Department of Internal Medicine III, University of Heidelberg, Im Neuenheimer Feld 410, 69120, Heidelberg, Germany.
Institute of Medical Biometry and Informatics, University of Heidelberg, Heidelberg, Germany.
Clin Res Cardiol. 2021 Mar;110(3):343-356. doi: 10.1007/s00392-020-01691-0. Epub 2020 Jun 24.
Currently, patient selection in TAVI is based upon a multidisciplinary heart team assessment of patient comorbidities and surgical risk stratification. In an era of increasing need for precision medicine and quickly expanding TAVI indications, machine learning has shown promise in making accurate predictions of clinical outcomes. This study aims to predict different intrahospital clinical outcomes in patients undergoing TAVI using a machine learning-based approach. The main clinical outcomes include all-cause mortality, stroke, major vascular complications, paravalvular leakage, and new pacemaker implantations.
The dataset consists of 451 consecutive patients undergoing elective TAVI between February 2014 and June 2016. The applied machine learning methods were neural networks, support vector machines, and random forests. Their performance was evaluated using five-fold nested cross-validation. Considering all 83 features, the performance of all machine learning models in predicting all-cause intrahospital mortality (AUC 0.94-0.97) was significantly higher than both the STS risk score (AUC 0.64), the STS/ACC TAVR score (AUC 0.65), and all machine learning models using baseline characteristics only (AUC 0.72-0.82). Using an extreme boosting gradient, baseline troponin T was found to be the most important feature among all input variables. Overall, after feature selection, there was a slightly inferior performance. Stroke, major vascular complications, paravalvular leakage, and new pacemaker implantations could not be accurately predicted.
Machine learning has the potential to improve patient selection and risk management of interventional cardiovascular procedures, as it is capable of making superior predictions compared to current logistic risk scores.
目前，TAVI 的患者选择基于多学科心脏团队对患者合并症和手术风险分层的评估。在精准医学需求不断增加和 TAVI 适应证迅速扩大的时代，机器学习在准确预测临床结局方面显示出了良好的应用前景。本研究旨在使用基于机器学习的方法预测 TAVI 患者的不同院内临床结局。主要临床结局包括全因死亡率、卒中和主要血管并发症、瓣周漏和新植入起搏器。
数据集包含 2014 年 2 月至 2016 年 6 月期间连续进行的 451 例择期 TAVI 患者。应用的机器学习方法包括神经网络、支持向量机和随机森林。采用五重嵌套交叉验证评估它们的性能。考虑到 83 个特征，所有机器学习模型在预测全因院内死亡率方面的性能（AUC 0.94-0.97）明显高于 STS 风险评分（AUC 0.64）、STS/ACC TAVR 评分（AUC 0.65）和仅使用基线特征的所有机器学习模型（AUC 0.72-0.82）。使用极端梯度提升，发现基线肌钙蛋白 T 是所有输入变量中最重要的特征。总体而言，经过特征选择后，性能略有下降。卒中和主要血管并发症、瓣周漏和新植入起搏器无法准确预测。
机器学习有可能改善介入心血管手术的患者选择和风险管理，因为它能够做出优于当前逻辑风险评分的预测。
