The new tool uses AI technology to assess the severity of lung infections and inform treatment

Artificial intelligence (AI) technology developed by researchers at the University of Waterloo can assess the severity of COVID-19 cases with promising accuracy.

Researchers from Waterloo and the spin-off start-up DarwinAI as well as radiologists from the Stony Brook School of Medicine and Montefiore took part in a study that is part of the open source initiative COVID-Net, which was launched more than a year ago part of the Medical Center in New York.

Deep learning AI was trained to analyze the extent and opacity of the infection in the lungs of COVID-19 patients using chest x-rays. The results were then compared to assessments of the same X-rays by experienced radiologists.

In terms of both extent and opacity, important indicators of the severity of infections, the predictions made by the AI ​​software agreed well with the results provided by the human experts.

Alexander Wong, professor of systems design and co-founder of DarwinAI, said the technology could provide an important tool for doctors to help them manage cases.

“Assessing the severity of a patient with COVID-19 is a critical step in the clinical workflow in determining the best course of action for treatment and care, whether it be admitting the patient to intensive care, receiving oxygen therapy, or putting on a patient mechanical ventilator, ”said Wong.

“The encouraging results from this study show that artificial intelligence has strong potential to be an effective tool in helping healthcare workers at the forefront of making decisions and improving clinical efficiency. This is especially important as the ongoing pandemic has put a heavy strain on health systems around the world. “

The journal published an article on research into computer-aided severity assessment using deep neural networks to assess the geographic and opacity levels of SARS-CoV-2 chest x-rays Scientific reports .

###

LEAVE A REPLY

Please enter your comment!
Please enter your name here