An Agent-based Decision Support for a Vaccination Campaign.

Area of Science:

• Epidemiology
• Computational modeling
• Public health

Background:

• Coronavirus disease 2019 (Covid-19) spread poses significant public health challenges.
• Effective vaccination strategies are crucial for controlling infectious disease outbreaks.
• Agent-based modeling offers a powerful tool for simulating complex epidemiological dynamics.

Purpose of the Study:

• To explore Covid-19 diffusion using a large-scale agent-based model (1:1000 population scale).
• To simulate and evaluate diverse vaccination strategies.
• To investigate artificial intelligence (AI) techniques for optimizing public health policy decisions.

Main Methods:

• Development of an agent-based model in NetLogo simulating an Italian region.
• Integration of genetic algorithms to determine optimal vaccination criteria.
• Simulation of various vaccination scenarios and analysis of their impact on disease spread.

Main Results:

• The model successfully simulated Covid-19 diffusion dynamics at a regional scale.
• AI-driven optimization identified effective vaccination rates tailored to different population types over time.
• The methodology demonstrated promise for data-driven public health policy formulation.

Conclusions:

• Agent-based modeling combined with AI presents a viable approach for enhancing infectious disease control strategies.
• The findings support the application of agent-oriented methods in public healthcare policy.
• Optimized vaccination strategies can significantly impact disease containment efforts.