Guo Kai, Fu Xiaoyan, Zhang Huimin, Wang Mengjian, Hong Songlin, Ma Shuxuan
Department of Transfusion Medicine, Beijing Children's Hospital, Capital Medical University, National Center for Children's Health, Beijing, China.
Fane Data Technology Corporation, Tianjin, China.
Transl Pediatr. 2021 Jan;10(1):33-43. doi: 10.21037/tp-20-238.
Postoperative blood coagulation assessment of children with congenital heart disease (CHD) has been developed using a conventional statistical approach. In this study, the machine learning (ML) was used to predict postoperative blood coagulation function of children with CHD, and assess an array of ML models.
This was a retrospective and data mining study. Based on the samples of 1,690 children with CHD, and screening data based on demographic characteristics, conventional coagulation tests (CCTs) and complete blood count (CBC), with a precise data selection process, and the support of data mining and ML algorithms including Decision tree, Naive Bayes, Support Vector Machine (SVM), Adaptive Boost (AdaBoost) and Random Forest model, and explored the best prediction models of postoperative blood coagulation function for children with CHD by models performance measured in the area under the receiver operating characteristic (ROC) curve (AUC), calibration or Lift curves, and further verified the reliability of the models with statistical tests.
In primary objective prediction, as decision tree, Naive Bayes, SVM, the AUC of our prediction algorithm was 0.81, 0.82, 0.82, respectively. The accuracy rate of the overall forecast has reached more than 75%. Subsequently, we furtherly build improved models. Among them, the true positive rate of the AdaBoost, Random Forest and SVM prediction models reached more than 80% in the ROC curve. These overall accuracy rate indicated a good classification model. Combined calibration curves and Lift curves, the better fit is the SVM model, which predicted postoperative abnormal coagulation, Lift =2.2, postoperative normal coagulation, Lift =1.8. The statistical results furtherly proved the reliability of ML models. The age, sex, mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), white blood cell count (WBC) and platelet count (PLT) were the key features for predicting the postoperative blood coagulation state of children with CHD.
ML technology and data mining algorithms may be used for outcome prediction in children with CHD for postoperative blood coagulation state based on the bulk of clinical data, especially CBC indictors from the real world.
先天性心脏病（CHD）患儿术后凝血功能评估一直采用传统统计方法。本研究利用机器学习（ML）预测CHD患儿术后凝血功能，并评估一系列ML模型。
这是一项回顾性数据挖掘研究。基于1690例CHD患儿的样本，根据人口统计学特征、传统凝血试验（CCT）和全血细胞计数（CBC）进行数据筛选，通过精确的数据选择过程，并在决策树、朴素贝叶斯、支持向量机（SVM）、自适应增强（AdaBoost）和随机森林模型等数据挖掘和ML算法的支持下，通过在受试者操作特征（ROC）曲线下面积（AUC）、校准或提升曲线中测量的模型性能，探索CHD患儿术后凝血功能的最佳预测模型，并通过统计检验进一步验证模型的可靠性。
在主要目标预测中，作为决策树、朴素贝叶斯、SVM，我们预测算法的AUC分别为0.81、0.82、0.82。总体预测准确率达到75%以上。随后，我们进一步构建了改进模型。其中，AdaBoost、随机森林和SVM预测模型在ROC曲线中的真阳性率达到80%以上。这些总体准确率表明是一个良好的分类模型。结合校准曲线和提升曲线，拟合较好的是SVM模型，其预测术后凝血异常时，提升度=2.2，术后凝血正常时，提升度=1.8。统计结果进一步证明了ML模型的可靠性。年龄、性别、平均红细胞体积（MCV）、平均红细胞血红蛋白含量（MCH）、平均红细胞血红蛋白浓度（MCHC）、白细胞计数（WBC）和血小板计数（PLT）是预测CHD患儿术后凝血状态的关键特征。
基于大量临床数据，尤其是来自现实世界的CBC指标，ML技术和数据挖掘算法可用于预测CHD患儿术后凝血状态。
