中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 重庆绿色智能技术研究院
  3. 中国科学院重庆绿色智能技术研究院
Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network

文献类型：期刊论文

作者Chen, Yu-wen2,3,4; Li, Yu-jie1; Deng, Peng1; Yang, Zhi-yong1; Zhong, Kun-hua2,3,4; Zhang, Li-ge2,4; Chen, Yang1; Zhi, Hong-yu1; Hu, Xiao-yan1; Gu, Jian-teng1
刊名BMC ANESTHESIOLOGY
出版日期2022-04-23
卷号22期号:1页码:11
关键词In-hospital mortality risk ICU Temporal Convolution Network Attention Mechanism Time series Artificial Intelligence
ISSN号1471-2253
DOI10.1186/s12871-022-01625-5
通讯作者Qin, Xiao-lin(qinxl2001@126.com) ; Yi, Bin(yibin1974@163.com)
英文摘要Background Dynamic prediction of patient mortality risk in the ICU with time series data is limited due to high dimensionality, uncertainty in sampling intervals, and other issues. A new deep learning method, temporal convolution network (TCN), makes it possible to deal with complex clinical time series data in ICU. We aimed to develop and validate it to predict mortality risk using time series data from MIMIC III dataset. Methods A total of 21,139 records of ICU stays were analysed and 17 physiological variables from the MIMIC III dataset were used to predict mortality risk. Then we compared the model performance of the attention-based TCN with that of traditional artificial intelligence (AI) methods. Results The area under receiver operating characteristic (AUCROC) and area under precision-recall curve (AUC-PR) of attention-based TCN for predicting the mortality risk 48 h after ICU admission were 0.837 (0.824 -0.850) and 0.454, respectively. The sensitivity and specificity of attention-based TCN were 67.1% and 82.6%, respectively, compared to the traditional AI method, which had a low sensitivity (< 50%). Conclusions The attention-based TCN model achieved better performance in the prediction of mortality risk with time series data than traditional AI methods and conventional score-based models. The attention-based TCN mortality risk model has the potential for helping decision-making for critical patients.
资助项目National Key R&D Program of China[2018YFC0116702] ; National Key R&D Program of China[2018YFC00116704] ; National Natural Science Foundation of China[82100658] ; National Natural Science Foundation of China[81600035] ; Medical Innovation Capacity Improvement Program for Medical Staff of the First Affiliated Hospital of the Third Military Medical University[SWH2018QNKJ-27] ; Technology innovation and application research and development project of Chongqing city[cstc2019jscx-msxmX0237]
WOS研究方向Anesthesiology
语种英语
WOS记录号WOS:000785935300003
出版者BMC
源URL[http://119.78.100.138/handle/2HOD01W0/15560]  
专题中国科学院重庆绿色智能技术研究院
通讯作者Qin, Xiao-lin; Yi, Bin
作者单位1.Third Mil Med Univ, Southwest Hosp, Dept Anaesthesiol, Army Med Univ, Chongqing 400038, Peoples R China
2.Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu 610041, Peoples R China
3.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
5.Univ Hong Kong, Li Ka Shing Fac Med, Dept Anaesthesiol, Hong Kong, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yu-wen,Li, Yu-jie,Deng, Peng,et al. Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network[J]. BMC ANESTHESIOLOGY,2022,22(1):11.
APA Chen, Yu-wen.,Li, Yu-jie.,Deng, Peng.,Yang, Zhi-yong.,Zhong, Kun-hua.,...&Yi, Bin.(2022).Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network.BMC ANESTHESIOLOGY,22(1),11.
MLA Chen, Yu-wen,et al."Learning to predict in-hospital mortality risk in the intensive care unit with attention-based temporal convolution network".BMC ANESTHESIOLOGY 22.1(2022):11.

入库方式： OAI收割

来源：重庆绿色智能技术研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。