University of British Columbia

Published purpose

The COVID-19 pandemic has exposed weaknesses in public health preparedness and response to infectious diseases. A major challenge has been real-time policy and resource planning: policy analysts have limited tools to explore policy options and their impact on the trajectory of the pandemic, with a lot of their work being based on exploring predefined scenarios. Moreover, the impact of policy options on socioeconomic factors usually is decoupled from the public health analysis leading to less ideal actions that might in turn impact mental and physical health in the population. In the case of COVID-19, for example, large-scale social distancing measures enacted in response to the current pandemic were effective at limiting the spread of SARS-CoV-2; however, these measures are unsustainable interventions for long periods of time, and have shown to affect the economy, education and the mental health of many members of society. With the number of COVID-19 cases falling, quantifying the impact of lifting these policies on public health has been a major challenge for policy analysts, once again showcasing the need for tools that can support such analysis. Another major issue in analyzing the COVID-19 pandemic has been the high uncertainty in the data available about the disease and its impact on the population. Quantifying these uncertainties and their impact on model results is key to developing a proper course of action. The aim of this project is to resolve the problems highlighted above by automating the process of exploring policy options for controlling the spread of infectious diseases. Coupling artificial intelligence tools with strong agent-based epidemiological models and models of other socioeconomic factors affected by policy interventions, The University of British Columbia (UBC) believes it can improve situational awareness and policy planning in face of a pandemic like COVID-19.