Written By: Longjam Dineshwori | Updated : September 6, 2021 2:31 PM IST
Beware if the new onset of diabetes due to Covid-19.
Severe COVID infection can lead to a drop in oxygen levels, making the patients difficult to breathe. Silent hypoxemia (low oxygen in your blood) is linked to several Covid-related deaths. Ventilators can be lifesaving for COVID-19 patients with severe respiratory symptoms and ensuring timely oxygen supply is important. However, to date, identifying which newly admitted COVID-19 patients are more likely to need ventilators to breathe has been a challenge for physicians. Now, researchers at Case Western Reserve University have developed an online tool that can accurately predict ventilator need in COVID patients.
According to the researchers, they analysed CT scans from nearly 900 COVID-19 patients diagnosed in 2020 to develop the tool, which can medical staff quickly determine who will need help breathing with a ventilator with 84% accuracy.
Knowing which COVID-19 patients will need a ventilator could help physicians plan how to care for a patient and hospitals to determine how many ventilators they'll need, said Anant Madabhushi, the Donnell Institute Professor of Biomedical Engineering at Case Western Reserve and head of the Center for Computational Imaging and Personalized Diagnostics (CCIPD).
The medical staff can upload a digitized image of the patient's chest scan to a cloud-based application, where deep-learning computers, or Artificial Intelligence (AI) would analyze it and predict whether that patient would likely need a ventilator, Madabhushi explained.
The research team used CT scans taken in 2020 from nearly 900 patients from the U.S. and from Wuhan, China to test the accuracy of the tool. It helped them spot distinctive features in patients who later ended up in the intensive care unit (ICU) and needed help breathing. The patterns on the CT scans revealed by the computers couldn't be seen by the naked eye, stated Amogh Hiremath, a graduate student in Madabhushi's lab and lead author on the paper
"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, as quoted by Science Daily.
Their research results were published this month in the IEEE Journal of Biomedical and Health Informatics. Madabhushi and his team will be testing the computational tool in real time at University Hospitals and Louis Stokes Cleveland VA Medical Center with COVID-19 patients.
