New technology could help doctors make the most of limited resources during the COVID-19 pandemic by identifying key patients in need of intensive care treatment
Developed at the University of Waterloo and the alumni funded start-up DarwinAI, this new system has been using artificial intelligence (AI) to “predict the necessity of COVID-19 ICU admission based on more than 200 clinical data points, including vital signs, blood test results and medical history.”
Director of the Vision and Image Processing (VIP) Lab at Waterloo, Alexander Wong pointed out how this new technology is an “important step in the clinal decision support process for triaging patients and developing treatment plans.”
This new software was developed by researchers using previously obtained data from a hospital in Brazil, using this data the “neutral network” was created. The “Neutral Network” can predict the need for the ICU admission in new COVID cases with greater than 95 percent accuracy.
“This network can predict the need for the ICU admission in new COVID cases with greater than 95 percent accuracy”
The aim of this new use of AI is not to replace doctors, however prediction technology such as this has been designed to be used as a new tool to aid physicians in making faster and more informed decisions ensure patients the most need of intensive care are receiving it.
“The goal is to help clinicians make faster, more consistent decisions based on past patient cases and outcomes.”
Researchers have made this technology freely available ensuring engineers and scientists around the globe and use it to help control the impact of COVID-19 on resources and ensure patients are receiving the care they need.
AI’s impact on medicine cannot be understated and this study illustrates one of the many ways it continues to revolutionise and improve patient care.
Although AI and tech advances are welcome within the healthcare sector, nations are still struggling with staffing shortages and many are asking for the budget be used to solve this continuing issues.
Read more about this research here: COVID-Net Clinical ICU: Enhanced Prediction of ICU Admission for COVID-19 Patients via Explainability and Trust Quantification.
