Audio version of the article
Researchers developed an artificial intelligence tool that can determine if COVID-19 patients will need a ventilator.
Case Western Reserve University researchers developed an artificial intelligence tool that can predict whether a COVID19 patient needs help breathing with a ventilator. The tool was created by analyzing CT scans of nearly 900 COVID19 patients who died in 2020 diagnosed, developed and was able to predict a patient’s condition for a ventilator with an accuracy of 84 percent.
“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,” the Donnell Institute Professor of Biomedical Engineering at Case Western Reserve and head of the Center for Computational Imaging and Personalized Diagnostics (CCIPD), Anant Madabhushi said in a press release.
“It could also be important for hospitals as they determine how many ventilators they’ll need.”
Madabhushi said he intends to use these results to test the artificial intelligence tool in real time at university hospitals and at the Louis Stokes Cleveland VA Medical Center with COVID19 patients. If successful, medical staff at both hospitals could upload a digital image of a breast scan to a cloud-based app, then Case Western Reserve’s AI could analyze it and predict the need for a ventilator. Among the more common symptoms of severe COVID-19 is the need for patients to be placed on ventilators to ensure they have enough oxygen to breathe. Almost from the start of the pandemic, the number of ventilators needed to support patients has been far greater than those available.
While vaccination rates reduced hospitalization rates for COVID19 and reduced the need for ventilators, the Delta variant has again led to ventilator shortages in some parts of the United States.
“These can be gut-wrenching decisions for hospitals—deciding who is going to get the most help against an aggressive disease,” Madabhushi said.
Until now, clinicians have lacked a consistent and reliable way to determine which newly admitted COVID19 patients would need ventilators – information that could be invaluable to hospitals dealing with limited supplies. The research team began its study to provide such an AI tool by evaluating the initial scans taken from approximately 900 patients in the US and Wuhan, China, in 2020. Using deep learning and artificial intelligence, Madabhushi said, the scans showed distinctive features for patients who ended up in the intensive care unit (ICU) and needed ventilation.
“This tool would allow for medical workers to administer medications or supportive interventions sooner to slow down disease progression,” said Amogh Hiremath, a graduate student in Madabhushi’s lab and lead author on the paper
“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.”
According to Hiremath, patterns on the CT scans were not visible to the naked eye but were only revealed by the computers.