基于图节点动静态特征的健康事件预测模型

doi:10.3969/j.issn.1006-2475.2023.10.006

摘要/Abstract

摘要： 随着电子病历（EHR）的广泛应用，基于深度学习的临床健康事件预测引起了众多研究者的关注。现有工作主要集中在挖掘患者的高阶时间特征，未能有效地学习疾病之间的隐关系。针对疾病表征学习的问题，本文提出一种新的疾病表示模型（Health Event Prediction Model Based on Dynamic and Static Features of Graph Nodes， DuDas）。该模型最终挖掘出的疾病隐表征包含静态和动态信息，最终实现对临床任务的预测。首先根据疾病共现频率构建疾病关系图，并通过one-hot编码模块为每个疾病节点分配一个初始隐表征。然后根据静态挖掘模块挖掘疾病的静态表征，并与相应的初始隐表征融合为初始动态隐表征。根据图卷积模块挖掘疾病之间的动态关系，学习疾病节点的最终动态隐表征。由于患者的就诊记录具有时间性，本文使用门控循环单元来挖掘历史诊断信息与当前诊断信息之间的关系。为了验证本文提出的方法的有效性，在2个真实数据集上进行实验。实验结果表明，本文提出的模型在预测健康事件任务上达到了更高水平。

关键词: 关键词：疾病表征, 动态表征, 静态表征, 图神经网络, 特征融合

Abstract: With the wide application of electronic healthcare records （EHRs）， the prediction of clinical health events based on deep learning has attracted the attention of many researchers. The existing work mainly focuses on mining the higher-order temporal characteristics of patients， and fails to effectively learn the hidden relationship between diseases. Aiming at the problem of disease representation learning， this paper proposes a novel disease representation model （Health Event Prediction Model Based on Dynamic and Static Features of Graph Nodes， DuDas）， through which the final hidden representation of disease mined by the model contains static and dynamic information， and finally realizes the prediction of clinical tasks. Firstly， the disease graph is constructed according to the disease co-occurrence frequency， and the initial hidden representation is assigned to each disease node by the one-hot coding module. Then， the static representation of the disease is excavated according to the static mining module， and it is fused with the corresponding initial hidden representation as the initial dynamic hidden representation. The dynamic relationship between diseases is mined according to the graph convolution module to learn the final dynamic hidden representation of disease nodes. Due to the temporal nature of patient visits， this article uses gated circulation units to mine the relationship between historical diagnostic information and current diagnostic information. In order to verify the effectiveness of the proposed method， we perform experimental verification on two real datasets. Experimental results show that the proposed model in this paper reaches the higher level in the task of predicting health events.

Key words: Key words: disease representation, dynamic representation, static representation, graph neural network, feature fusion

中图分类号:

TP391

陈俊义. 基于图节点动静态特征的健康事件预测模型[J]. 计算机与现代化, 2023, 0(10): 39-44.

CHEN Jun-yi. Health Event Prediction Model Based on Dynamic and Static Features of Graph Nodes[J]. Computer and Modernization, 2023, 0(10): 39-44.

