摘要
目的探讨机器学习对于经颈静脉肝内门体分流术(TIPS)的肝硬化患者预后的临床预测价值。方法本研究共纳入山东大学附属山东省立医院2016年1月至2019年12月收治的53例肝硬化患者,分别收集术前及术后临床变量68项,以术后出血、肝性脑病、肝病相关死亡、分流道失功能分别作为独立结局。使用逻辑回归筛选对结局有显著影响的临床变量,分别构建相应的支持向量机(SVM)模型,同时构建沙普利可加性特征解释方法(SHAP)模型进行解释分析。结果术后出血SVM模型,准确率0.75,召回率1.00,曲线下面积(AUC)=0.81;肝性脑病SVM模型,准确率0.75,召回率0.67,AUC=0.77;肝病相关死亡SVM模型,准确率0.88,召回率1.00,AUC=0.87;分流道失功能SVM模型,准确率0.94,召回率0.67,AUC=0.87。构建的四个模型中纳入变量SHAP值最高的依次为服用利尿剂、服用益生菌、术前门静脉压力值和终末期肝病模型(MELD)评分。结论机器学习在肝硬化TIPS术后不同临床结局的预测中有较好的实用价值,可辅助临床医生预测此类患者术后状况,早期进行有效干预。
Objective To investigate the clinical predictive value of machine learning in patients with cirrhosis undergoing transjugular intrahepatic portal shunt(TIPS).Methods A total of 53 cirrhosis patients admitted to Shandong Provincial Hospital Affiliated to Shandong University from January 2016 to December 2019 were included in this study.Sixty-eight preoperative and postoperative clinical variables were collected,and postoperative bleeding,hepatic encephalopathy,liver disease-related death and shunt disfunction were used as independent outcomes,respectively.Logistic regression was used to select clinical variables that had significant influence on the outcome.Corresponding support vector machine(SVM)models were constructed and Shapley Additive explanation(SHAP)model was constructed for interpretation and analysis.Results The accuracy,recall rate and area under the curve(AUC)of the SVM model for postoperative bleeding were 0.75,1.00 and 0.81,respectively.The three parameters for hepatic encephalopathy were 0.75,0.67 and 0.77,respectively.The three parameters for liver disease-related death were 0.88,1.00 and 0.87,respectively.The three parameters for shunt disfunction were 0.94,0.67 and 0.87,respectively.Among the four constructed models,the highest SHAP values of included variables were diuretics,probiotics,preoperative portal venous pressure and end-stage liver disease model(MELD)score.Conclusion Machine learning has good practical value in predicting different clinical outcomes after TIPS for liver cirrhosis patients,which can assist clinicians to predict the postoperative status of such patients and carry out effective intervention at an early stage.
作者
黄婷萍
王广川
黄广军
张春清
Huang Tingping;Wang Guangchuan;Huang Guangjun;Zhang Chunqing(Department of Gastroenterology,Shandong Provincial Hospital,Cheeloo College of Medicine,Shandong University,Jinan 250021,China;Department of Gastroenterology,Shandong Provincial Hospital Affiliated to Shandong First Medical University,Jinan 250021,China)
出处
《中华消化病与影像杂志（电子版）》
2022年第1期4-10,共7页
Chinese Journal of Digestion and Medical Imageology(Electronic Edition)
基金
国家自然科学基金委员会(课题编号:81970533)。
关键词
肝硬化
经颈静脉肝内门体分流术
机器学习
临床结局
Liver cirrhosis
Transjugular intrahepatic portal shunt
Machine learning
Clinical outcome
