Application of decision tree model in predicting the risk of hypothermia after cardiopulmonary bypass in children with congenital heart disease / 中华实用儿科临床杂志

ABSTRACT

Objective:To analyze the influential factors of hypothermia in congenital heart disease (CHD) after cardiopulmonary bypass (CPB) rewarming using the decision tree model, thus providing theoretical basis for medical staff.Methods:A total of 711 CHD children who underwent surgery in the Shanghai Children′s Medical Center from January 1, 2019 to April 30, 2019 were retrospectively analyzed.A decision tree model was established to predict the risk factors for hypothermia in CHD children following CPB.Results:The decision tree model showed that CPB program, preoperative nutrition score and body surface area were the high-risk factors for hypothermia in CHD children after CPB rewarming.The accuracy, sensitivity, specificity of the decision tree model were 86.45%, 77.14% and 90.97%, respectively, and the area under the receiver operating characteristic curve was 0.851(95% CI: 0.798-0.904). Conclusions:Decision tree model has a high application value in predicting hypothermia in CHD children following CPB.It contributes to identify the influential factors of hypothermia, and provides references for performing preventive treatment and nursing measures to control the risk of hypothermia.