Abstract
The rising prevalence of atrial fibrillation (AF) continues to impose a burden on the healthcare systems globally, leading to significant economic losses. Currently, electrocardiography (ECG) is the golden standard for AF detection. However, ECG recordings may be misinterpreted as other conditions such as sinus tachycardia or supraventricular tachycardia. This notwithstanding, the high cost, limited portability, and short duration of ECG recordings can pose additional limitations to its use. The recent development of AF detection technology using photoplethysmography (PPG) signals yields promising potential. Subsequently, the clinical implications of AF detection using wearable technology can enable the early detection and timely management of AF, thereby reducing patient morbidity and mortality. However, the accuracy of PPG-based AF detection can be limited by some technical issues. Current guidelines are restricted to ECG-based methods. Therefore, the aim of this chapter is to perform a systemic review of the existing literature on AF detection using PPG signals. Overall, the available evidence reveals that PPG is an effective, user-friendly, low-cost method for long-term screening of AF. Nonetheless, further prospective studies need to be conducted to compare the performance of current AF detection methods versus PPG-based approaches.
Original language | English |
---|---|
Title of host publication | Signal Processing Driven Machine Learning Techniques for Cardiovascular Data Processing |
Editors | Rajesh Kumar Tripathy, Ram Bilas Pachori |
Publisher | Academic Press |
Chapter | 4 |
Pages | 49-63 |
Number of pages | 15 |
Edition | 1 |
ISBN (Electronic) | 9780443141409 |
ISBN (Print) | 9780443141416 |
DOIs | |
Publication status | Published - 12 Jun 2024 |
Keywords
- wearable technology
- long-term screening
- heart disease
- arrhythmia
- healthcare policy
- artificial intelligence
- PPG