无创性预测乙肝肝硬化门脉高压性胃病的Logistic回归模型

Logistic regression model of noninvasive prediction for portal hypertensive gastropathy in patients with hepatitis B associated cirrhosis

目的 探讨乙型肝炎肝硬化患者中门脉高压性胃病（PHG）发生的危险因素,建立无创性预测PHG的Logistic回归模型.方法 回顾性分析2012年3月至2014年3月中山大学附属第三医院诊治的234例乙肝肝硬化患者的临床资料,把是否发生PHG作为应变量,对各自变量进行单因素筛选分析,将有意义的各无创性自变量进一步行多因素非条件Logistic回归分析,建立Logistic回归 模型,计算各因素的优势比（0R）,并应用受试者工作特征（ROC）曲线评价该模型判断PHG的准确度、灵敏度和特异度.结果 经单因素Logistic回归分析,筛选出肝功能失代偿、白蛋白（ALB）、胆红素（TB）、凝血酶原时间（PT）、血小板（PLT）、白细胞（WBC）、门静脉管径、脾指数、脾门静脉内径、内径比、PLT脾脏体积比、食管静脉曲张（EV）及胃底静脉曲张（GV）对PHG发生的影响差异有统计学意义（P＜0.05）.多因素分析显示肝功能失代偿（X1）、TB（X2）、PLT（X3）和脾门静脉内径（X4）是PHG发生的危险因素,所建立的回归模型为Logit P=-2.667＋2.186X1-2.167X2＋0.725X3＋0.976X4.该模型对门脉高压性胃病综合判断准确率为79.1％,灵敏度77.2％,特异度80.8％.结论 肝功能失代偿、TB、PLT和脾门静脉内径是PHG发生的危险因素,由无创性各指标建立的回归模型为Logit P=-2.667 ＋2.186X1-2.167X2 ＋0.725X3 ＋0.976X4。

Objective To explore the risk factors of portal hypertensive gastropathy （PHG） in patients with hepatitis B associated cirrhosis and establish a Logistic regression model of noninvasive prediction.Methods The clinical data of 234 hospitalized patients with hepatitis B associated cirrhosis from March 2012 to March 2014 were analyzed retrospectively.The dependent variable was the occurrence of PHG while the independent variables were screened by binary Logistic analysis.Multivariate Logistic regression was used for further analysis of significant noninvasive independent variables.Logistic regression model was established and odds ratio was calculated for each factor.The accuracy,sensitivity and specificity of model were evaluated by the curve of receiver operating characteristic （ROC）.Results According to univariate Logistic regression,the risk factors included hepatic dysfunction,albumin （ALB）,bilirubin （TB）,prothrombin time （PT）,platelet （PLT）,white blood cell （WBC）,portal vein diameter,spleen index,splenic vein diameter,diameter ratio,PLT to spleen volume ratio,esophageal varices （EV） and gastric varices （GV）.Multivariate analysis showed that hepatic dysfunction （X1）,TB （X2）,PLT （X3） and splenic vein diameter （X4） were the major occurring factors for PHG.The established regression model was Logit P =-2.667 ＋ 2.186X1-2.167X2 ＋ 0.725X3 ＋ 0.976X4.The accuracy of model for PHG was 79.1% with a sensitivity of 77.2% and a specificity of 80.8%.Conclusion Hepatic dysfunction,TB,PLT and splenic vein diameter are risk factors for PHG and the noninvasive predicted Logistic regression model was Logit P=-2.667 ＋2.186X1-2.167X2 ＋0.725X3 ＋0.976X4.