Systems Biology Approaches to Understanding COVID-19 Spread in the Population

Area of Science:

• Systems biology
• Epidemiology
• Machine learning

Background:

• The COVID-19 pandemic highlights the need for advanced modeling of infectious disease dynamics.
• Complex systems like pandemics require simplified yet informative approaches for analysis.

Purpose of the Study:

• To demonstrate a combined dynamic modeling and machine learning approach for understanding infectious disease spread.
• To identify key factors influencing disease transmissibility using epidemiological data.

Main Methods:

• Utilizing compartmental epidemiological models to simplify complex systems.
• Applying machine learning techniques, specifically feature selection, to identify transmissibility drivers.
• Inferring epidemiological characteristics like basic and effective reproductive numbers.

Main Results:

• The study shows that combining dynamic modeling and machine learning is effective for analyzing disease spread.
• Key factors contributing to disease transmissibility can be uncovered through this integrated approach.
• The methodology is applicable to COVID-19 and other infectious diseases.

Conclusions:

• A hybrid approach of dynamic modeling and machine learning offers a powerful framework for epidemiological research.
• This methodology can enhance our understanding of infectious disease dynamics and inform public health strategies.
• The approach is versatile and can be applied to a wide range of epidemic scenarios.