参考文献［27］

［1］	HARUTYUNYAN H， KHACHATRIAN H， KALE D C， et al. Multitask learning and benchmarking with clinical time series data［J］. Scientific Data， 2019，6. DOI: 10.1038/s41597-019-0103-9.
［2］	BAI T， ZHANG S S， EGLESTON B L， et al. Interpretable representation learning for healthcare via capturing disease progression through time［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2018:43-51.
［3］	LU C， HAN T， NING Y. Context-aware health event prediction via transition functions on dynamic disease graphs［C］// Proceedings of the 36th AAAI Conference on Artificial Intelligence. 2022，36（4）:4567-4574.
［4］	CHAKRABORTY P， FAROOQ F. A robust framework for accelerated outcome-driven risk factor identification from EHR［C］// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2019:1800-1808.
［5］	XU B， WANG N Y， CHEN T Q， et al. Empirical evaluation of rectified activations in convolutional network［J］. arXiv preprint arXiv:1505.00853， 2015.
［6］	ZHANG X S， TANG F Y， DODGE H H， et al. MetaPred: Meta-learning for clinical risk prediction with limited patient electronic health records［C］// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2019:2487-2495.
［7］	LU C， REDDY C K， CHAKRABORTY P， et al. Collaborative graph learning with auxiliary text for temporal event prediction in healthcare［C］// Proceedings of the 30th International Joint Conference on Artificial Intelligence. 2021:3529-3535.
［8］	SONG H， RAJAN D， THIAGARAJAN J， et al. Attend and diagnose: Clinical time series analysis using attention models［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 2018，32（1）. DOI: 10.1609/aaai.v32i1.11635.
［9］	CHOI E， BAHADORI M T， SCHUETZ A， et al. Doctor AI: Predicting clinical events via recurrent neural networks［C］// Proceedings of the 2016 Machine Learning for Healthcare Conference. 2016:301-318.
［10］	MA T F， XIAO C， WANG F. Health-ATM: A deep architecture for multifaceted patient health record representation and risk prediction［C］// Proceedings of the 2018 SIAM International Conference on Data Mining. 2018. DOI: 10.1137/1.9781611975321.30.
［11］	CHOI E， XIAO C， STEWART W， et al. Mime: Multilevel medical embedding of electronic health records for predictive healthcare［C］// Proceedings of the 2018 Advances in Neural Information Processing Systems. 2018:4547-4557.
［12］	SCHWAB P， SCEBBA G C， ZHANG J， et al. Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks［C］// Proceedings of the 2017 Conference on Computing in Cardiology （CinC）. 2017. DOI: 10.22489/CinC.2017.363-223.
［13］	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. 2014:701-710.
［14］	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. 2016:855-864.
［15］	RIBEIRO L F R， SAVERESE P H P， FIGUEIREDO D R. Struc2vec: Learning node representations from structural identity［C］// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017:385-394.
［16］	SHANG J Y， MA T F， XIAO C， et al. Pre-training of graph augmented transformers for medication recommendation［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence AI for Improving Human Well-being. 2019:5953-5959.
［17］	DEVLIN J， CHANG M W， LEE K， et al. BERT: Pre-training of deep bidirectional transformers for language understanding［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2019:4171-4186.
［18］	PHAM T， TRAN T， PHUNG D. DeepCare: A deep dynamic memory model for predictive medicine［C］// Proceedings of the 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining. 2016:30-41.
［19］	WU J， HE J R， XU J J. DEMO-Net: Degree-specific graph neural networks for node and graph classification［C］// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2019:406-415.
［20］	KIPF T N， WELLING M. Semi-supervised classification with graph convolutional networks［C］// Proceedings of the 2017 International Conference on Learning Representations. 2017:410-422.
［21］	RONG Y， HUANG W B， XU T Y， et al. DropEdge: Towards deep graph convolutional networks on node classification［C］// Proceedings of the 2020 International Conference on Learning Representations. 2020:1107-1120.
［22］	HU F Y， ZHU Y Q， WU S， et al. Hierarchical graph convolutional networks for semi-supervised node classification［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019:4532-4539.
［23］	WANG Y Y， DUAN Z H， LIAO B B， et al. Heterogeneous attributed network embedding with graph convolutional networks［C］// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. 2019，33（1）:10061-10062.
［24］	CHOI E， BAHADORI M T， KULAS J A， et al. RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016:3512-3520.
［25］	MA F L， CHITTA R， ZHOU J， et al. Dipole: Diagnosis prediction in healthcare via attention-based bidirectional recurrent neural networks［C］// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017:1903-1911.
［26］	LUO J Y， YE M C， XIAO C， et al. HiTANet: Hierarchical time-aware attention networks for risk prediction on electronic health records［C］// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2020:647-656.
［27］	NGUYEN P， TRAN T， WICKRAMASINGHE N， et al. Deepr: A convolutional net for medical records［J］. IEEE Journal of Biomedical and Health Informatics， 2017，21（1）:22-30.

[1]	夏义春, 李汪根, 李豆豆, 葛英奎, 王志格. 结合注意力机制和图神经网络的CTR预估模型[J]. 计算机与现代化, 2023, 0(03): 29-37.
[2]	姚春华, 张学磊, 宋馨宇, 张举, 蔡佳志, 冯翱. 一种基于图卷积神经网络和依存分析的财经新闻情感分析方法[J]. 计算机与现代化, 2022, 0(05): 33-39.