Accurate detection of atrial fibrillation events with R-R intervals from ECG signals

Abstract

Atrial fibrillation (AF) is a typical category of arrhythmia. Clinical diagnosis of AF is based on the detection of abnormal R-R intervals (RRIs) with an electrocardiogram (ECG). Previous studies considered this detection problem as a classification problem and focused on extracting a number of features. In this study we demonstrate that instead of using any specific numerical characteristic as the input feature, the probability density of RRIs from ECG conserves comprehensive statistical information; hence, is a natural and efficient input feature for AF detection. Incorporated with a support vector machine as the classifier, results on the MIT-BIH database indicates that the proposed method is a simple and accurate approach for AF detection in terms of accuracy, sensitivity, and specificity.

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

“…Various machine learning classifiers were then trained on subsets consisting of the highest‐ranked HRV features. Lown et al (2020) and Duan et al (2022) also extracted HRV features from RR intervals, used style transfer to synthesize realistic ECGs, increasing the training data five‐fold. B. Chen et al (2023) developed a clustering algorithm based on self‐supervised contrastive learning to analyze ECG data.…”

Detection of Atrial Fibrillation Episodes based on 3D Algebraic Relationships between Cardiac Intervals

“…The surface electrocardiogram (ECG) is the primary tool used for the clinical diagnosis of atrial fibrillation (AF), and AF is distinguished by the absence of a P wave due to the electrical activity being disorganized. The RR interval, which reflects the ventricular interbeat, was proposed as a significant biomarker for AF detection, despite the P wave’s relatively low amplitude and challenging baseline that make its detection difficult [ 29 ]. Several publications investigate how the complexity of RR intervals changes as different cardiovascular disorders progress [ 30 , 31 ].…”

“…This suggests that ventricular repolarization rather than ventricular depolarization is a better predictor of future AF events (e.g., QRS duration). As previous reports have mainly concentrated on the AF risk associated with the entire QT interval, which includes components of both ventricular depolarization and repolarization, the results of this analysis offer significant insight into the pathophysiology of AF [ 29 ]. The interventricular synchronization aspects of the QRS duration parameter may be linked to the intrinsic regulatory system of the heart.…”

“…It is prolonged in some heart diseases, such as ischemic heart disease. Patients with prolonged QRS had a higher prevalence of AF, according to the authors of a cross-sectional study involving 25,000 people with left ventricular dysfunction [ 29 ]. The majority of methods employed by physicians rely on the analysis of discrete values such as heart rate, blood pressure, or the duration of a single cardiac interval.…”

Analysis of Electrocardiogram Dynamic Features for Arrhythmia Classification

“…AF is recognized as a cardiac irregularity marked by a rapid and irregular heart rhythm. This condition leads to the buildup and the formation of blood clots within the heart increases the likelihood of developing heart disease and experiencing a heart attack, encountering heart failure, and suffering from a stroke [3]. Nevertheless, PAC and PVC frequently responsible for rhythmic disturbances, can imitate the irregular heartbeat pattern that is typical of Atrial Fibrillation.…”