PPG-AFNet: a lightweight and intelligible network for atrial fibrillation identification using photoplethysmography signals

Key Points

• Atrial fibrillation identification is enhanced with the PPG-AFNet network, achieving high accuracy.
• The network processes photoplethysmography signals, with a reported identification accuracy of over 90%.
• Analysis of traditional methods and deep learning techniques revealed significant performance gaps in atrial fibrillation detection.
• This study highlights the potential for efficient, real-time detection of atrial fibrillation using lightweight network architectures.