Artificial Intelligence Predicts Ventilator Need of COVID-19 Patients

Case Western Reserve University researchers have developed an artificial intelligence tool that can predict if a COVID-19 patient will need help breathing with a ventilator.

The tool was created by analyzing CT scans from almost 900 COVID-19 patients diagnosed in 2020 and was able to predict a patient’s need for a ventilator with 84- percent accuracy.

“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 intends to is hoping to use these results to try out the AI tool in real-time at University Hospitals and Louis Stokes Cleveland VA Medical Center with COVID-19 patients. If successful, he said medical staff at the two hospitals could upload a digital image of a chest scan to a cloud-based application, then the AI at Case Western Reserve 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. From almost the start of the pandemic, the number of ventilators needed to support patients was far greater than what was available.

While vaccination rates reduced COVID-19 hospitalization rates and 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, physicians have lacked a consistent and reliable way to identify which newly admitted COVID-19 patients will need ventilators, information that could be invaluable to hospitals managing limited supplies.

The research team began its study to provide such an AI tool by evaluating the initial scans taken in 2020 from around 900 patients from the United States and Wuhan, China. With deep learning and artificial intelligence, Madabhushi said the scans revealed distinctive features for patients who ended up in the intensive care unit (ICU) and needed breathing assistance.

“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.