摘要
通过文献综述,总结了在构建ICU患者住院死亡风险预测模型时所涉及的基本概念、步骤和常用方法。讨论了预测变量的来源及其筛选办法。在临床医生最为熟知的逻辑回归模型的基础上,阐述了人工神经网络、决策树和支持向量机三种机器学习模型的基本框架以及优劣势。描述了用于评价模型性能好坏的各种指标以及验证模型性能的方式。
Through literature review,the basic concepts,procedures and common methods involved in the developmentof mortality prediction models are summarized.First,the sources of predictor variables and their corresponding screeningapproaches are discussed.Second,on the basis of the logistic regression model which is most familiar to clinicians,thebasic framework and advantages and disadvantages of the neural network,decision tree and support vector machine areelaborated.Finally,the common metrics used to evaluate the performance of the model are described,as well as the wayto validate the model.
作者
谢俊卿
蔺轲
孔桂兰
XIE Junqing;LIN Ke;KONG Guilan(Medical Informatics Center, Peking University, Beijing 100191, China;Department of Epidemiology & Biostatistics, School of Public Health, Peking University, Beijing 100191, China)
出处
《计算机工程与应用》
CSCD
北大核心
2017年第20期24-30,共7页
Computer Engineering and Applications
基金
北京大学医信种子基金(No.BMU20160592)
关键词
死亡预测
逻辑回归
机器学习
重症监护室
mortality prediction
logistic regression
machine learning
Intensive Care Unit(ICU)
