Artificial intelligence is used to predict the need of ventilator for COVID-19 patients. The prediction is 84% accurate.
A new online tool to determine the need of ventilators for COVID-19 patients was developed by researchers at the Case Western Reserve University and is published in the Journal of Biomedical and Health Informatics. The tool was developed by analyzing 900 covid-19 patients and the prediction was 84% accurate. This helps the medical staff to decide which patient will need the ventilator.
COVID-19
Covid-19 infection is caused by RNA virus SARS-CoV-2. It affects the upper respiratory tract (nose, throat and lungs), it causes severe inflammation and even death. The other organs that are affected by the virus are heart, brain and kidney. Risk factors for the infection are older age, male gender and chronic diseases like obesity and diabetes.
Need for ventilators
Need for oxygen for severe COVID patients is one of the common symptoms. The ventilators ensure that the patients get continue and enough supply of oxygen when they breathe. From the beginning of the pandemic the number of ventilators needed outpaced the supply and at one point the physicians had to split the ventilator for patients. Vaccination reduced the rate of hospitalization and the need for ventilator.
According to Madabhushi – professor at the Donnell Institute “These can be gut-wrenching decisions for hospitals—deciding who is going to get the most help against an aggressive disease,”
The online tool uses the images of CT scan to see the severity of the infection and decides whether the patients need the ventilator or not.
“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.” Says Hiremath – author of the paper.
Advertisement
The information revealed that the COVID-19 related pattern were different compared to other diseases like H1N1.
Advertisement
Source-Medindia