TCM from multiple perspectives, and developing and improving the science of TCM.

Cite this article

LAI Keyun , LAI Changsheng , HE Liyun , WANG Guangjun , CHEN Xiao . Application of graph neural network in mental and nervous system diseases and its enlightenment in the field of Traditional Chinese Medicine[J]. Science & Technology Review, 2023 , 41(14) : 101 -108 . DOI: 10.3981/j.issn.1000-7857.2023.14.012

References

[1] 刘忠雨 . 深入浅出图神经网络[M]. 北京: 北京机械工业出版社, 2020: 1-2.
[2] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. ArXiv Preprint ArXiv, 2014, doi: 10.48550/arXiv.1409.1556.
[3] Goldberg Y. A primer on neural network models for natural language processing[J]. Journal of Artificial Intelligence Research, 2016, 57: 345-420.
[4] 国务院关于印发新一代人工智能发展规划的通知[EB/OL]. (2017-07-20) [2023-02-10]. http://www. gov. cn/zhengce/content/2017-07/20/content_5211996.htm.
[5] Lim J, Ryu S, Park K, et al. Predicting drug-target interaction using a novel graph neural network with 3D structure-embedded graph representation[J]. Journal of Chemical Information and Modeling, 2019, 59(9): 3981-3988.
[6] Chang Q, Li C, Tian Q, et al. Classification of first-episode schizophrenia, chronic schizophrenia and healthy control based on brain network of mismatch negativity by graph neural network[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 1784-1794.
[7] Bessadok A, Mahjoub M A, Rekik I. Brain multigraph prediction using topology-aware adversarial graph neural network[J]. Medical Image Analysis, 2021, 72: 102090.
[8] 吴博, 梁循, 张树森, 等 . 图神经网络前沿进展与应用[J]. 计算机学报, 2022, 45(1): 35-68.
[9] Scarselli F, Gori M, Tsoi A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1): 61-80.
[10] Bruna J, Zaremba W, Szlam A, et al. Spectral networks and locally connected networks on graphs[J]. ArXiv Preprint ArXiv, 2013, doi: 10.48550/arXiv.1312.6203.
[11] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. ArXiv Preprint ArXiv, 2016, 1609. 02907.
[12] Seo Y, Defferrard M, Vandergheynst P, et al. Structured sequence modeling with graph convolutional recurrent networks[C]//Neural Information Processing: 25th International Conference, ICONIP 2018, Siem Reap, Cambodia: Springer International Publishing, 2018: 362-373.
[13] 刘知远 . 图神经网络导论[M]. 北京: 人民邮电出版社, 2021: 13-14.
[14] Farahani F V, Karwowski W, Lighthall N R. Application of graph theory for identifying connectivity patterns in human brain networks: A systematic review[J]. Frontiers in Neuroscience, 2019, 13: 585.
[15] Mathur P, Chakka V K. Graph signal processing of EEG signals for detection of epilepsy[C]// International Conference on Signal Processing and Integrated Networks(SPIN) 2020. Noida, India: IEEE, 2020: 839-843.
[16] Lian Q, Qi Y, Pan G, et al. Learning graph in graph convolutional neural networks for robust seizure prediction[J]. Journal of Neural Engineering, 2020, 17(3): 035004.
[17] Parisot S, Ktena S I, Ferrante E, et al. Disease prediction using graph convolutional networks: Application to autism spectrum disorder and Alzheimer's disease[J]. Medical Image Analysis, 2018, 48: 117-130.
