A priority queue-based telemonitoring system for automatic diagnosis of heart diseases in integrated fog computing...

Area of Science:

• Healthcare technology
• Computer science
• Artificial intelligence

Background:

• Distributed fog and edge computing offer reduced latency for healthcare data processing compared to traditional cloud computing.
• Existing fog computing models for healthcare systems exhibit limitations in enhancing overall system performance and patient response times.

Purpose of the Study:

• To propose a novel performance model integrating fog computing, priority queues, and certainty theory for edge computing devices.
• To enhance the efficiency of clinical decision support systems (CDSS) in healthcare, specifically for heart disease patient analysis.

Main Methods:

• A new model was developed by incorporating fog computing, priority queues, and certainty theory within edge computing devices.
• Certainty Factor (CF) values were assigned to heart disease symptoms for patient condition evaluation in the fog layer.
• Patient requests were categorized into priority queues within the fog layer for optimized processing.

Main Results:

• The proposed model demonstrated significant improvements: 25.55% reduction in network usage, 42.92% decrease in latency, and 34.28% improvement in patient request response time compared to cloud models.
• Integration of CF values and priority queues in the fog layer enhanced system Quality of Service (QoS).

Conclusions:

• The novel fog computing model effectively addresses limitations of existing systems in healthcare applications.
• Prioritizing patient requests based on CF values in CDSS significantly boosts system QoS and reduces patient response times, offering a more efficient healthcare solution.