Data-driven pandemic response

Project overview

Our modern economy has proven to be quite susceptible to any local disruption that can impact our public health system. Amid the COVID-19 pandemic and continuous outbreaks, public health systems are under big pressure in many countries as their limited ability to handle unexpected events creates high patient numbers with potential collapse of the whole system. In this context, the assessment of infectious disease spread, and containment strategies is critical for controlling the timeframe and outcomes of pandemics.

Development of novel epidemic models that integrate modern machine learning (ML) methods to predict the virus spread from real epidemic data are key to analyse how the different public health intervention strategies can effectively influence the epidemic diffusion. This research aims at developing a novel ML framework able to estimate epidemiological parameters based on static and dynamic features of the data. This work would enable a unified understating of epidemic data to support decision-making within the community.

This project is funded by QUT Centre for Data Science.

Outcomes

  • ML-based modelling of complex populations during pandemic scenario.
  • A framework for the assessment of public health policy implementation.

Project team

Stefani Sotomayor

Dr Susanna Cramb

Associate Professor Darren Wraith



Aerial view of crowd connected by lines