Artificial intelligence combined with novel data sources to improve the public health response to infectious diseases

Principal Advisor: Dr Amalie Dyda

Phone: +61 7 3365 5393

Organisational unit: School of Public Health

This research will investigate the utility of using multiple data sources to train disease prediction models to enhance infectious disease surveillance. The key to effective public health management of infectious diseases is timely and detailed information about the spread of infection and who is being affected. Recently, novel methods of surveillance using social media and crowd sourced data in conjunction with machine learning methods have been used to predict disease outbreaks. These types of data provide benefits over traditional sources as they are generally publicly available and can provide additional timeliness. This work has focused on the use of one primary data source, with initial investigation into combining of a number of data sources showing increased timeliness. To date, these approaches have not been investigated in the Australian context.