[18] Song T A, Chowdhury S R, Yang F, et al. Graph convolutional neural networks for Alzheimer's disease classification[C]//2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019). Venice, Italy: IEEE, 2019: 414-417.
[19] Velickovic P, Cucurull G, Casanova A, et al. Graph attention networks[J]. Stat, 2017, 1050(20): 10.48550.
[20] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, doi: 10.48550/arXiv.1706.03762.
[21] Yang H, Li X, Wu Y, et al. Interpretable multimodality embedding of cerebral cortex using attention graph network for identifying bipolar disorder[C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen:
Springer International Publishing, 2019: 799-807.
[22] Zhang X, He L, Chen K, et al. Multi-view graph convolutional network and its applications on neuroimage analysis for parkinson's disease[C]//AMIA Annual Symposium Proceedings. New York: American Medical Informatics Association, 2018: 1147.
[23] Yao D, Sui J, Yang E, et al. Temporal-adaptive graph convolutional network for automated identification of major depressive disorder using resting-state fMRI[C]//Machine Learning in Medical Imaging: 11th International Workshop, MLMI 2020, Held in Conjunction with MICCAI 2020. Lima, Peru: Springer International Publishing, 2020: 1-10.
[24] Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting[J]. ArXiv Preprint ArXiv, 2017, doi: 10.48550/arXiv.1709.04875.
[25] Li Z, Hwang K, Li K, et al. Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity[J]. Scientific Reports, 2022, 12(1): 18998.
[26] Kipf T N, Welling M. Variational graph auto-encoders[J]. ArXiv Preprint ArXiv, 2016, doi: 10.48550/arXiv.1611.07308.
[27] Li Y, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting[J]. ArXiv Preprint ArXiv, 2017, doi: 10.48550/arXiv.1707.01926.
[28] Seo Y, Defferrard M, Vandergheynst P, et al. Structured sequence modeling with graph convolutional recurrent networks[C]//Neural Information Processing: 25th International Conference, ICONIP 2018. Siem Reap, Cambodia: Springer International Publishing, 2018: 362-373.
[29] 胡杨 . 面向智能中医辅助诊疗的多注意力和知识辅助神经网络设计研究[D]. 广州: 华南理工大学, 2020.
[30] 一种结合深度卷积网络和图神经网络的中医证候诊断和健康评价方法: CN202010853821.5[P]. 杭州: 杭州泉脉科技有限公司, 2021-06-22.
[31] Schlichtkrull M, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks[C]//The Semantic Web: 15th International Conference, ESWC 2018. Heraklion, Crete, Greece: Springer International Publishing, 2018: 593-607.
[32] 靳远远 . 基于图神经网络的中医药方推荐技术研究[D]. 上海: 华东师范大学, 2022.
[33] 基于图神经网络的中医辩治推荐系统、方法和电子设备: CN202110913252.3[P]. 海南: 海南榕树家信息科技有限公司, 2021-11-09.
[34] 基 于 超 图 神 经 网 络 的 中 草 药 方 剂 推 荐 方 法 :CN202111577788.9[P]. 福州: 闽江学院, 2022-03-29.
[35] 基于证候信息的图神经网络中药推荐方法: CN202210 870609.9[P]. 上海: 华东师范大学, 2022-10-11.
[36] Zeng X, Zhu S, Lu W, et al. Target identification among known drugs by deep learning from heterogeneous networks[J]. Chemical Science, 2020, 11(7): 1775-1797.
[37] 一 种 基 于 知 识 图 谱 的 中 药 复 方 靶 标 预 法 : CN202111123982.X[P]. 南京: 东南大学, 2021-12-07.
[38] 龚倬 . 基于知识图谱的中药复方靶标预测模型研究与实现[D]. 南京: 东南大学, 2021.
[39] 一种基于图神经网络及组学信息的药物功效预测方法: CN202210206033.6[P]. 广州: 广州中医药大学(广州中医药研究院), 2022-06-21.
[40] 许鸿本, 赵文, 周惠敏, 等 . 基于脏腑病机的辅助智能诊疗系统研究[J]. 福建中医药, 2021, 52(11): 5-9.
[41] 赵文 . 基于中医状态辨识的《伤寒论》诊疗思维与逻辑及智能诊疗模型研究[D]. 福州: 福建中医药大学, 2021.
Outlines

/