A cross-modal clinical prediction system for intensive care unit patient outcome

doi:10.1016/j.knosys.2023.111160

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	A cross-modal clinical prediction system for intensive care unit patient outcome
	Sun, Mengxuan 1,2; Yang, Xuebing 1; Niu, Jinghao 1; Gu, Yifan 1,2; Wang, Chutong 1,2; Zhang, Wensheng 1,3
刊名	KNOWLEDGE-BASED SYSTEMS
	2024-01-11
卷号	283 页码:16
关键词	Electronic health records Clinical outcome prediction Patient representation Cross-modal contrastive learning
ISSN号	0950-7051
DOI	10.1016/j.knosys.2023.111160
通讯作者	Yang, Xuebing(yangxuebing2013@ia.ac.cn) ; Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	Electronic Health Records (EHRs) are becoming an encyclopedia of clinical concepts, encompassing diagnoses, medications and clinical descriptions to describe patients' health conditions. The abundance of EHR data presents unprecedented opportunities for leveraging machine learning in clinical predictive tasks. However, the complex process of acquiring healthcare data in some settings like Intensive Care Unit (ICU) gives rise to various challenges in mining EHR, such as modality diversity, heterogeneity, data silo and data quality problems, etc. In this paper, to overcome the data heterogeneity and data quality issues, we propose a Code Text cross-modal Contrastive Learning (CTCL) framework specifically designed for predicting ICU patient outcomes. This framework leverages both structured (multi-view medical codes) and unstructured (clinical notes) EHR data to extract patient representations. To capture the complicated intra and inter interactions among medical codes, CTCL employs a multi-view graph convolution network to extract code encodings and a cross-view contrastive loss to regularize the model parameters. To enhance patient representations across different modalities, a cross-modal contrastive learning module is introduced. Experimental evaluations on the eICU-CRD database demonstrate that CTCL outperforms state-of-the-art competitors on the ICU mortality prediction task and in-hospital readmission prediction task. Furthermore, ablation studies and discussions demonstrate the effectiveness of each module of the framework.
资助项目	Na-tional Key Research and Development Program of China[2021ZD0111005] ; Na-tional Key Research and Development Program of China[61976212] ; Na-tional Key Research and Development Program of China[62006139] ; Na-tional Key Research and Development Program of China[62203437] ; Na-tional Key Research and Development Program of China[61976213]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:001147289400001
资助机构	Na-tional Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54798]
专题	多模态人工智能系统全国重点实验室
通讯作者	Yang, Xuebing; Zhang, Wensheng
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Guangzhou Univ, Guangzhou 510006, Peoples R China
推荐引用方式 GB/T 7714	Sun, Mengxuan,Yang, Xuebing,Niu, Jinghao,et al. A cross-modal clinical prediction system for intensive care unit patient outcome[J]. KNOWLEDGE-BASED SYSTEMS,2024,283:16.
APA	Sun, Mengxuan,Yang, Xuebing,Niu, Jinghao,Gu, Yifan,Wang, Chutong,&Zhang, Wensheng.(2024).A cross-modal clinical prediction system for intensive care unit patient outcome.KNOWLEDGE-BASED SYSTEMS,283,16.
MLA	Sun, Mengxuan,et al."A cross-modal clinical prediction system for intensive care unit patient outcome".KNOWLEDGE-BASED SYSTEMS 283(2024):16.