文献速递瓣膜外科

基于机器学习的择期心脏瓣膜手术患者风险分层

Machine learning-based risk profile classification of patients undergoing elective heart valve surgery.
PubMed 文献 · Eur J Cardiothorac Surg · 2021-01-01

单中心回顾性研究纳入2229例择期心脏瓣膜手术患者,利用随机森林、人工神经网络和支持向量机从129个术前参数预测30天死亡率。随机森林模型袋外AUC为0.839,显著优于EuroSCORE的0.704及仅用EuroSCORE特征的模型AUC 0.745。机器学习可更准确预测瓣膜手术结局。

要点

  • 随机森林模型预测30天死亡率AUC 0.839,优于EuroSCORE的0.704。
  • 基于129个术前参数的机器学习模型可个体化评估择期瓣膜手术风险。
  • 该方法可推广至其他择期高风险干预并针对机构队列训练模型。

核心结论

  • 先进机器学习方法预测瓣膜手术结局的准确性高于基于逻辑回归和预选参数的现有风险评分。

研究设计与样本

  • 单中心回顾性研究,纳入2008年1月1日至2014年12月31日在该中心接受择期心脏瓣膜手术的患者,最终队列2229例,30天死亡率为3.86%(86/2229)。
  • 使用随机森林、人工神经网络和支持向量机从129个可用的人口学和术前参数子集中预测30天死亡率。
  • 排除标准为同一患者再次手术、因主动脉弓手术需要顺行脑灌注的患者以及成人先天性心脏病患者;该试验已在clinicaltrials.gov注册(NCT03724123)。

主要发现

  • 在完整数据集上训练的最终随机森林模型提供的袋外受试者工作特征曲线下面积(AUC)为0.839。
  • 随机森林模型显著优于欧洲心脏手术风险评估系统(EuroSCORE)(AUC = 0.704)。
  • 随机森林模型显著优于仅使用EuroSCORE所用特征子集训练的模型(AUC = 0.745)。

临床怎么用

  • 机器学习模型可用于择期心脏瓣膜手术前的个体化风险预测,辅助患者咨询并避免可能的并发症。
  • 该方法可针对特定机构的队列进行模型训练,具有推广至其他择期高风险干预的潜力。

局限性

  • 本研究为单中心回顾性研究。

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

OBJECTIVES: Machine learning methods potentially provide a highly accurate and detailed assessment of expected individual patient risk before elective cardiac surgery. Correct anticipation of this risk allows for the improved counselling of patients and avoidance of possible complications. We therefore investigated the benefit of modern machine learning methods in personalized risk prediction for patients undergoing elective heart valve surgery. METHODS: We performed a monocentric retrospective study in patients who underwent elective heart valve surgery between 1 January 2008 and 31 December 2014 at our centre. We used random forests, artificial neural networks and support vector machines to predict the 30-day mortality from a subset of 129 available demographic and preoperative parameters. Exclusion criteria were reoperation of the same patient, patients who needed anterograde cerebral perfusion due to aortic arch surgery and patients with grown-up congenital heart disease. Finally, the cohort consisted of 2229 patients with a 30-day mortality of 3.86% (86 of 2229 cases). This trial has been registered at clinicaltrials.gov (NCT03724123). RESULTS: The final random forest model trained on the entire data set provided an out-of-bag area under the receiver operator characteristics curve (AUC) of 0.839, which significantly outperformed the European System for Cardiac Operative Risk Evaluation (EuroSCORE) (AUC = 0.704) and a model trained only on the subset of features EuroSCORE uses (AUC = 0.745). CONCLUSIONS: Advanced machine learning methods can predict outcomes of valve surgery procedures with higher accuracy than established risk scores based on logistic regression on pre-selected parameters. This approach is generalizable to other elective high-risk interventions and allows for training models to the cohorts of specific institutions.

来源:Eur J Cardiothorac Surg,查看原文。版权归原作者所有。

引用

  1. Bodenhofer U, Haslinger-Eisterer B, Minichmayer A, et al. Machine learning-based risk profile classification of patients undergoing elective heart valve surgery. Eur J Cardiothorac Surg. 2021. PMID: 34050368. doi:10.1093/ejcts/ezab219

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。