Department of Cardiac Surgery, Bristol Heart Institute, Translational Health Sciences, University of Bristol, UK.
National Institute for Health Research Bristol Biomedical Research Centre, University Hospitals Bristol and Weston NHS Foundation Trust and University of Bristol, Bristol, UK.
Eur J Cardiothorac Surg. 2024 Oct 1;66(4). doi: 10.1093/ejcts/ezae368.
A study of the performance of in-hospital/30-day mortality risk prediction models using an alternative machine learning algorithm (XGBoost) in adults undergoing cardiac surgery.
Retrospective analyses of prospectively routinely collected data on adult patients undergoing cardiac surgery in the UK from January 2012 to March 2019. Data were temporally split 70:30 into training and validation subsets. Independent mortality prediction models were created using sequential backward floating selection starting with 61 variables. Assessments of discrimination, calibration, and clinical utility of the resultant XGBoost model with 23 variables were then conducted.
A total of 224,318 adults underwent cardiac surgery during the study period with a 2.76% (N = 6,100) mortality. In the testing cohort, there was good discrimination (area under the receiver operator curve 0.846, F1 0.277) and calibration (especially in high-risk patients). Decision curve analysis showed XGBoost-23 had a net benefit till a threshold probability of 60%. The most important variables were the type of operation, age, creatinine clearance, urgency of the procedure and the New York Heart Association score.
Feature-selected XGBoost showed good discrimination, calibration and clinical benefit when predicting mortality post-cardiac surgery. Prospective external validation of a XGBoost-derived model performance is warranted.
使用替代机器学习算法（XGBoost）研究心脏手术后住院/30 天死亡率风险预测模型的性能。
回顾性分析了 2012 年 1 月至 2019 年 3 月期间在英国接受心脏手术的成年患者的前瞻性常规收集数据。数据按 70:30 的时间分割成训练和验证子集。使用 61 个变量的顺序后向浮动选择开始创建独立的死亡率预测模型。然后对具有 23 个变量的 XGBoost 模型的区分度、校准和临床实用性进行评估。
在研究期间，共有 224318 名成年人接受了心脏手术，死亡率为 2.76%（N=6100）。在测试队列中，该模型具有良好的区分度（接收者操作特征曲线下面积 0.846，F1 0.277）和校准（尤其是在高危患者中）。决策曲线分析显示，XGBoost-23 直到概率阈值为 60%才有净收益。最重要的变量是手术类型、年龄、肌酐清除率、手术的紧急程度和纽约心脏协会评分。
在预测心脏手术后的死亡率时，经过特征选择的 XGBoost 显示出良好的区分度、校准和临床获益。需要对 XGBoost 衍生模型的性能进行前瞻性外部验证。
