Exploring Different Approaches to Epidemic Processes Simulation: Compartmental, Machine Learning, and Agent-Based Models

The COVID-19 pandemic has brought the issue of emerging diseases to the forefront of global public health concerns. The virus's rapid spread, which originated in Wuhan, China, and quickly spread worldwide, has highlighted the need for effective strategies to mitigate the impact of emerging diseases. Mathematical and simulation modeling has been increasingly used to develop and implement measures to reduce the spread of morbidity in epidemics. This approach has been beneficial in the case of COVID-19. This chapter discusses three main approaches to modeling infectious diseases: compartmental models, machine learning, and agent-based modeling, using COVID-19 as a case study. A review of the most highly cited papers on each approach was conducted, and the advantages and disadvantages of various models were highlighted. The analysis revealed that while each modeling approach has its strengths and limitations, the most effective strategy combines different approaches to take advantage of their strengths. For example, compartmental models can provide insight into the overall progression of an epidemic, while agent-based models can capture the complexity of individual interactions and behaviors. Machine learning models, on the other hand, can identify patterns and predict future trends, making them particularly useful for forecasting and decision-making. While no single modeling approach is perfect, combining different approaches can provide a more comprehensive understanding of the spread of infectious diseases and inform the development of effective public health interventions.