Toward Dynamic Risk Prediction of Outcomes After Coronary Artery Bypass Graft: Improving Risk Prediction With Intraoperative Events Using Gradient Boosting.
Toward Dynamic Risk Prediction of Outcomes After Coronary Artery Bypass Graft: Improving Risk Prediction With Intraoperative Events Using Gradient Boosting.
复制标题
Dynamic risk prediction of outcomes after coronary artery bypass grafting: using gradient boosting techniques to improve risk prediction using intraoperative events.
DOI：
10.1161/circoutcomes.120.007363
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Krumholz HM
中科院分区：
文献类型：
--
作者：
Mori M;Durant TJS;Huang C;Mortazavi BJ;Coppi A;Jean RA;Geirsson A;Schulz WL;Krumholz HM
术中数据可以改善预测术后事件的模型。我们评估了将术中变量纳入现有术前模型对冠状动脉旁路移植术（CABG）模型预测性能的影响。
我们利用全国胸外科医师协会成人心脏手术数据库，分析了 2014-2016 年间在 1,083 个中心实施的 378,572 例孤立的 CABG 病例。结果包括手术死亡率、5种术后并发症以及所有事件的综合表示。我们通过逻辑回归（LR）或极端梯度提升（XGBoost）来拟合模型。在每种建模方法中，我们只使用术前变量、术中变量或术前+术中变量。我们用 3 组变量、2 种变量选择方法、2 种建模方法和 7 种结果的独特组合建立了 84 个模型。每个模型都在 70:30 的分层随机抽样中进行了 20 次迭代测试，分为开发/测试样本。在测试数据集上使用 c 统计量、精确度-召回曲线 (AUPRC) 和校准指标（包括 Brier 评分）对模型性能进行了评估。
患者平均年龄为 65.3 岁，24.7% 为女性。手术死亡率（不包括术中死亡）为 1.9%。在所有结果中，与仅考虑术前或术中变量的模型相比，考虑术前+术中变量的模型明显提高了 Brier 评分和 AUPRC。与带或不带变量选择的 LR 模型相比，不带外部变量选择的 XGBoost 在 7 个结果中的 4 个结果（死亡率、肾衰竭、通气时间延长和综合结果）中具有最佳的 c 统计量、Brier 评分和 AUPRC 值。根据校准图，死亡率风险再分层显示，LR 模型低估了 11,114 例患者（9.8%）的风险，高估了 12,005 例患者（10.6%）的风险。相比之下，XGBoost 模型低估了 7,218 例患者（6.4%）的风险，高估了 0 例患者（0%）的风险。
在孤立的 CABG 中，在术前变量的基础上增加术中变量可改善对所有 7 种结果的预测。基于 XGBoost 的风险模型可以更好地预测不良事件，从而指导临床治疗。
Intraoperative data may improve models predicting postoperative events. We evaluated the effect of incorporating intraoperative variables to the existing preoperative model on the predictive performance of the model for coronary artery bypass graft (CABG). We analyzed 378,572 isolated CABG cases performed across 1,083 centers, using the national Society of Thoracic Surgeons Adult Cardiac Surgery Database between 2014–2016. Outcomes were operative mortality, 5 postoperative complications, and composite representation of all events. We fitted models by logistic regression (LR) or extreme gradient boosting (XGBoost). For each modeling approach, we used preoperative only, intraoperative only, or pre+intraoperative variables. We developed 84 models with unique combinations of the 3 variable sets, 2 variable selection methods, 2 modeling approaches, and 7 outcomes. Each model was tested in 20 iterations of 70:30 stratified random splitting into development/testing samples. Model performances were evaluated on the testing dataset using the c-statistic, precision-recall curve (AUPRC), and calibration metrics, including the Brier score. The mean patient age was 65.3 years, and 24.7% were women. Operative mortality, excluding intraoperative death, occurred in 1.9%. In all outcomes, models that considered pre+intraoperative variables demonstrated significantly improved Brier score and AUPRC compared with models considering pre or intraoperative variables alone. XGBoost without external variable selection had the best c-statistics, Brier score, and AUPRC values in 4 of the 7 outcomes (mortality, renal failure, prolonged ventilation, and composite) compared with LR models with or without variable selection. Based on the calibration plots, risk re-stratification for mortality showed that the LR model underestimated the risk in 11,114 patients (9.8%) and overestimated in 12,005 patients (10.6%). In contrast, XGBoost model underestimated the risk in 7,218 patients (6.4%) and overestimated in 0 patients (0%). In isolated CABG, adding intraoperative variables to preoperative variables resulted in improved predictions of all 7 outcomes. Risk models based on XGBoost may provide a better prediction of adverse events to guide clinical care.