Du Xinwei, Wang Hao, Wang Shunmin, He Yi, Zheng Jinghao, Zhang Haibo, Hao Zedong, Chen Yiwei, Xu Zhiwei, Lu Zhaohui
Department of Cardiothoracic Surgery, Shanghai Children's Medical Center, School of Medicine, Shanghai Jiaotong University, 200127 Shanghai, China.
Information Center, Shanghai Children's Medical Center, School of Medicine, Shanghai Jiaotong University, 200127 Shanghai, China.
Rev Cardiovasc Med. 2022 Nov 3;23(11):376. doi: 10.31083/j.rcm2311376. eCollection 2022 Nov.
A machine learning model was developed to estimate the in-hospital mortality risk after congenital heart disease (CHD) surgery in pediatric patient.
Patients with CHD who underwent surgery were included in the study. A Extreme Gradient Boosting (XGBoost) model was constructed based onsurgical risk stratification and preoperative variables to predict the risk of in-hospital mortality. We compared the predictive value of the XGBoost model with Risk Adjustment in Congenital Heart Surgery-1 (RACHS-1) and Society of Thoracic Surgery-European Association for Cardiothoracic Surgery (STS-EACTS) categories.
A total of 24,685 patients underwent CHD surgery and 595 (2.4%) died in hospital. The area under curve (AUC) of the STS-EACTS and RACHS-1 risk stratification scores were 0.748 [95% Confidence Interval (CI): 0.707-0.789, 0.001] and 0.677 (95% CI: 0.627-0.728, 0.001), respectively. Our XGBoost model yielded the best AUC (0.887, 95% CI: 0.866-0.907, 0.001), and sensitivity and specificity were 0.785 and 0.824, respectively. The top 10 variables that contribute most to the predictive performance of the machine learning model were saturation of pulse oxygen categories, risk categories, age, preoperative mechanical ventilation, atrial shunt, pulmonary insufficiency, ventricular shunt, left atrial dimension, a history of cardiac surgery, numbers of defects.
The XGBoost model was more accurate than RACHS-1 and STS-EACTS in predicting in-hospital mortality after CHD surgery in China.
开发了一种机器学习模型，用于估计儿科患者先天性心脏病（CHD）手术后的院内死亡风险。
纳入接受CHD手术的患者进行研究。基于手术风险分层和术前变量构建了极端梯度提升（XGBoost）模型，以预测院内死亡风险。我们将XGBoost模型的预测价值与先天性心脏病手术风险调整-1（RACHS-1）和胸外科医师协会-欧洲心胸外科学会（STS-EACTS）分类进行了比较。
共有24685例患者接受了CHD手术，595例（2.4%）在医院死亡。STS-EACTS和RACHS-1风险分层评分的曲线下面积（AUC）分别为0.748[95%置信区间（CI）：0.707-0.789，P<0.001]和0.677（95%CI：0.627-0.728，P<0.001）。我们的XGBoost模型获得了最佳AUC（0.887，95%CI：0.866-0.907，P<0.001），敏感性和特异性分别为0.785和0.824。对机器学习模型预测性能贡献最大的前10个变量是脉搏血氧饱和度类别、风险类别、年龄、术前机械通气、心房分流、肺功能不全、心室分流、左心房内径、心脏手术史、缺陷数量。
在中国，XGBoost模型在预测CHD手术后的院内死亡方面比RACHS-1和STS-EACTS更准确。
