Machine learning in the detection and management of atrial fibrillation

Abstract

Machine learning has immense novel but also disruptive potential for medicine. Numerous applications have already been suggested and evaluated concerning cardiovascular diseases. One important aspect is the detection and management of potentially thrombogenic arrhythmias such as atrial fibrillation. While atrial fibrillation is the most common arrhythmia with a lifetime risk of one in three persons and an increased risk of thromboembolic complications such as stroke, many atrial fibrillation episodes are asymptomatic and a first diagnosis is oftentimes only reached after an embolic event. Therefore, screening for atrial fibrillation represents an important part of clinical practice. Novel technologies such as machine learning have the potential to substantially improve patient care and clinical outcomes. Additionally, machine learning applications may aid cardiologists in the management of patients with already diagnosed atrial fibrillation, for example, by identifying patients at a high risk of recurrence after catheter ablation. We summarize the current state of evidence concerning machine learning and, in particular, artificial neural networks in the detection and management of atrial fibrillation and describe possible future areas of development as well as pitfalls. Graphical abstract Typical data flow in machine learning applications for atrial fibrillation detection.

eCardiology: ein strukturierter Ansatz zur Förderung der digitalen Transformation in der Kardiologie

“…Weitere beeindruckende Ergebnisse umfassen z. B. die Anwendung von KI in der Bewertung von Röntgenbildern, das Vorhersagen der fraktionellen Flussreserve (FFR) anhand von rekonstruierten, koronaren Computertomographie-Angiographien oder die Vorhersage des baldigen Auftretens von Vorhofflimmern in EKGs mit Sinusrhythmus [ 6 – 9 ].…”

A Study of R-R Interval Transition Matrix Features for Machine Learning Algorithms in AFib Detection

“…More recent research in AFib detection has increasingly incorporated advanced machine learning techniques [ 27 ]. A 2020 study performed wavelet transformations on Lorenz plots and fed these transformed plots into support vector machines (SVM), yielding a sensitivity of 99.2% and a specificity of 99.5% [ 14 ].…”

“…With the surge of interest in deep learning, researchers have explored the application of deep learning techniques for AFib detection [ 16 , 27 , 30 , 31 , 32 , 33 ]. Liaqat et al employed machine learning classifiers, including SVM, Logistic Regression, and XGBoost, as well as deep learning models, such as convolutional neural networks (CNN) and long short-term memory (LSTM) for AFib detection [ 30 ].…”

“…Concerns have been raised about the intransparency of deep neural networks, which makes it challenging for medical professionals to obtain useful information regarding the AFib classification. [ 27 ]. Many methods to improve the transparency of neural networks have been proposed, allowing the classification results to be more informative for individuals and medical professionals [ 36 , 37 ]…”

Can Deep Learning Models Differentiate Atrial Fibrillation from Atrial Flutter?

“…Over the past decades, the research community has increasingly focused on automating AFib detection, with Deep Learning (DL) emerging as an effective technique for ECG analysis [7], [8]. Studies consistently show high accuracy in detecting AFib compared to non-AFib classes [9]- [13], with some proposing merging AFib and AFlut into a single class for classification [12].…”