Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network

xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

Recognition of Supraventricular Arrhythmias in Holter ECG Recordings by ECHOView Color Map: A Case Series Study

Ambulatory 24-72 h Holter ECG monitoring is recommended for patients with suspected arrhythmias, which are often transitory and might remain unseen in resting standard 12-lead ECG. Holter manufacturers provide software diagnostic tools to assist clinicians in evaluating these large amounts of data. Nevertheless, the identification of short arrhythmia events and differentiation of the arrhythmia type might be a problem in limited Holter ECG leads. This observational clinical study aims to explore a novel and weakly investigated ECG modality integrated into a commercial diagnostic tool ECHOView (medilog DARWIN 2, Schiller AG, Switzerland), while used for the interpretation of long-term Holter-ECG records by a cardiologist. The ECHOView transformation maps the beat waveform amplitude to a color-coded bar. One ECHOView page integrates stacked color bars of about 1740 sequential beats aligned by R-peak in a window (R ± 750 ms). The collected 3-lead Holter ECG recordings from 86 patients had a valid duration of 21 h 20 min (19 h 30 min-22 h 45 min), median (quartile range). The ECG rhythm was reviewed with 3491 (3192-3723) standard-grid ECG pages and a substantially few number of 51 (44-59) ECHOView pages that validated the ECHOView compression ratio of 67 (59-74) times. Comments on the ECG rhythm and ECHOView characteristic patterns are provided for 14 examples representative of the most common rhythm disorders seen in our population, including supraventricular arrhythmias (supraventricular extrasystoles, paroxysmal supraventricular arrhythmia, sinus tachycardia, supraventricular tachycardia, atrial fibrillation, and flutter) and ventricular arrhythmias (ventricular extrasystoles, non-sustained ventricular tachycardia). In summary, the ECHOView color map transforms the ECG modality into a novel diagnostic image of the patient's rhythm that is comprehensively interpreted by a cardiologist. ECHOView has the potential to facilitate the manual overview of Holter ECG recordings, to visually identify short-term arrhythmia episodes, and to refine the diagnosis, especially in high-rate arrhythmias.

Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation

The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.