Related Experiment Video
Updated: Dec 27, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
A Review on the State of the Art in Atrial Fibrillation Detection Enabled by Machine Learning
Insights
This review covers machine learning and signal processing for Atrial Fibrillation (AF) auto-diagnosis using ECG data. It highlights the need for accurate, low-cost, low-energy solutions for proactive AF management.
Area of Science:
- Cardiology
- Biomedical Engineering
- Artificial Intelligence
Background:
- Atrial Fibrillation (AF) is a major global cause of illness and death.
- Diagnosing AF is difficult due to its often silent and intermittent nature.
Purpose of the Study:
- To review current ECG-based machine learning and signal processing techniques for automated AF diagnosis.
- To discuss AF biomarkers, ECG data collection methods, and sensing technologies.
- To identify challenges in developing automated AF diagnostic solutions.
Main Methods:
- Comprehensive literature review of state-of-the-art machine learning models.
- Analysis of signal processing techniques for ECG data.
- Discussion of wearable and implantable ECG sensing technologies.
Main Results:
- The review consolidates information on AF auto-diagnosis methods, biomarkers, and data collection.
- Key challenges in developing accurate, low-cost, low-energy AF auto-diagnosis systems are identified.
Conclusions:
- There is a significant need for accessible and efficient automated systems for proactive Atrial Fibrillation management.
- Further research into low-power, cost-effective AF diagnostic solutions is crucial.
Abstract:
Atrial Fibrillation (AF) the most commonly occurring type of cardiac arrhythmia is one of the main causes of morbidity and mortality worldwide. The timely diagnosis of AF is an equally important and challenging task because of its asymptomatic and episodic nature. In this paper, state-of-the-art ECG data-based machine learning models and signal processing techniques applied for auto diagnosis of AF are reviewed. Moreover, key biomarkers of AF on ECG and the common methods and equipment used for the collection of ECG data are discussed. Besides that, the modern wearable and implantable ECG sensing technologies used for gathering AF data are presented briefly. In the end, key challenges associated with the development of auto diagnosis solutions of AF are also highlighted. This is the first review paper of its kind that comprehensively presents a discussion on all these aspects related to AF auto-diagnosis in one place. It is observed that there is a dire need for low energy and low cost but accurate auto diagnosis solutions for the proactive management of AF.
