Researchers design a CT-based AI tool to assist staff in determining which patients will need a ventilator

A CT-based AI tool to assist medical staff in determining which COVID-19 patients will need a ventilator has been designed by researchers at Case Western Reserve University, Ohio.

The team analysed CT scans from almost nine hundred COVID-19 patients diagnosed in 2020 and predicted ventilator need with eighty-four per cent precision.

Head of the Center for Computational Imaging and Personalised Diagnostics and the Donnell Institute Professor of Biomedical Engineering, Case Western Reserve, Anant Madabhushi, stated: “That could be important for physicians as they plan how to care for a patient, and of course, for the patient and their family to know. It could also be important for hospitals as they determine how many ventilators they’ll need.”

Madabhushi hopes to use the results to attempt the computational tool in real-time at Louis Stokes Cleveland VA Medical Center and University Hospitals with COVID-19 patients.

Medical staff at the two hospitals could upload a digitised image of the chest scan, if successful, to a cloud-based application to be analysed and predict whether the patient would require a ventilator.
The research was published in IEEE Journal of Biomedical and Health Informatics.

Lead author on the paper and a graduate student in Madabhushi’s lab, Amogh Hiremath, stated: “This tool would allow for medical workers to administer medications or supportive interventions sooner to slow down disease progression. And it would allow for early identification of those at increased risk of developing severe acute respiratory distress syndrome – or death. These are the patients who are ideal ventilator candidates.”