文献速递冠心病外科瓣膜外科主动脉外科

开发机器学习模型预测心脏手术后结局与费用

Development of a Machine Learning Model to Predict Outcomes and Cost After Cardiac Surgery.
PubMed 文献 · Ann Thorac Surg · 2022-07-30

本研究利用本机构4874例心脏手术患者的胸外科医师协会注册数据,按80%训练、20%测试划分,采用极端梯度提升决策树算法预测手术死亡率、主要并发症或死亡及高住院费用,并在有风险评分的指标手术病例中验证后应用于非指标病例。

要点

  • 极端梯度提升算法可预测心脏手术后死亡率、主要并发症及高费用。
  • 术前肌酐、全血细胞计数、身高体重、心室功能及肝功能障碍为所有结局的重要预测因素。
  • 在非指标心脏手术中,模型对死亡率的AUC-PR为0.15(95%CI 0.05-0.32),对主要并发症或死亡为0.59(95%CI 0.51-0.68)。

核心结论

  • 极端梯度提升机器学习算法可预测心脏手术后死亡率、主要并发症和高费用,包括尚无成熟风险模型的手术。
  • 这些机器学习算法可能改进多种手术后的风险预测。

研究设计与样本

  • 研究纳入本机构4874例接受心脏手术患者的胸外科医师协会注册数据,其中56%为冠状动脉旁路移植术、42%为瓣膜手术、19%为主动脉手术。
  • 数据按80%训练集和20%测试集划分,训练极端梯度提升决策树机器学习算法预测手术死亡率、主要并发症或死亡、以及医疗保险异常高住院费用。
  • 算法性能采用准确率、F1分数和精确率-召回率曲线下面积(AUC-PR)评估。
  • 机器学习算法在有胸外科医师协会死亡率和主要并发症风险评分的指标手术病例中验证,并与逻辑回归比较,随后应用于非指标病例。

主要发现

  • 包含25个输入参数的机器学习算法预测手术死亡率:准确率95%、F1 0.31、AUC-PR 0.21。
  • 预测主要并发症或死亡:准确率71%、F1 0.47、AUC-PR 0.47。
  • 预测高费用:准确率84%、F1 0.62、AUC-PR 0.65。
  • 术前肌酐、全血细胞计数、患者身高和体重、心室功能及肝功能障碍是所有结局的重要预测因素。
  • 在非指标心脏手术患者中,机器学习模型对死亡率的AUC-PR为0.15(95%CI 0.05-0.32),对主要并发症或死亡的AUC-PR为0.59(95%CI 0.51-0.68)。

局限性

  • 原文未报告局限性。

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: Machine learning (ML) algorithms may enhance outcomes prediction and help guide clinical decision making. This study aimed to develop and validate a ML model that predicts postoperative outcomes and costs after cardiac surgery. METHODS: The Society of Thoracic Surgeons registry data from 4874 patients who underwent cardiac surgery (56% coronary artery bypass grafting, 42% valve surgery, 19% aortic surgery) at our institution were divided into training (80%) and testing (20%) datasets. The Extreme Gradient Boosting decision-tree ML algorithms were trained to predict three outcomes: operative mortality, major morbidity or mortality, and Medicare outlier high hospitalization cost. Algorithm performance was determined using accuracy, F1 score, and area under the precision-recall curve (AUC-PR). The ML algorithms were validated in index surgery cases with The Society of Thoracic Surgeons risk scores for mortality and major morbidities and with logistic regression and were then applied to nonindex cases. RESULTS: The ML algorithms with 25 input parameters predicted operative mortality (accuracy 95%; F1 0.31; AUC-PR 0.21), major morbidity or mortality (accuracy 71%, F1 0.47; AUC-PR 0.47), and high cost (accuracy 84%; F1 0.62; AUC-PR 0.65). Preoperative creatinine, complete blood count, patient height and weight, ventricular function, and liver dysfunction were important predictors for all outcomes. For patients undergoing nonindex cardiac operations, the ML model achieved an AUC-PR of 0.15 (95% CI, 0.05-0.32) for mortality and 0.59 (95% CI, 0.51-0.68) for major morbidity or mortality. CONCLUSIONS: The extreme gradient boosting ML algorithms can predict mortality, major morbidity, and high cost after cardiac surgery, including operations without established risk models. These ML algorithms may refine risk prediction after cardiac surgery for a wide range of procedures.

来源:Ann Thorac Surg,查看原文。版权归原作者所有。

引用

  1. Zea-Vera R, Ryan CT, Navarro SM, et al. Development of a Machine Learning Model to Predict Outcomes and Cost After Cardiac Surgery. Ann Thorac Surg. 2022. PMID: 35917942. doi:10.1016/j.athoracsur.2022.06.055

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。