Automatic Atrial Fibrillation detection: A novel approach using discrete wavelet transform and heart rate variability

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Early detection of Atrial Fibrillation (AF) is vital for preventing serious cardiac complications.
• Current screening methods may have limitations in accuracy and accessibility.

Purpose of the Study:

• To propose and evaluate a novel method for robust automatic Atrial Fibrillation detection (AAFD).
• To assess the potential of the proposed method as a screening tool for patients at risk of AF.

Main Methods:

• A new AAFD approach combining atrial activity (AA) and heart rate variability (HRV) was developed.
• The method incorporates automatic peak detection, noise cancellation, and bagged tree classification.
• Performance was evaluated using the MIT-BIH Atrial Fibrillation database.

Main Results:

• The proposed AAFD method demonstrated high performance in simulations.
• Achieved an average sensitivity of 96.51%, specificity of 99.19%, and overall accuracy of 98.22%.

Conclusions:

• The novel AAFD method combining AA and HRV is highly accurate and robust.
• This approach shows significant potential as an effective screening tool for Atrial Fibrillation detection.