Remote patient monitoring system combining hardware and artificial intelligence based software

Area of Science:

• Biomedical Engineering
• Artificial Intelligence
• Cardiology

Background:

• Remote patient monitoring is crucial for managing chronic conditions.
• Arrhythmia detection requires accurate and timely analysis of physiological data.
• Existing systems may lack the precision needed for early clinical intervention.

Purpose of the Study:

• To develop a novel remote patient monitoring system.
• To implement a customized Deep Neural Network (DNN) for enhanced arrhythmia detection.
• To create a decision support tool for healthcare providers.

Main Methods:

• Integration of IoT-based biomedical sensors for real-time data collection.
• Development of a customized Deep Neural Network (DNN) for data analysis.
• Implementation of user-friendly mobile and desktop interfaces for alerts and summaries.

Main Results:

• The DNN model achieved a test accuracy of 99.94%, recall of 99.92%, and precision of 99.57%.
• The system demonstrated very low false positive and false negative rates.
• High-performance classification integrated into accessible interfaces.

Conclusions:

• The developed remote patient monitoring system shows significant potential for clinical application.
• The AI-driven approach enables early and reliable detection of heart abnormalities and arrhythmia.
• The system can serve as a valuable decision support tool for healthcare personnel.