Centre of Health Informatics and Technology, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, 5230 Odense, Denmark.
Centre of Health Informatics and Technology, The Mærsk Mc-Kinney Møller Institute, University of Southern Denmark, 5230 Odense, Denmark; Department of Mathematics and Computer Science, University of Southern Denmark, 5230 Odense, Denmark.
Int J Med Inform. 2022 Jul;163:104790. doi: 10.1016/j.ijmedinf.2022.104790. Epub 2022 May 7.
Atrial fibrillation (AF) is one of the most prevalent cardiac arrhythmias, which challenges the healthcare systems globally.Timely detection of AF can potentially reduce the mortality and morbidity rates as well as alleviate the economic burden caused by this.Digital solutions are shown to enhance the diagnosis of cardiac abnormalities.
By the latest advancements in the field of medical informatics and tele-health monitoring, huge amount of electro-physiological signals, such as electrocardiograms (ECG), can be easily collected.One of the most common ways for physicians/cardiologists to analyse these signals is through visual inspection.However, it is not always easy and in most cases cumbersome to analyse these big amounts of ECG data.Therefore, it is of great interest to develop models that are capable of analyzing these data and help physicians making better decisions.This paper proposes and compares well-known machine learning (ML) algorithms to diagnose short episodes of AF. This also paves the way for real-time detection of AF in clinical settings.
Different ML algorithms such as Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Stacking Classifier (SC), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) were applied to detect AF. These models were trained using extracted statistical features from ECG signals.
The proposed ML models were trained on a dataset with 23 ECG records of length approximately 10 h each using leave one group out cross validation (LOGO-CV) technique and achieved the best sensitivity (Se), specificity (Sp), positive predictive value (PPV), false positive rate (FPR), and F-score of 85.67%, 81.25%, 90.85%, 18.75% and 88.18%, respectively, to classify AF from normal sinus rhythms (NSR) in short ECG segments of 20 heartbeats.Additionally, the models were examined on three unseen datasets, namely the Long Term AF dataset, MIT-BIH Arrhythmia dataset, and MIT-BIH Normal Sinus Rhythm dataset, to assess their robustness and generalization.
The obtained results show high performance and flexibility of some of the applied ML models compared to other well-known algorithms. In general, the empirical results confirm that ensemble methods, such as AdaBoost, generalized well and perform better than other approaches.
心房颤动（AF）是最常见的心律失常之一，对全球的医疗保健系统构成挑战。及时发现 AF 有可能降低死亡率和发病率，并减轻由此造成的经济负担。数字解决方案已被证明可以增强对心脏异常的诊断。
通过医学信息学和远程健康监测领域的最新进展，可以轻松收集大量电生理信号，例如心电图（ECG）。医生/心脏病专家分析这些信号的最常见方法之一是通过目视检查。但是，分析这些大量 ECG 数据并不总是容易且在大多数情况下很麻烦。因此，开发能够分析这些数据并帮助医生做出更好决策的模型非常重要。本文提出并比较了著名的机器学习（ML）算法，以诊断 AF 的短暂发作。这也为在临床环境中实时检测 AF 铺平了道路。
应用了各种机器学习算法，如支持向量机（SVM）、决策树（DT）、随机森林（RF）、堆叠分类器（SC）、极端梯度提升（XGBoost）和自适应提升（AdaBoost），来检测 AF。这些模型使用从 ECG 信号中提取的统计特征进行训练。
使用留一法交叉验证（LOGO-CV）技术，将所提出的 ML 模型在包含 23 个 ECG 记录的数据集上进行训练，每个记录的长度约为 10 小时，以检测 20 个心跳的短 ECG 段中 AF 与正常窦性节律（NSR）的分类，结果模型的灵敏度（Se）、特异性（Sp）、阳性预测值（PPV）、假阳性率（FPR）和 F 评分最佳，分别为 85.67%、81.25%、90.85%、18.75%和 88.18%。此外，还在三个未见过的数据集（即长期 AF 数据集、MIT-BIH 心律失常数据集和 MIT-BIH 正常窦性节律数据集）上检查了模型，以评估其稳健性和泛化能力。
与其他知名算法相比，所应用的一些机器学习模型的结果表明其具有较高的性能和灵活性。总体而言，经验结果证实，集成方法（如 AdaBoost）泛化效果良好，性能优于其他方法。
