U.S researchers develop AI to predict ventilator need in patients

As we move forward witnessing numerous waves of COVID-19, researchers in the U.S have developed an online tool using Artificial Intelligence (AI) that will help the medical staff determine patients who are in urgent need of a ventilator.

The group of researchers belonging to the Case Western Reserve University developed the tool, through analysis of CT scans from approximately 900 COVID-19 patients diagnosed in 2020. The accuracy of this tool is about 84 per cent.

Anant Madabhushi, Professor of Biomedical Engineering at Case Western Reserve said, "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."

He further added, "It could also be important for hospitals as they determine how many ventilators they'll need."

Since the pandemic started, there has been a massive requirement for ventilators in hospitals which have never been sufficient enough. There have been times where the hospitals had to split the ventilators because they couldn't determine the requirement initially.

"These can be gut-wrenching decisions for hospitals deciding who is going to get the most help against an aggressive disease," Madabhushi said.

Madabhushi also said that those CT scans revealed, with the help of deep-learning computers, or AI, distinctive features for patients who later ended up in the intensive care unit (ICU) and needed help breathing. The CT scans could not be seen by the naked eye, but were revealed only by the computers, said Amogh Hiremath, a graduate student in Madabhushi's lab.

"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," Hiremath said.

Source : DNA India