Research to better diagnose COVID-19
Radiologists at Vancouver General Hospital, the University of British Columbia, and Vancouver Coastal Health Research Institute are leading an international study to better predict the presence of COVID-19 based on CT scans. Radiologists, fellows, residents, and UBC medical students are collecting, analyzing, and labeling thousands of CT scans, and in some cases chest X-rays, from COVID-19 patients around the globe. Information gleaned from the scans will form the basis for an open source artificial-intelligence model to predict the presence, severity, and complications of COVID-19 on CT scans. The model will integrate clinical data to help support and supplement existing tools to improve patient care. For example, it could help physicians determine whether individuals are best treated at home or whether they may require hospitalization/ventilation. It will not replace current testing. The model will also assist in detecting similarities and differences in variations of patterns across different cultural and ethnic groups, and help researchers understand early and late stages of patterns of disease. It could also help flag those who may ultimately develop permanent lung damage/fibrosis. Researchers are confident this new tool will help them predict disease severity and its clinical impact in different patient populations.
Once developed, the new artificial-intelligence model will be piloted at Vancouver General Hospital with an aim to embed it in routine diagnostic procedures to improve the accuracy of COVID-19 diagnostics.
Funding for this project is provided by the UBC Community Health and Wellbeing Cloud Innovation Centre (UBC CIC), opened in January 2020 and powered by Amazon Web Services (AWS), as well as the AWS Diagnostic Development Initiative (DDI).
For more information about the project, visit https://cic.ubc.ca/covid-19-ct-scans.
That is great work, UBC radiology department is a leading institute in the field of research, I’ll be honored to participate in such hot research.