Mutke Markus R, Brasier Noe, Raichle Christina, Ravanelli Flavia, Doerr Marcus, Eckstein Jens
Chief Medical Information Officer - Office, University Hospital Basel, Basel, Switzerland.
Department of Internal Medicine, University Hospital Basel, Basel, Switzerland.
Telemed J E Health. 2021 Mar;27(3):296-302. doi: 10.1089/tmj.2020.0036. Epub 2020 May 18.
Background:Atrial fibrillation (AF), the most common cardiac arrhythmia, can be detected by smartphones and smartwatches.
Introduction:Single-lead ECGs (iECGs) and photoplethysmography (PPG) sensors provide the opportunity for a broad, simple, and easily repeatable cardiac rhythm analysis. To reduce unnecessary medical follow-up testing due to false positive results, our aim was to find a screening approach applicable on smart devices with a focus on high specificity.
Methods:We used PPG measurements from smartphones and smartwatches and iECG data from two previous validation trials. Two AF detection algorithms (A and B) were applied on the iECG dataset and compared directly. Further, we used 1-min PPG measurements as a first-pass filter for arrhythmia detection and simulated a sequential testing: Once an arrhythmia was detected in the PPG, the iECG counterpart of the patient was analyzed by algorithm A, B, or A + B combined although algorithm B was primarily designed for PPG analysis.
Results:The iECGs from 1,288 participants were analyzed. Algorithm A did not show a diagnosis in 16.1%. In the remaining, sensitivity and specificity were 99.6%, and 97.4% respectively. Accuracy was 98.5%, and correct classification rate (CCR) was 82.7%. Algorithm B always differentiated between normal and arrhythmic and reached an overall sensitivity of 95.4%, a specificity of 91.6%, and an accuracy and CCR of 93.3%. Sequential testing by combining both algorithms into a three-phase test (Test positive PPG, then iECG analysis by A and B combined) resulted in a 100% specificity.
Conclusion:Algorithm B performed strongly in PPG analysis as well as iECG analysis. PPG signals and consecutive iECG combined when an arrhythmia was detected by PPG resulted in a specificity that was higher than 99%.
Discussion:The analysis allows a direct comparison of iECG algorithms without possible dilution by different measurement procedures or recording-devices. We improved specificity in AF-screening approaches with wearables by simulating a novel approach. Results rely on signal quality.
心房颤动（AF）是最常见的心律失常，可通过智能手机和智能手表检测到。
单导联心电图（iECG）和光电容积脉搏波描记法（PPG）传感器为广泛、简单且易于重复的心律分析提供了机会。为减少因假阳性结果导致的不必要的医学随访检测，我们的目标是找到一种适用于智能设备的筛查方法，重点关注高特异性。
我们使用了来自智能手机和智能手表的PPG测量值以及来自之前两项验证试验的iECG数据。将两种房颤检测算法（A和B）应用于iECG数据集并直接进行比较。此外，我们将1分钟的PPG测量值用作心律失常检测的初筛滤波器，并模拟了序贯检测：一旦在PPG中检测到心律失常，就通过算法A、B或A + B组合对患者的iECG对应数据进行分析，尽管算法B主要设计用于PPG分析。
对1288名参与者的iECG进行了分析。算法A在16.1%的病例中未得出诊断结果。在其余病例中，敏感性和特异性分别为99.6%和97.4%。准确率为98.5%，正确分类率（CCR）为82.7%。算法B总能区分正常和心律失常情况，总体敏感性为95.4%，特异性为91.6%，准确率和CCR为93.3%。将两种算法组合成三相检测（PPG检测阳性，然后通过A和B组合进行iECG分析）的序贯检测特异性达到了100%。
算法B在PPG分析以及iECG分析中表现出色。当通过PPG检测到心律失常时，PPG信号与连续的iECG相结合，特异性高于99%。
该分析允许直接比较iECG算法，而不会因不同的测量程序或记录设备而可能产生稀释效应。我们通过模拟一种新方法提高了可穿戴设备在房颤筛查方法中的特异性。结果依赖于信号质量。
