Artificial Intelligence Can Help Doctors Manage COVID-19

Chest X-rays used in the COVID-Net study show varying degrees of infection and opacity in the lungs of COVID-19 patients. Credit: University of Waterloo

The artificial intelligence (AI) technology developed by researchers at the University of Waterloo is capable of assessing the severity of COVID-19 cases with a promising degree of accuracy.

One study, which is part of the open source COVID-Net initiative launched over a year ago, involved researchers from Waterloo and the spin-off start-up company DarwinAI, as well as radiologists from the Stony Brook School of Medicine and the Montefiore. Medical Center in New York.

Deep-learning AI was trained to analyze the extent and opacity of infection in the lungs of COVID-19 patients based on chest X-rays. The scores were then compared to reviews of the same X-rays by expert radiologists.

For both magnitude and opacity, important indicators of infection severity, the AI ​​software’s predictions matched the human expert scores well.

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

“Assessing the severity of a patient with COVID-19 is a critical step in the clinical workflow to determine the best course of action for treatment and care, be it admitting the patient to the ICU, giving or administering oxygen therapy to a patient. a mechanical fan, ”Wong said.

“The promising results in this study show that artificial intelligence has strong potential to be an effective tool to support primary care health professionals in their decisions and to improve clinical efficiency, which is especially important given the amount of stress sustained pandemic has placed on the health care systems in the area. the world. ”

A paper on the study, “Towards Computer-Assisted Severity Assessment via Deep Neural Networks for Geographic and Opacity Scoring of SARS-CoV-2 Chest X-rays,” appears in the journal Scientific Reports.

Reference: “To computer-aided severity assessment via deep neural networks for geographic and opacity scores of SARS-CoV-2 chest radiographs” by A. Wong, ZQ Lin, L. Wang, AG Chung, B. Shen, A Abbasi, M. Hoshmand-Kochi, and TQ Duong, April 29, 2021, Scientific Reports.
DOI: 10.1038 / s41598-021-88538-4