Center for Outcomes Research and Evaluation, Yale New Haven Hospital, CT (M.M., T.J.S.D., C.H., B.J.M., R.A.J, A.C., W.L.S., H.M.K).
Division of Cardiac Surgery, Department of Surgery (M.M., A.G.), Yale University School of Medicine, New Haven, CT.
Circ Cardiovasc Qual Outcomes. 2021 Jun;14(6):e007363. doi: 10.1161/CIRCOUTCOMES.120.007363. Epub 2021 Jun 3.
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.
We analyzed 378 572 isolated coronary artery bypass graft cases performed across 1083 centers, using the national Society of Thoracic Surgeons Adult Cardiac Surgery Database between 2014 and 2016. Outcomes were operative mortality, 5 postoperative complications, and composite representation of all events. We fitted models by logistic regression 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, area under the precision-recall curve, 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 area under the precision-recall curve compared with models considering pre or intraoperative variables alone. XGBoost without external variable selection had the best C statistics, Brier score, and area under the precision-recall curve values in 4 of the 7 outcomes (mortality, renal failure, prolonged ventilation, and composite) compared with logistic regression models with or without variable selection. Based on the calibration plots, risk restratification for mortality showed that the logistic regression model underestimated the risk in 11 114 patients (9.8%) and overestimated in 12 005 patients (10.6%). In contrast, the XGBoost model underestimated the risk in 7218 patients (6.4%) and overestimated in 0 patients (0%).
In isolated coronary artery bypass graft, 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.
术中数据可能会提高预测术后事件的模型的准确性。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模型预测性能的影响。
我们分析了 2014 年至 2016 年间，全国胸外科医师学会成人心脏手术数据库中 1083 个中心进行的 378572 例独立冠状动脉旁路移植术病例。结果为手术死亡率、5 种术后并发症和所有事件的综合表现。我们使用逻辑回归或极端梯度提升（XGBoost）进行模型拟合。对于每种建模方法，我们使用术前变量、术中变量或术前+术中变量。我们使用 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，开发了 84 个模型。每个模型在 20 次 70:30 分层随机拆分到开发/测试样本中进行测试。使用测试数据集上的 C 统计量、精度-召回曲线下面积和校准指标（包括 Brier 评分）评估模型性能。
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+术中变量的模型的 Brier 评分和精度-召回曲线下面积明显提高。在 7 种结果中的 4 种（死亡率、肾衰竭、延长通气和复合）中，不进行外部变量选择的 XGBoost 具有最佳的 C 统计量、Brier 评分和精度-召回曲线下面积值，而具有或不具有变量选择的逻辑回归模型。基于校准图，死亡率的风险再分层表明，逻辑回归模型低估了 11114 名患者（9.8%）的风险，高估了 12005 名患者（10.6%）的风险。相比之下，XGBoost 模型低估了 7218 名患者（6.4%）的风险，而没有高估任何患者（0%）的风险。
在独立冠状动脉旁路移植术中，将术中变量添加到术前变量中可提高对所有 7 种结果的预测能力。基于 XGBoost 的风险模型可能会更好地预测不良事件，以指导临床护理。
