Developing an atrial activity-based algorithm for detection of atrial fibrillation.

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Atrial fibrillation (AF) is a common arrhythmia.
• Current AF detection methods often rely on heart rate, which can be unreliable.
• A P-wave based approach offers a novel detection strategy.

Purpose of the Study:

• To develop and validate a novel atrial activity-based method for AF identification.
• To detect the absence of normal sinus rhythm (SR) P-waves from the surface ECG for AF detection.
• To create a rate-independent algorithm for AF determination.

Main Methods:

• Extraction of nine features from P-waves during SR.
• Development of a statistical model using a multivariate Gaussian Mixture Model (GMM) via Expectation-Maximization algorithm.
• Identification of P-wave absence (PWA) for AF detection, with an optional post-processing majority vote.

Main Results:

• The algorithm was tested on 20 records from the MIT-BIH Atrial Fibrillation Database.
• Classification using seven beats achieved a sensitivity of 99.28% and a specificity of 90.21%.
• The method demonstrates comparable performance to current heart rate-based algorithms.

Conclusions:

• The proposed method accurately identifies AF by detecting P-wave absence.
• The algorithm is rate-independent and capable of AF determination in a few beats.
• This novel approach offers a promising alternative for AF detection.