Zika Virus Prediction Using AI-Driven Technology and Hybrid Optimization Algorithm in Healthcare

Area of Science:

• Public Health
• Infectious Diseases
• Artificial Intelligence

Background:

• The Zika virus outbreak in the Americas highlighted challenges in predicting geographic spread and infection rates.
• Inefficient resource allocation by public health agencies stemmed from a lack of accurate outbreak forecasting.
• RNA testing is crucial for identifying Zika virus infections.

Purpose of the Study:

• To develop a highly accurate forecasting model for the Zika virus outbreak.
• To improve the efficiency of public health surveillance and resource allocation.
• To enhance the secure communication of patient results.

Main Methods:

• A Hybrid Optimization Algorithm, specifically multilayer perceptron with a probabilistic optimization strategy, was trained using relevant characteristics.
• Machine learning algorithms and artificial intelligence methodologies were implemented within a MATLAB program.
• A hybrid cryptosystem combining Advanced Encryption Standard (AES) and Triple Data Encryption Standard (TDES) was used for data security.

Main Results:

• The Hybrid Optimization Algorithm achieved a high accuracy rate in forecasting Zika virus outbreak scope and infection frequency.
• The AI-driven system reduced forecast time while maintaining excellent prediction accuracy.
• The cryptosystem processing time was minimal (0.15s) with 91.25% accuracy in experimental outcomes.

Conclusions:

• The developed AI model significantly improves the accuracy of Zika virus outbreak prediction.
• The system enhances the efficiency of public health response and resource management.
• The secure data encryption method ensures accurate and timely communication of patient results.