Zhang Ningjie, Fan Kexin, Ji Hongwen, Ma Xianjun, Wu Jingyi, Huang Yuanshuai, Wang Xinhua, Gui Rong, Chen Bingyu, Zhang Hui, Zhang Zugui, Zhang Xiufeng, Gong Zheng, Wang Yongjun
Department of Blood Transfusion, The Second Xiangya Hospital, Central South University, Changsha, China.
Department of Laboratory Medicine, The Second Xiangya Hospital, Central South University, Changsha, China.
Front Cardiovasc Med. 2023 Jun 13;10:1050698. doi: 10.3389/fcvm.2023.1050698. eCollection 2023.
Selecting features related to postoperative infection following cardiac surgery was highly valuable for effective intervention. We used machine learning methods to identify critical perioperative infection-related variables after mitral valve surgery and construct a prediction model.
Participants comprised 1223 patients who underwent cardiac valvular surgery at eight large centers in China. The ninety-one demographic and perioperative parameters were collected. Random forest (RF) and least absolute shrinkage and selection operator (LASSO) techniques were used to identify postoperative infection-related variables; the Venn diagram determined overlapping variables. The following ML methods: random forest (RF), extreme gradient boosting (XGBoost), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), AdaBoost, Naive Bayesian (NB), Logistic Regression (LogicR), Neural Networks (nnet) and artificial neural network (ANN) were developed to construct the models. We constructed receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) was calculated to evaluate model performance.
We identified 47 and 35 variables with RF and LASSO, respectively. Twenty-one overlapping variables were finally selected for model construction: age, weight, hospital stay, total red blood cell (RBC) and total fresh frozen plasma (FFP) transfusions, New York Heart Association (NYHA) class, preoperative creatinine, left ventricular ejection fraction (LVEF), RBC count, platelet (PLT) count, prothrombin time, intraoperative autologous blood, total output, total input, aortic cross-clamp (ACC) time, postoperative white blood cell (WBC) count, aspartate aminotransferase (AST), alanine aminotransferase (ALT), PLT count, hemoglobin (Hb), and LVEF. The prediction models for infection after mitral valve surgery were established based on these variables, and they all showed excellent discrimination performance in the test set (AUC > 0.79).
Key features selected by machine learning methods can accurately predict infection after mitral valve surgery, guiding physicians in taking appropriate preventive measures and diminishing the infection risk.
筛选与心脏手术后感染相关的特征对于有效干预具有重要价值。我们使用机器学习方法来识别二尖瓣置换术后围手术期感染的关键相关变量，并构建预测模型。
研究对象为在中国八个大型中心接受心脏瓣膜手术的1223例患者。收集了91项人口统计学和围手术期参数。采用随机森林（RF）和最小绝对收缩与选择算子（LASSO）技术识别术后感染相关变量；通过维恩图确定重叠变量。采用以下机器学习方法：随机森林（RF）、极限梯度提升（XGBoost）、支持向量机（SVM）、梯度提升决策树（GBDT）、AdaBoost、朴素贝叶斯（NB）、逻辑回归（LogicR）、神经网络（nnet）和人工神经网络（ANN）构建模型。绘制受试者工作特征（ROC）曲线并计算曲线下面积（AUC）以评估模型性能。
分别通过RF和LASSO识别出47个和35个变量。最终选择21个重叠变量用于模型构建：年龄、体重、住院时间、总红细胞（RBC）和新鲜冰冻血浆（FFP）输注总量、纽约心脏协会（NYHA）分级、术前肌酐、左心室射血分数（LVEF）、RBC计数、血小板（PLT）计数、凝血酶原时间、术中自体血、总输出量、总输入量、主动脉阻断（ACC）时间、术后白细胞（WBC）计数、天冬氨酸转氨酶（AST）、丙氨酸转氨酶（ALT）、PLT计数、血红蛋白（Hb）和LVEF。基于这些变量建立了二尖瓣置换术后感染的预测模型，在测试集中均显示出良好的区分性能（AUC>0.79）。
通过机器学习方法选择的关键特征能够准确预测二尖瓣置换术后感染，指导医生采取适当的预防措施，降低感染风险。
