基于术中指标建立非心胸手术术后呼吸衰竭梯度提升预测模型  

Establishment of a gradient boosting prediction model for respiratory failure after non-cardiothoracic surgery based on intraoperative indicators

作　　者：黄家号 李雨捷 刘祥 杨智勇 孙义竹 梁浩 易斌 鲁开智 HUANG Jiahao;LI Yujie;LIU Xiang;YANG Zhiyong;SUN Yizhu;LIANG Hao;YI Bin;LU Kaizhi(Department of Anesthesiology,First Affiliated Hospital,Army Medical University(Third Military Medical University),Chongqing,400038,China)

机构地区：[1]陆军军医大学(第三军医大学)第一附属医院麻醉科,重庆400038

出　　处：《陆军军医大学学报》2023年第8期739-745,共7页Journal of Army Medical University

基　　金：国家重点研发计划(2018YFC0116702)。

摘　　要：目的开发并验证一个基于术中指标在非心胸手术患者术后呼吸衰竭(postoperative respiratory failure,PRF)的机器学习预测模型。方法纳入西南医院2014年1月至2019年6月行非心胸手术患者705例[训练集565例(PRF 128例),测试集140例(PRF 35例)]、华西医院2019年5月至2020年1月和中山医院2019年6月至2019年12月行非心胸手术患者164例[验证集164例(PRF 41例)]。提取患者19项术中预测指标,通过6种机器学习算法:梯度提升模型(gradient boosting model,GBM)、广义线性模型(generalize linear model,GLM)、k-近邻(k-nearest neighbor,KNN)、朴素贝叶斯(naive bayes,NB)、神经网络(neural network,NNET),支持向量机(support vector machine linear,SVM)开发及测试模型,并在验证集进行验证,通过各模型间性能对比,筛选出最佳模型,最终建立网页预测模型。结果GBM获得了最佳性能,准确性76.2%(95%CI:69.0%~82.5%),受试者操作曲线下面积(area under the subject curve,AUC):0.794(95%CI:0.707~0.882),精准-召回曲线下面积(area under the precision-recall curve,AUPRC):0.641,Brier评分:0.169。结论基于GBM算法开发的模型具有更高的泛化性、准确性、临床实用性,并有助于避免过度拟合。建立的网页预测模型(http://150.158.55.139)可为患者PRF提供新的动态评估方法,量化手术风险。ObjectiveTo develop and validate a machine learning prediction model for postoperative respiratory failure(PRF)in patients after non-cardiothoracic surgery based on intraoperative indicators.MethodsA total of 705 patients undergoing non-cardiothoracic surgery in our hospital from January 2014 to June 2019 were enrolled,and then 565 patients of them were assigned in the training set(including 128 cases of PRF)and 140 patients into the test set(35 cases of PRF).Another 164 patients undergoing non-cardiothoracic surgery at West China Hospital from May 2019 to January 2020 and Zhongshan Hospital from June 2019 to December 2019 were assigned into the validation set(41 cases of PRF).Nineteen intraoperative indicators were extracted,and 6 machine learning algorithms,such as gradient boosting model(GBM),generalize linear model(GLM),k-nearest neighbor(KNN),naive bayes(NB),neural network(NNET),and support vector machine linear(SVM)were used to develop and test the models and were verified in the validation set.The best model was screened out by comparing the performance of each model,and finally,the web page prediction model was established.ResultsGBM obtained the best performance,with an accuracy of 76.2%(95%CI:69.0%~82.5%),an area under the subject curve(AUC)of 0.794(95%CI:0.707~0.882),an area under the precision-recall curve(AUPRC)of 0.641,and a Brier score of 0.169.ConclusionThe model developed based on GBM algorithm is of higher generalization,accuracy,and clinical utility,and helps avoid overfitting.The developed web page prediction model(http://150.158.55.139)can provide a new dynamic evaluation method for PRF and quantify surgical risk.

关 键 词：术后呼吸衰竭 预测模型 临床实用性 量化手术风险 

分 类 号：R319[医药卫生—基础医学] R563.806R619.9