基于机器学习的瓣膜病心房颤动患者心脏血栓形成预测和特征分析

Prediction and characteristic analysis of cardiac thrombosis in patients with atrial fibrillation undergoing valve disease surgery based on machine learning

目的评估机器学习算法在心脏瓣膜病心房颤动患者心脏血栓形成的预测和表征中的应用。方法本研究从四川大学华西医院及其分院收集2016—2021年心脏瓣膜病伴心房颤动患者的临床数据,从2515例接受瓣膜手术的患者中筛选出886例瓣膜病伴心房颤动患者纳入研究,其中男545例(61.5%)、女341例(38.5%),平均年龄(55.62±9.26)岁,192例患者术中证实有心脏血栓形成。采用5种监督机器学习算法来预测患者的血栓形成。基于患者的临床数据(特征筛选后的33个特征),采用10折嵌套交叉验证方法,通过曲线下面积、F1分数以及马修斯相关系数等评价指标对模型的预测效果进行评价。最后,使用SHAP解释方法来解释模型,并以患者为例分析模型的特征。结果随机森林模型各项综合评估指标最佳,受试者工作特征曲线下面积为0.748±0.043,准确率79.2%。对模型的解释和分析表明,每搏输出量、二尖瓣E波峰值流速和三尖瓣压力梯度等是影响预测的重要因素。结论随机森林模型实现了最好的预测性能,有望被临床医生用作一种辅助决策工具,用于筛查患有瓣膜病心房颤动的高栓塞风险患者。

Objective To evaluate the use of machine learning algorithms for the prediction and characterization of cardiac thrombosis in patients with valvular heart disease and atrial fibrillation.Methods This article collected data of patients with valvular disease and atrial fibrillation from West China Hospital of Sichuan University and its branches from 2016 to 2021.From a total of 2515 patients who underwent valve surgery,886 patients with valvular disease and atrial fibrillation were included in the study,including 545(61.5%)males and 341(38.5%)females,with a mean age of 55.62±9.26 years,and 192 patients had intraoperatively confirmed cardiac thrombosis.We used five supervised machine learning algorithms to predict thrombosis in patients.Based on the clinical data of the patients(33 features after feature screening),the 10-fold nested cross-validation method was used to evaluate the predictive effect of the model through evaluation indicators such as area under the curve,F1 score and Matthews correlation coefficient.Finally,the SHAP interpretation method was used to interpret the model,and the characteristics of the model were analyzed using a patient as an example.Results The final experiment showed that the random forest classifier had the best comprehensive evaluation indicators,the area under the receiver operating characteristic curve was 0.748±0.043,and the accuracy rate reached 79.2%.Interpretation and analysis of the model showed that factors such as stroke volume,peak mitral E-wave velocity and tricuspid pressure gradient were important factors influencing the prediction.Conclusion The random forest model achieves the best predictive performance and is expected to be used by clinicians as an aided decision-making tool for screening high-embolic risk patients with valvular atrial fibrillation.