Medical School of Chinese PLA, 100853 Beijing, China.
Department of Cardiovascular Surgery, The First Medical Center of Chinese PLA General Hospital, 100853 Beijing, China.
Heart Surg Forum. 2023 Jun 14;26(3):E255-E263. doi: 10.1532/hsf.5341.
New-onset postoperative atrial fibrillation (POAF) is the most common complication after valvular surgery, but its etiology and risk factors are incompletely understood. This study investigates the benefits of machine learning methods in risk prediction and in identifying relative perioperative variables for POAF after valve surgery.
This retrospective study involved 847 patients, who underwent isolated valve surgery from January 2018 to September 2021 in our institution. We used machine learning algorithms to predict new-onset postoperative atrial fibrillation and to select relatively important variables from a set of 123 preoperative characteristics and intraoperative information.
The support vector machine (SVM) model demonstrated the best area under the receiver operating characteristic (AUC) value of 0.786, followed by logistic regression (AUC = 0.745) and the Complement Naive Bayes (CNB) model (AUC = 0.672). Left atrium diameter, age, estimated glomerular filtration rate (eGFR), duration of cardiopulmonary bypass, New York Heart Association (NYHA) class III-IV, and preoperative hemoglobin were high-ranked variables.
Risk models based on machine learning algorithms may be superior to traditional models, which were primarily based on logistic algorithms to predict the occurrence of POAF after valve surgery. Further prospective multicenter studies are needed to confirm the performance of SVM in predicting POAF.
新发术后心房颤动（POAF）是瓣膜手术后最常见的并发症，但病因和危险因素尚未完全阐明。本研究旨在探讨机器学习方法在预测瓣膜手术后新发 POAF 风险和识别相对围手术期变量方面的优势。
本回顾性研究纳入了 2018 年 1 月至 2021 年 9 月期间在我院接受单纯瓣膜手术的 847 例患者。我们使用机器学习算法预测新发术后心房颤动，并从 123 项术前特征和术中信息中选择相对重要的变量。
支持向量机（SVM）模型的受试者工作特征曲线下面积（AUC）值最佳，为 0.786，其次是逻辑回归（AUC=0.745）和互补朴素贝叶斯（CNB）模型（AUC=0.672）。左心房直径、年龄、估算肾小球滤过率（eGFR）、体外循环时间、纽约心脏协会（NYHA）心功能分级 III-IV 级和术前血红蛋白是高排名变量。
基于机器学习算法的风险模型可能优于传统模型，后者主要基于逻辑算法预测瓣膜手术后 POAF 的发生。需要进一步开展前瞻性多中心研究以验证 SVM 在预测 POAF 方面的性能。
