在接受心脏手术的患者中,术后心房颤动(POAF)的发生率高达20%至55%。机器学习(ML)已经越来越多地用于监控,筛选,并识别不同的心血管临床状况。有人提出ML可能是预测心脏手术后POAF的有用工具。在Medline进行了电子数据库搜索,EMBASE,科克伦,谷歌学者,和ClinicalTrials.gov,以确定调查ML在预测心脏手术后POAF中的作用的主要研究。共有5,955篇引文进行了标题和摘要筛选,最终纳入5项研究。报告的POAF发生率为21.5%至37.1%。研究的机器学习模型包括:深度学习,决策树,逻辑回归,支持向量机,梯度增强决策树,梯度增压机,K-最近的邻居,神经网络,和随机森林模型。报告的ML模型的灵敏度范围为0.22至0.91,特异性为0.64至0.84,受试者工作特征曲线下面积为0.67至0.94。年龄,性别,左心房直径,肾小球滤过率,和机械通气持续时间是POAF的重要临床危险因素。有限的证据表明,机器学习模型可能在心脏手术后预测心房颤动方面发挥作用,因为它们能够检测不同的相关性模式,并结合了几个人口统计学和临床变量。然而,纳入研究的异质性和缺乏外部验证是在常规实践中常规纳入这些模型的最重要限制.人工智能,心脏手术,决策树,深度学习,梯度增压机,梯度增强决策树,k-最近的邻居,逻辑回归,机器学习,神经网络,术后心房颤动,术后并发症,随机森林,风险评分,范围审查,支持向量机。
Postoperative atrial fibrillation (POAF) occurs in up to 20% to 55% of patients who underwent cardiac surgery. Machine learning (ML) has been increasingly employed in monitoring, screening, and identifying different cardiovascular clinical conditions. It was proposed that ML may be a useful tool for predicting POAF after cardiac surgery. An electronic database search was conducted on Medline, EMBASE, Cochrane, Google Scholar, and ClinicalTrials.gov to identify primary studies that investigated the role of ML in predicting POAF after cardiac surgery. A total of 5,955 citations were subjected to title and abstract screening, and ultimately 5 studies were included. The reported incidence of POAF ranged from 21.5% to 37.1%. The studied ML models included: deep learning, decision trees, logistic regression, support vector machines, gradient boosting decision tree, gradient-boosted machine, K-nearest neighbors, neural network, and random forest models. The sensitivity of the reported ML models ranged from 0.22 to 0.91, the specificity from 0.64 to 0.84, and the area under the receiver operating characteristic curve from 0.67 to 0.94. Age, gender, left atrial diameter, glomerular filtration rate, and duration of mechanical ventilation were significant clinical risk factors for POAF. Limited evidence suggest that machine learning models may play a role in predicting atrial fibrillation after cardiac surgery because of their ability to detect different patterns of correlations and the incorporation of several demographic and clinical variables. However, the heterogeneity of the included studies and the lack of external validation are the most important limitations against the routine incorporation of these models in routine practice. Artificial intelligence, cardiac surgery, decision tree, deep learning, gradient-boosted machine, gradient boosting decision tree, k-nearest neighbors, logistic regression, machine learning, neural network, postoperative atrial fibrillation, postoperative complications, random forest, risk scores, scoping
review, support vector machine.