What does this research mean for the field?

Deep learning architectures significantly outperform traditional machine learning models in detecting atrial fibrillation from long-term ECG signals, achieving higher accuracy and F1-scores. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The aim is to enhance detection accuracy of atrial fibrillation using advanced machine and deep learning frameworks.

March 3, 2026Open Access

Comparative Analysis of Machine Learning and Deep Learning Models for Atrial Fibrillation Detection from Long-Term ECG

Key Result

Deep learning models, particularly the best architecture tested, significantly outperformed traditional machine learning for atrial fibrillation detection with high accuracy and F1-score.

Key Points

The aim is to enhance detection accuracy of atrial fibrillation using advanced machine and deep learning frameworks.
Developed a comprehensive detection framework integrating segmentation and feature extraction.
Introduced a coalescence window for dynamic clustering of arrhythmic episodes.
Evaluated multiple classifiers, including machine learning and deep learning models like TCNs, CNNs, and BiLSTM.
Performed experiments on a balanced dataset of ECG signals.
Deep learning models significantly outperformed traditional approaches in detection accuracy.
The best model achieved high accuracy and F1-score in detecting atrial fibrillation.
The proposed pipeline is modular and designed for real-time and edge computing environments.

Structured PICO

Do advanced deep learning architectures improve atrial fibrillation detection accuracy from long-term ECGs compared to traditional machine learning models?

Population

Balanced dataset of long-term ECG signals containing atrial fibrillation events

Intervention

Advanced deep learning architectures (Temporal Convolutional Networks [TCNs], Convolutional Neural Networks [CNNs], and Bidirectional Long Short-Term Memory [BiLSTM]) with optimized segmentation and a coalescence window

Comparator

Traditional machine learning models

Outcome

Atrial fibrillation detection accuracy and F1-scoresurrogate

Advanced deep learning models significantly outperform traditional machine learning approaches for detecting atrial fibrillation from ECGs, highlighting their potential for scalable, real-time clinical monitoring.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Atrial fibrillation is the most prevalent sustained cardiac arrhythmia and a major risk factor for stroke, heart failure, and premature mortality. Automatic detection remains challenging due to the variability of electrocardiogram (ECG) morphology, noise, and the paroxysmal nature of atrial fibrillation events. This study proposes a comprehensive framework that integrates optimised segmentation, feature extraction, and advanced deep learning architectures to improve detection accuracy. A coalescence window is introduced to dynamically cluster arrhythmic episodes, aligning computational analysis with clinical event distributions. Multiple classifiers are investigated, ranging from traditional machine learning models to state-of-the-art deep neural networks, including Temporal Convolutional Networks (TCNs), Convolutional Neural Networks (CNNs), and Bidirectional Long Short-Term Memory (BiLSTM). Experimental evaluation on a balanced dataset of ECG signals demonstrates the superior performance of deep learning models, with the best architecture achieving high accuracy and F1-score, significantly outperforming traditional approaches. Furthermore, the proposed pipeline is designed to be modular and resource-aware, supporting potential deployment in real-time and edge computing environments. These results highlight the feasibility of scalable atrial fibrillation monitoring systems that bridge algorithmic innovation with clinical applicability, ultimately contributing to earlier diagnosis and improved patient management.