A Survey of Heart Anomaly Detection Using Ambulatory Electrocardiogram (ECG)

Area of Science:

• Biomedical Engineering
• Cardiology
• Artificial Intelligence

Background:

• Cardiovascular diseases (CVDs) are the leading global cause of death, necessitating early detection and treatment.
• Ambulatory monitoring devices collect extensive biometric and electrocardiogram (ECG) signals, but raw data analysis is time-consuming.
• Automated anomaly detection in ECG signals offers a potential solution to assist clinicians in diagnosing cardiac conditions.

Purpose of the Study:

• To review the current state-of-the-art in automatic anomaly detection for ECG signals.
• To discuss the advantages and disadvantages of existing devices and algorithms for ECG analysis.
• To identify future research directions for advanced ambulatory cardiac monitoring systems.

Main Methods:

• Literature review of current technologies and algorithms for ECG anomaly detection.
• Analysis of pros and cons of various devices and signal processing techniques.
• Exploration of research gaps and future trends in ambulatory cardiac monitoring.

Main Results:

• Current devices can record extensive patient data but pose challenges in raw signal interpretation.
• Automatic anomaly detection systems show promise as assistive tools for medical professionals.
• Significant variations exist in the efficacy and application of different detection algorithms.

Conclusions:

• Automated ECG analysis is crucial for efficient diagnosis and management of cardiovascular diseases.
• Further research is needed to optimize algorithms and develop next-generation monitoring systems.
• Integration of advanced AI in ambulatory monitoring can significantly improve patient outcomes.