Arrhythmia detection and classification using ECG and PPG techniques: a review.

Area of Science:

• Biomedical Engineering
• Cardiology
• Signal Processing

Background:

• Electrocardiogram (ECG) and photoplethysmograph (PPG) are key non-invasive techniques for cardiac assessment.
• Arrhythmia, a common cardiovascular disease, presents diagnostic challenges due to its paroxysmal nature and reliance on manual observation.
• Wearable sensor technology offers continuous patient monitoring, necessitating automated detection methods.

Purpose of the Study:

• To review state-of-the-art ECG and PPG-based methods for automatic arrhythmia detection.
• To discuss preprocessing, feature extraction, and classification techniques relevant to cardiac signal analysis.
• To highlight wearable sensors, available databases, and limitations in current arrhythmia detection strategies.

Main Methods:

• Review of existing literature on ECG and PPG signal processing for arrhythmia identification.
• Analysis of preprocessing, feature extraction, and machine learning classification algorithms.
• Examination of wearable sensors and public datasets used in arrhythmia research.

Main Results:

• Comprehensive overview of ECG and PPG-based techniques for detecting various arrhythmias.
• Identification of current limitations in automated arrhythmia detection systems.
• Discussion of potential solutions and future directions for improving accuracy and reliability.

Conclusions:

• Automated detection of arrhythmia using ECG and PPG signals is crucial for effective cardiac monitoring, especially with wearable technology.
• Further research is needed to address the limitations of current methods and enhance the diagnostic capabilities for paroxysmal arrhythmias.
• Integration of advanced signal processing and machine learning with wearable sensors holds promise for improved cardiovascular disease management.