COVID-19 Prevention Strategies for Victoria Students within Educational Facilities: An AI-Based Modelling Study

Area of Science:

• Epidemiology
• Public Health
• Data Science

Background:

• Educational institutions are significant hubs for SARS-CoV-2 transmission in Victoria.
• Despite preventive measures, individuals under 20 represented over a quarter of state infections (2020-2022).
• A notable difference in infection rates was observed between the 0-9 and 10-19 age groups.

Purpose of the Study:

• To investigate risk factors for COVID-19 infection within Victorian educational settings.
• To analyze the effectiveness of various preventive measures across different age groups (0-9 and 10-19).

Main Methods:

• Utilized an incremental deep learning recurrent neural network-gated recurrent unit (RNN-GRU) model.
• Simulations incorporated three risk dimensions: school-related, student-related community, and general population factors.
• Data analysis focused on infection cases in Victoria from 2020 to 2022.

Main Results:

• School-initiated contact tracing, vaccination policies, testing, and face coverings showed significant associations with COVID-19 prevention in educational settings.
• Factors like state and international travel controls, and school closures had varying effectiveness between the 0-9 and 10-19 age groups.
• The 10-19 age group experienced higher infection rates compared to the 0-9 group.

Conclusions:

• Targeted preventive strategies are essential for educational institutions to curb SARS-CoV-2 spread.
• Specific interventions demonstrate differential effectiveness based on age groups within the school environment.
• Enhanced preventive support is recommended for younger populations, particularly adolescents aged 10-19.