XGboost模型对缺血性脑卒中出院后90d内复发再入院风险的预测效果分析  

XGboost model in predicting readmission of patients with ischemic stroke recurrence within 90 d

作　　者：许源 马健勇[2] 葛艳秋 黎敏[4] 任元凯 易应萍[1] Xu Yuan;Ma Jianyong;Ge Yanqiu;Li Min;Ren Yuankai;Yi Yingping(Clinical Big Data Research Center,Second Affiliated Hospital of Nanchang University,Nanchang 330006,Chin;Department of Cardiology,Second Affiliated Hospital of Nanchang University,Nanchang 330006,Chin;Department of Public Health,School of Medicine,Nanchang University,Nanchang 330006,China;Department of Neurology,Second Affiliated Hospital of Nanchang University,Nanchang 330006,Chin;HBT Medical Information Company,Suzhou 215000,China)

机构地区：[1]南昌大学第二附属医院医疗大数据研究中心,南昌330006 [2]南昌大学第二附属医院心血管内科,南昌330006 [3]南昌大学医学部公共卫生学院,南昌330006 [4]南昌大学第二附属医院神经内科,南昌330006 [5]赫博特医疗信息科技有限公司,苏州215000

出　　处：《中华神经医学杂志》2018年第8期813-818,共6页Chinese Journal of Neuromedicine

基　　金：江西省科技厅科技创新平台（20171BCD40024）;江西省科技厅一般项目（20171BBH80025）

摘　　要：目的评价XGboost模型对缺血性脑卒中出院后90d内复发再入院风险的预测效果，为缺血性脑卒中复发再入院高危人群的早期筛查及预防提供参考依据。方法回顾性收集南昌大学第二附属医院神经内科自2007年1月至2017年7月收治的6070例初发缺血性脑卒中患者的临床资料，采用XGboost模型及多因素Logistic回归分析模型筛选出患者出院后90d内复发再入院的影响因素，分析比较两者的受试者工作特征曲线（ROC）及计算敏感度、特异度、约登指数，以评价XGboost模型的预测效果。结果出院后90d内复发再入院的缺血性脑卒中患者共520例，发病率为8．57％。多因素Logistic回归分析显示住院天数（OR=1．016，P=0．000，95％CI：1．008-1．025）、高血压（OR=4．598，P=-0．000，95％CI：3．717-5．687）、肺部感染（OR=1．452，P=-0．025，95％CI：1．048—2．012）、中性粒细胞百分比（OR=1．013，P=-0．006，95％CI：1．004～1．022）、红细胞分布宽度（变异系数）（OR=I．161，P=-0．000，95％CI：1．090～1．237）、碱性磷酸酶（OR=1．003，P=-0．023，95％CI：1．000～1．005）是复发再入院的独立影响因素。XGboost模型显示排名前六位的复发再人院的影响因素分别为高血压（重要度评分32分）、红细胞分布宽度（变异系数）（重要度评分20分）、直接胆红素（重要度评分19分）、住院天数（重要度评分18分）、肺部感染（重要度评分15分）、碱性磷酸酶（重要度评分14分）。ROC曲线分析显示，XGboost模型预测复发再人院的ROC下面积[0．792（95％CI：0．717～0．762）较多因素Logistic回归分析模型[0．739（95％CI：0．764～0．818）]提升了约5个百分点，且模型灵敏度（89．30％）、约登指数（0．444）均明显高于多因素Logistic回归分析模型（77．3％、0．405）。结论XGboost模型对缺血性脑卒中出院后90d内复发再人院Objective To explore the predictive efficacy of XGboost model in predicting risk of relapse and re-admission within 90 d in patients with ischemic stroke, and provide basis for early screening and prevention of high-risk population with ischemic stroke. Methods The clinical data of 6070 primary ischemic stroke patients admitted to our hospital from January 2007 to July 2017 were retrospectively collected. XGboost model and multivariate Logistic regression model were utilized to screen out the influencing factors of relapse and re-admission within 90 d in patients with ischemic stroke. A predictive model was set up. Receiver operating characteristic （ROC） curve was drawn and compared. Sensitivity, specificity and Youden index were calculated and compared to evaluate the prediction performance of XGboost model. Results During the observation period, a total of 520 patients with relapsed ischemic stroke were observed within a period of 90 d, and the incidence density was 8.57%. Multivariate Logistic regression analysis showed that length of first hospital stay, hypertension, pulmonary infection, neutrophil percentage, red blood cell distribution width （variable coefficient）, and alkaline phosphatase level were independent influencing factors for re-hospitalization within 90 d of ischemic stroke, （OR=1.016, P=-0.000, 95%CI： 1.008-1.025; OR=4.598, P=-0.000, 95%CI： 3.717-5.687; OR=1.452, P=-0.025, 95%CI： 1.048-2.012; OR=1.013, P=-0.006, 95%CI： 1.004-1.022; OR=1.161, P=-0.000, 95%CI： 1.090-1.237; OR=1.003, P=0.023, 95%CI： 1.000-1.005）. Analysis of importance of risk factors for re-admission of ischemic stroke using XGboost model showed that the top 6 factors were hypertension, red blood cell distribution width, direct bilirubin, length of hospital stay, pulmonary infection, and alkaline phosphatase, and the corresponding importance scores were 32, 20, 19, 18, 15 and 14, respectively. ROC curve analysis results indicated that the area under the ROC for re-admission for XGboost model was 0.792 （9

关 键 词：XGboost模型 多因素Logistic回归分析模型 预测模型 缺血性脑卒中 复发再入院:影响因素 

分 类 号：R743.3[医药卫生—神经病学与精神病学]