An intelligent system for predicting and preventing MERS-CoV infection outbreak

Area of Science:

• Public Health Informatics
• Epidemiology
• Cloud Computing in Healthcare

Background:

• Middle East Respiratory Syndrome-Coronavirus (MERS-CoV) is a highly contagious airborne disease with a significant mortality rate.
• Effective prediction and prevention strategies necessitate real-time analysis of user health data and geographic location.
• Cloud computing offers scalable, flexible, and cost-effective solutions for developing advanced healthcare systems.

Purpose of the Study:

• To propose an effective cloud computing system for predicting MERS-CoV infected patients.
• To provide a geographic-based risk assessment for controlling MERS-CoV outbreaks.
• To leverage geographic positioning for early quarantine and public health management.

Main Methods:

• Development of a cloud computing system integrating user health data and geographic information.
• Utilizing a Bayesian belief network for MERS-CoV infection prediction.
• Employing geographic positioning system (GPS) data for spatial risk assessment and visualization on Google Maps.

Main Results:

• The proposed system achieved high accuracy in classifying MERS-CoV infected patients.
• The system provided appropriate geographic-based risk assessment, identifying high-risk areas.
• Synthetic data testing on 0.2 million users demonstrated the system's effectiveness.

Conclusions:

• The developed cloud computing system is effective for predicting MERS-CoV infections and assessing geographic risk.
• Real-time geographic mapping of infected individuals facilitates early quarantine measures.
• This approach enhances public health management by enabling citizens to avoid exposure and agencies to respond efficiently.