Privacy-Preserving Electrocardiogram Monitoring for Intelligent Arrhythmia Detection

Area of Science:

• Biomedical Engineering
• Cyber-Physical Systems
• Health Informatics

Background:

• Long-term electrocardiogram (ECG) monitoring is crucial for early arrhythmia detection.
• Previous research focused on monitoring and data analysis but often overlooked patient privacy.
• Cyber-physical systems offer potential for advanced remote health monitoring.

Purpose of the Study:

• To develop an intelligent heart monitoring system that prioritizes patient privacy and data security.
• To integrate ECG sensing, data analysis, and secure communication within a single system.
• To evaluate the system's effectiveness in heartbeat detection and classification while maintaining confidentiality.

Main Methods:

• Proposed an intelligent heart monitoring system comprising a wearable ECG sensor, remote station, and decision support server.
• Utilized the Pan-Tompkins algorithm for heartbeat detection and a decision tree for classification.
• Implemented signal scrambling, anonymous identity schemes, and public key cryptosystem for privacy and security.

Main Results:

• Achieved a 95.74% success rate in heartbeat detection.
• Attained nearly 96.63% accuracy in heartbeat classification.
• Successfully preserved user privacy and secured communications between system components.

Conclusions:

• The developed intelligent heart monitoring system effectively detects and classifies arrhythmias.
• The system demonstrates strong performance in data analysis while ensuring robust patient privacy and secure communication.
• This approach enhances the dependability of remote ECG monitoring systems.