Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension.
Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension.
复制标题
DOI：
10.1016/j.jss.2020.05.007
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Bihorac A
中科院分区：
文献类型：
--
作者：
Datta S;Loftus TJ;Ruppert MM;Giordano C;Upchurch GR Jr;Rashidi P;Ozrazgat-Baslanti T;Bihorac A
预测术后并发症的模型往往忽略了重要的术中事件和生理变化。本研究验证了这样一个假设：与术前数据相比，同时使用术前和术中数据输入数据可以提高预测术后并发症的准确性、辨别力和精确度。这项回顾性队列分析包括43,943名成年人，在5年期间在一家机构接受了52,529例住院手术。经过验证的mysurgical risk平台中的随机森林机器学习模型利用电子健康记录数据和患者社区特征，对住院期间发生的七种术后并发症和死亡率进行了患者层面的预测。对于每个结果，单独使用术前数据训练一个模型；一个模型同时训练术前和术中数据。比较模型的准确率、鉴别率（表示为AUROC：接收者工作特征曲线下面积）、精密度（表示为AUPRC：精密度-召回率曲线下面积）和重分类指标。结合术前和术中数据的机器学习模型在预测所有7种术后并发症（重症监护病房住院时间>48小时，机械通气>48小时，包括谵妄、心血管并发症、急性肾损伤、静脉血栓栓塞和伤口并发症在内的神经系统并发症）和院内死亡率(准确性：88%对77%，AUROC: 0.93对0.87,AUPRC: 0.21对0.15)。并发症的总体重分类改善为2.4-10.0%，住院死亡率改善为11.2%。结合术前和术中数据显著提高了机器学习模型预测术后并发症和死亡率的准确性、辨别力和精确度。
Models that predict postoperative complications often ignore important intraoperative events and physiological changes. This study tested the hypothesis that accuracy, discrimination, and precision in predicting postoperative complications would improve when using both preoperative and intraoperative data input data compared with preoperative data alone. This retrospective cohort analysis included 43,943 adults undergoing 52,529 inpatient surgeries at a single institution during a five-year period. Random forest machine learning models in the validated MySurgeryRisk platform made patient-level predictions for seven postoperative complications and mortality occurring during hospital admission using electronic health record data and patient neighborhood characteristics. For each outcome, one model trained with preoperative data alone; one model trained with both preoperative and intraoperative data. Models were compared by accuracy, discrimination (expressed as AUROC: area under the receiver operating characteristic curve), precision (expressed as AUPRC: area under the precision-recall curve), and reclassification indices. Machine learning models incorporating both preoperative and intraoperative data had greater accuracy, discrimination, and precision than models using preoperative data alone for predicting all seven postoperative complications (intensive care unit length of stay >48 hours, mechanical ventilation >48 hours, neurological complications including delirium, cardiovascular complications, acute kidney injury, venous thromboembolism, and wound complications) and in-hospital mortality (accuracy: 88% vs. 77%, AUROC: 0.93 vs. 0.87, AUPRC: 0.21 vs. 0.15). Overall reclassification improvement was 2.4–10.0% for complications and 11.2% for in-hospital mortality. Incorporating both preoperative and intraoperative data significantly increased the accuracy, discrimination, and precision of machine learning models predicting postoperative complications and mortality.
登录
查看更多内容
影响因子：
2
作者：
Pencina, Michael J.;D'Agostino, Ralph B., Sr.;Steyerberg, Ewout W.
通讯作者：
Steyerberg, Ewout W.
影响因子：
9
作者：
Chiew CJ;Liu N;Wong TH;Sim YE;Abdullah HR
通讯作者：
Abdullah HR
DOI：
10.1093/jee/39.2.269
发表时间：
1945-01-01
期刊：
BIOMETRICS BULLETIN
影响因子：
--
作者：
WILCOXON, F
通讯作者：
WILCOXON, F
影响因子：
3.8
作者：
Chiu, Alexander S.;Jean, Raymond A.;Pei, Kevin Y.
通讯作者：
Pei, Kevin Y.
影响因子：
3.8
作者：
Brennan, Meghan;Puri, Sahil;Bihorac, Azra
通讯作者：
Bihorac, Azra