Structure-aware siamese graph neural networks for encounter-level patient similarity learning

doi:10.1016/j.jbi.2022.104027

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Structure-aware siamese graph neural networks for encounter-level patient similarity learning
	Gu, Yifan1,2 ; Yang, Xuebing1 ; Tian, Lei1,2 ; Yang, Hongyu 5,6; Lv, Jicheng 5,6; Yang, Chao5,6 ; Wang, Jinwei 5,6; Xi, Jianing 7; Kong, Guilan 3,4; Zhang, Wensheng1,2
发表期刊	JOURNAL OF BIOMEDICAL INFORMATICS
ISSN	1532-0464
	2022-03-01
卷号	127 页码:13
通讯作者	Kong, Guilan(guilan.kong@hsc.pku.edu.cn) ; Zhang, Wensheng(zhangwenshengia@hotmail.com)
摘要	Patient similarity learning has attracted great research interest in biomedical informatics. Correctly identifying the similarity between a given patient and patient records in the database could contribute to clinical references for diagnosis and medication. The sparsity of underlying relationships between patients poses difficulties for similarity learning, which becomes more challenging when considering real-world Electronic Health Records (EHRs) with a large number of missing values. In the paper, we organize EHRs as a graph and propose a novel deep learning framework, Structure-aware Siamese Graph neural Networks (SSGNet), to perform robust encounter-level patient similarity learning while capturing the intrinsic graph structure and mitigating the influence from missing values. The proposed SSGNet regards each patient encounter as a node, and learns the node embeddings and the similarity between nodes simultaneously via Graph Neural Networks (GNNs) with siamese architecture. Further, SSGNet employs a low-rank and contrastive objective to optimize the structure of the patient graph and enhance model capacity. The extensive experiments were conducted on two publicly available datasets and a real-world dataset regarding IgA nephropathy from Peking University First Hospital, in comparison with multiple baseline and state-of-the-art methods. The significant improvement in Accuracy, Precision, Recall and F1 score on the patient encounter pairwise similarity classification task demonstrates the superiority of SSGNet. The mean average precision (mAP) of SSGNet on the similar encounter retrieval task is also better than other competitors. Furthermore, SSGNet's stable similarity classification accuracies at different missing rates of data validate the effectiveness and robustness of our proposal.
关键词	Encounter-Level Patient Similarity Representation Learning Siamese Networks Graph Neural Networks
DOI	10.1016/j.jbi.2022.104027
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102100] ; National Natural Science Foundation of China[61961160707] ; National Natural Science Foundation of China[61976212] ; National Natural Science Foundation of China[61906190] ; National Natural Science Foundation of China[62006139] ; CAMS Innovation Fund for Medical Sciences[2019-I2M-5-046]
项目资助者	National Key R&D Program of China ; National Natural Science Foundation of China ; CAMS Innovation Fund for Medical Sciences
WOS研究方向	Computer Science ; Medical Informatics
WOS类目	Computer Science, Interdisciplinary Applications ; Medical Informatics
WOS记录号	WOS:000772252000017
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
七大方向——子方向分类	人工智能+医疗
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48223
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Kong, Guilan; Zhang, Wensheng
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Peking Univ, Natl Inst Hlth Data Sci, Beijing, Peoples R China 4.Peking Univ, Adv Inst Informat Technol, Hangzhou, Peoples R China 5.Peking Univ, Dept Med, Renal Div, Hosp 1, Beijing, Peoples R China 6.Chinese Acad Med Sci, Res Units Diag & Treatment Immune Mediated Kidney, Beijing, Peoples R China 7.Northwestern Polytech Univ, Sch Artificial Intelligence Opt & Elect iOPEN, Xian, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Gu, Yifan,Yang, Xuebing,Tian, Lei,et al. Structure-aware siamese graph neural networks for encounter-level patient similarity learning[J]. JOURNAL OF BIOMEDICAL INFORMATICS,2022,127:13.
APA	Gu, Yifan.,Yang, Xuebing.,Tian, Lei.,Yang, Hongyu.,Lv, Jicheng.,...&Zhang, Wensheng.(2022).Structure-aware siamese graph neural networks for encounter-level patient similarity learning.JOURNAL OF BIOMEDICAL INFORMATICS,127,13.
MLA	Gu, Yifan,et al."Structure-aware siamese graph neural networks for encounter-level patient similarity learning".JOURNAL OF BIOMEDICAL INFORMATICS 127(2022):13.