The second wave of COVID-19 infections earlier this year wreaked havoc in several countries, including India, causing a shortage of ICU beds, oxygen cylinders and other essential medical supplies.
(Sign up to our Technology newsletter, Today's Cache, for insights on emerging themes at the intersection of technology, business and policy. Click here to subscribe for free.)
A new system developed by researchers at the University of Waterloo uses artificial intelligence (AI) to predict the necessity of ICU admission, allowing hospitals to manage their available resources better.
The system predicts ICU required based on over 200 vital data points including vital signs, blood test results and medical history. The software was trained using data from almost 400 cases at one of the largest hospitals in Brazil, which helped doctors decide if new COVID patients should be admitted for intensive care.
It is said to be more than 95% accurate, the team said in a study titled ‘Enhanced Prediction of ICU Admission for COVID-19 Patients via Explainability and Trust Quantification’.
Also Read | An algorithm to detect stress using smartwatches
The tool is meant to arm doctors with a faster and more efficient way of making informed decisions and ensuring patients’ needs are met based on past patient cases and outcomes, instead of replacing them altogether, the team noted.
The team has also made the software freely available to scientists and doctors worldwide to expand its capabilities.
The system will also be incorporated into an existing clinical decision support system, which is expected to help doctors detect COVID-19 in patients and determine its severity using AI analysis of medical images.
