Cardio-Thoracic Unit, Bordeaux University Hospital (CHU), F-33600 Bordeaux, France.
IHU Liryc, Electrophysiology and Heart Modeling Institute, Fondation Bordeaux Université, F-33600 Bordeaux, France.
Sensors (Basel). 2023 Nov 20;23(22):9283. doi: 10.3390/s23229283.
Smartwatches equipped with automatic atrial fibrillation (AF) detection through electrocardiogram (ECG) recording are increasingly prevalent. We have recently reported the limitations of the Apple Watch (AW) in correctly diagnosing AF. In this study, we aim to apply a data science approach to a large dataset of smartwatch ECGs in order to deliver an improved algorithm. We included 723 patients (579 patients for algorithm development and 144 patients for validation) who underwent ECG recording with an AW and a 12-lead ECG (21% had AF and 24% had no ECG abnormalities). Similar to the existing algorithm, we first screened for AF by detecting irregularities in ventricular intervals. However, as opposed to the existing algorithm, we included all ECGs (not applying quality or heart rate exclusion criteria) but we excluded ECGs in which we identified regular patterns within the irregular rhythms by screening for interval clusters. This "irregularly irregular" approach resulted in a significant improvement in accuracy compared to the existing AW algorithm (sensitivity of 90% versus 83%, specificity of 92% versus 79%, < 0.01). Identifying regularity within irregular rhythms is an accurate yet inclusive method to detect AF using a smartwatch ECG.
配备通过心电图 (ECG) 记录自动心房颤动 (AF) 检测功能的智能手表越来越普及。我们最近报告了 Apple Watch (AW) 在正确诊断 AF 方面的局限性。在这项研究中,我们旨在应用数据科学方法对大量智能手表 ECG 数据集进行分析,以提供改进的算法。我们纳入了 723 名患者(579 名用于算法开发,144 名用于验证),他们接受了 AW 和 12 导联 ECG 记录(21%有 AF,24%无 ECG 异常)。与现有的算法类似,我们首先通过检测心室间隔不规则来筛查 AF。然而,与现有的算法不同,我们纳入了所有 ECG(不应用质量或心率排除标准),但排除了通过筛查间隔聚类识别不规则节律内规则模式的 ECG。与现有的 AW 算法相比,这种“不规则的规则”方法显著提高了准确性(敏感性为 90%,特异性为 92%,<0.01)。在不规则节律中识别规则是一种使用智能手表 ECG 检测 AF 的准确且包容性的方法。