Technology iCOVID: Digital diagnosis on the horizon

iCOVID: Digital diagnosis on the horizon

Artificial intelligence could soon be used to detect COVID-19 and rank the severity of the disease.

A new research project funded by Charles Sturt University will train computers to help clinicians triage patients.

Existing artificial intelligence (AI) models can already distinguish between COVID-19 and pneumonia in a lung x-ray with 88 per cent accuracy.

Now, the Charles Sturt team are pioneering a world-first deep learning project which will combine images of X-ray, chest scans and breathing patterns with other factors such as age and risk factors.

Together, the results will produce a ‘corona severity’ score to determine those who need immediate medical attention.

Professor Manoranjan Paul says the pilot study into AI analysis would be complete by the end of the year.

“The proposed system will provide accurate diagnosis, prognosis and screening of patients who can be flagged for further review by a radiologist or clinician for possible treatment or quarantine,” he said.

Now more than ever, we are relying on our universities to lead the way. Show your support by signing the petition to #KeepItClever today.