US researchers have developed an online tool using artificial intelligence (AI) to help medical staff quickly determine which COVID-19 patients will need help with breathing with ventilators. The Case Western Reserve University team developed the tool through analysis of CT scans of nearly 900 COVID-19 patients diagnosed in 2020, and is able to predict ventilator requirement with 84 percent accuracy.
“This can be important for clinicians as they plan how to care for a patient and, of course, the patient and their family get to know,” said Anant Madbhushi, a professor of biomedical engineering at Case Western Reserve. “It could also be important for hospitals because they determine how many ventilators they will need,” he said.
The more common symptoms of severe COVID-19 cases require patients to be put on ventilators to ensure they can continue to take in enough oxygen while they breathe.
Yet, almost from the start of the pandemic, the number of ventilators needed to support such patients far outweighed the available supplies, to the point that hospitals began to “split up” ventilators, a practice in which one ventilator is one ventilator. Helps more patients.
“It can be a serious decision for hospitals to make as to who will get the most help against an aggressive disease,” Madbhushi said.
The findings are detailed in the IEEE Journal of Biomedical and Health Informatics.
The team began its efforts to develop the tool by evaluating initial scans taken in 2020 from nearly 900 patients from Wuhan, in the US and China, in the first known cases of the disease caused by the novel coronavirus.
Madbhushi said those CT scans showed that deep-learning computers, or AI-assisted features, are typical for patients who later ended up in the intensive care unit (ICU) and needed help breathing. .
Amogh Hiremath, a graduate student in Madabhushi’s lab, said the CT scan could not be seen with the naked eye, but was only revealed by a computer.
“This device will allow medical workers to administer drugs or adjuvant interventions sooner to slow the progression of the disease,” Hiremuth said.
“And it will allow early identification of those at risk of developing severe acute respiratory distress syndrome, or death. These are the patients who are ideal ventilator candidates,” he said.
read all breaking news, breaking news And coronavirus news Here
.