Yield of atrial fibrillation detection with Textile Wearable Holter from the acute phase of stroke: Pilot study of Crypto-AF registry

A Deep Learning Approach for Featureless Robust Quality Assessment of Intermittent Atrial Fibrillation Recordings from Portable and Wearable Devices

“…In addition, the ECG signals in diverse databases reflected heart electrical activity from different body positions. Whereas in the PC2017DB and the THDB a lead I equivalent ECG was captured by electrodes located at each hand of the patient [ 43 , 44 ], in the PDB a non-standard lead was acquired from the patient’s thorax [ 15 ]. Similarly, the ECG recordings in each database also presented diverse kinds and levels of noises, because they were obtained from different environments and making use of different approaches.…”

“…Moreover, most arrhythmic events in the initial stage of the disease often last a few seconds or minutes; their detection needs long-term continuous monitoring of a patient’s electrocardiogram (ECG) [ 13 ]. To this respect, previous works have proven that the longer the duration of monitoring, the greater the possibility of early identification of patients suffering from intermittent AF [ 14 , 15 ].…”

“…The most recent advances in portable and wearable medical devices may become highly useful in this premature screening of silent AF, because they are able to significantly increase the monitoring time window where the arrhythmia can be detected. Thus, fresh improvements in low-power embedded systems, communication protocols, and cloud computing technologies have allowed the development of numerous wearable systems with the ability for ECG monitoring over several weeks and even months, while the subject continues a normal active life [ 15 , 16 , 17 , 18 ]. However, these devices will usually work in highly dynamic and changing environments, thus providing ECG signals that are especially prone to be corrupted with different kinds of noises, such as motion artifacts, powerline interference, baseline wander, and high-frequency electromyography disturbances, among others [ 19 ].…”

“…While a broad variety of techniques for ECG quality assessment have been proposed to date [ 20 ], most of them cannot deal with signals acquired via portable or wearable systems. On the one hand, many algorithms have been designed to simultaneously analyze the 12 leads found in the standard ECG, but portable and wearable systems often present a more reduced number of signals, commonly between one and three [ 15 , 16 , 17 , 18 ]. On the other hand, numerous methods raised to assess single-lead ECG quality are based on detecting fiducial points and morphological events in the signal, and then computing parameters such as mean RR interval, ratio of maximum to minimum RR interval, time consistency of PQRST waveforms, coherence of QRS complexes, etc.…”

External continuous ECG versus loop recording for atrial fibrillation detection in patients who had a stroke

“…In 2014, Tu et al 21 reported that 28-day continuous ECG recording was poorly tolerated in patients who had a cryptogenic stroke, with only 40% completing the recording period; remaining patients were excluded mainly due to skin irritation and also artefacts caused by loose electrodes and trouble sleeping with the device caused exclusions. Higher patient comfort and compliance was observed with a specially designed textile wearable continuous ECG recorder, resulting in 84% of patients who had a cryptogenic stroke completing 28-day recording 22. Gain of prolonging continuous ECG recording in AF detection is currently explored in the ongoing German Impact of standardized MONitoring for Detection of Atrial Fibrillation in Ischemic Stroke trial 23…”