机器学习算法在心脏手术死亡风险预测中的效用
本研究评估机器学习算法(XGBoost)在成人心脏手术中预测手术死亡风险的效用。纳入2011至2017年单中心11,190例手术,主要结局为手术死亡。XGBoost在验证队列中各项模型性能指标均较STS PROM有改善,但改善幅度有限,需在更大队列中进一步验证。
要点
- XGBoost在验证队列中C-index为0.808,优于STS PROM的0.795。
- XGBoost平均精度0.221,高于STS PROM的0.180。
- 模型性能改善幅度有限,需在更大队列中验证。
核心结论
- XGBoost等机器学习算法在心脏手术预测分析中具有前景。
- 本研究中模型性能改善幅度有限,需在更大队列中进一步验证。
研究设计与样本
- 单中心回顾性研究,纳入2011至2017年成人心脏手术11,190例。
- 使用10折交叉验证与1000次重复自举法开发并评估XGBoost模型。
主要发现
- XGBoost与STS PROM预测风险中度相关(r=0.652),在手术死亡患者中弱相关(r=0.473)。
- 验证队列中XGBoost平均精度0.221 vs STS PROM 0.180。
- 验证队列中XGBoost C-index 0.808 vs STS PROM 0.795。
- 验证队列中XGBoost校准平均观察与预期死亡率比0.993 vs STS PROM 0.956。
- 在3%-10%风险判别阈值下,XGBoost准确率较STS PROM提高1%-3%,F1分数0.281 vs 0.230。
临床怎么用
- 机器学习模型可作为心脏手术死亡风险预测的辅助工具,但当前改善幅度有限,不宜完全替代STS PROM。
局限性
- 单中心研究,结果外推需谨慎。
- 模型性能改善幅度有限,需在更大队列中验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: This study evaluated the predictive utility of a machine learning algorithm in estimating operative mortality risk in cardiac surgery. METHODS: Index adult cardiac operations performed between 2011 and 2017 at a single institution were included. The primary outcome was operative mortality. Extreme gradient boosting (XGBoost) models were developed and evaluated using 10-fold cross-validation with 1000-replication bootstrapping. Model performance was assessed using multiple measures including precision, recall, calibration plots, area under the receiver-operating characteristic curve (C-index), accuracy, and F1 score. RESULTS: A total of 11,190 patients were included (7048 isolated coronary artery bypass grafting [CABG], 2507 isolated valves, and 1635 CABG plus valves). The Society of Thoracic Surgeons Predicted Risk of Mortality (STS PROM) was 3.2% ± 5.0%. Actual operative mortality was 2.8%. There was moderate correlation (r = 0.652) in predicted risk between XGBoost and STS PROM for the overall cohort and weak correlation (r = 0.473) in predicted risk between the models specifically in patients with operative mortality. XGBoost demonstrated improvements in all measures of model performance when compared with the STS PROM in the validation cohorts: mean average precision (0.221 XGBoost vs 0.180 STS PROM), C-index (0.808 XGBoost vs 0.795 STS PROM), calibration (mean observed-to-expected mortality: XGBoost 0.993 vs 0.956 STS PROM), accuracy (1%-3% improvement across discriminatory thresholds of 3%-10% risk), and F1 score (0.281 XGBoost vs 0.230 STS PROM). CONCLUSIONS: Machine learning algorithms such as XGBoost have promise in predictive analytics in cardiac surgery. The modest improvements in model performance demonstrated in the current study warrant further validation in larger cohorts of patients.
引用
- Kilic A, Goyal A, Miller JK, et al. Predictive Utility of a Machine Learning Algorithm in Estimating Mortality Risk in Cardiac Surgery. Ann Thorac Surg. 2019. PMID: 31706872. doi:10.1016/j.athoracsur.2019.09.049
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。