UniSA helping to protect Defence against bio threats

The University of South Australia is leading a project involving using data from consumer wearable devices to detect early signs of infection in a person, with the goal of better protecting defence personnel against biological and chemical warfare threats.

The university is working with the Department of Defence, industry partner Insight Via Artificial Intelligence and the University of Adelaide on the project, which involves developing statistical machine learning algorithms to detect signs of infection to monitor the health of military personnel.

The project also involves instigating early treatment for infections where necessary and ensuring people working in the armed forces are fit for duty.

Lead researcher UniSA Professor Siobhan Banks said consumer wearable devices measure biometric data that can help detect infections well before observable symptoms occur.

“Consumer wearable devices continuously measure vital signs, including heart rate, skin temperature and sleep, creating huge sets of data for each person. Changes in these parameters occur very quickly after infection as part of the immune response,” she said.

“Most diagnostic methods involve sampling blood or nasal fluid to detect pathogens responsible for infections. This approach is costly, time-consuming and requires a laboratory for analysis.”

The project will develop a cloud service that links to wearable devices and a smart phone application, with the potential to collect thousands of hours of continuous health data at a low cost and low burden to Defence.

“What if we could make use of this passively recorded data to detect the earliest molecular and cellular physiological events, caused by pathogen exposure, even prior to active infection?” Banks said.

The project forms part of Defence’s ‘Operating in Chemical, Biological, Radiological and Nuclear Environments’ STaR Shot program, and is being supported by the Defence Science and Technology Group and the Defence Artificial Intelligence Research Network.

Image credit: iStock.com/Tippapatt