Portable Holter with Cloud-Based Learning Analytics for Real-Time Health Monitoring

Area of Science:

• Cardiology and Medical Devices
• Biomedical Engineering
• Machine Learning in Healthcare

Background:

• Rising incidence of cardiovascular diseases necessitates improved heart health monitoring solutions.
• Conventional Holter monitors present limitations in terms of bulkiness and user convenience.

Purpose of the Study:

• To introduce a novel wireless device, the Smart Portable Holter, for real-time cardiac monitoring.
• To enhance early detection of heart irregularities with improved accuracy and user convenience.
• To leverage machine learning for advanced cardiac event analysis.

Main Methods:

• Continuous electrocardiogram (ECG) signal acquisition via a wireless, portable device.
• Secure cloud-based data transmission and processing.
• Analysis using machine learning models: Random Forest and Extreme Gradient Boosting (XGBoost).

Main Results:

• The Smart Portable Holter achieved 98% accuracy in detecting cardiac events.
• Demonstrated high reliability in identifying cardiac arrhythmias using real-world datasets.
• The device's compact, wireless design significantly improved user comfort and compliance.

Conclusions:

• The Smart Portable Holter represents a significant advancement in portable cardiac monitoring.
• Combines portability, real-time analytics, and high diagnostic accuracy for proactive heart health.
• Empowers patients and healthcare providers with actionable insights for early diagnosis and personalized treatment.