ECG and PPG Signals-Based Premature Ventricular Contraction Detection Methods: A Review, Key Challenges, and Future...

Area of Science:

• Cardiology
• Biomedical Engineering
• Signal Processing

Background:

• Premature ventricular contractions (PVCs) are common arrhythmias requiring timely detection for cardiovascular event prevention and reduced clinical workload.
• Automated detection of PVCs from electrocardiogram (ECG) and photoplethysmogram (PPG) signals is essential for effective long-term cardiac monitoring.

Purpose of the Study:

• To review state-of-the-art methods for PVC detection using ECG and PPG signals.
• To categorize existing methods into threshold-based, traditional machine learning, and deep learning approaches.
• To discuss signal databases, performance metrics, preprocessing techniques, challenges, and future directions in PVC detection.

Main Methods:

• Review of signal processing, traditional machine learning, and deep learning techniques for PVC detection.
• Categorization of methods into heuristic-based, conventional machine learning, and deep learning frameworks.
• Overview of ECG and PPG signal databases and performance evaluation metrics.

Main Results:

• Existing PVC detection methods are categorized, with a focus on R-peak and systolic peak detection preprocessing.
• Various preprocessing techniques for ECG and PPG signals are reviewed.
• Performance and contributions of current methods are analyzed.

Conclusions:

• Accurate PVC detection faces challenges from noise in ambulatory and exercise conditions.
• Future research should address resource constraints for wearable long-term monitoring devices.
• Advancements in deep learning and signal processing are crucial for improving PVC detection accuracy and reliability.