UBC & Vancouver General Hospital Lead AWS-Powered AI Initiative for Superior COVID-19 Diagnosis

Apr 25, 2020 | Amazon Web Services, Artificial Intelligence, AWS, Cloud Technology, Coronavirus, COVID-19, Diagnosis, University of British Columbia, Vancouver General Hospital

UBC & Vancouver General Hospital Lead AWS-Powered AI Initiative for Superior COVID-19 Diagnosis

An artificial intelligence study led by Vancouver clinical physicians and researchers gains momentum as they combine thousands of chest images of COVID-19 patients from around the world. By collecting thousands of CT scans and X-rays from all corners of the globe (from China to the Middle East), radiologists from Vancouver General Hospital (VGH), the University of British Columbia (UBC), and Vancouver Coastal Health Research Institute leads an international study to better predict the presence of COVID-19 based on CT scans. The study is led out of the UBC Community Health and Wellbeing Cloud Innovation Centre.

The Study

An intense worldwide effort led out of the beautiful city of Vancouver, BC—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—from Canada and the Middle East to China, South Korea, and Italy.

How are they using Artificial Intelligence?

As the study team accumulates data, they are leveraging AI algorithms—in this case, an open source AI 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, reports the Vancouver Coastal Health Research Institute in a news release.

What are some examples of the utility of this approach?

The tool could help physicians determine whether individuals are best treated at home or whether they may require hospitalization/ventilation. However, this will not replace testing. Dr. Kendall Ho, VHG emergency physician and Academic Director, UBC Cloud Innovation Centre commented, “the model will also assist in detecting similarities and differences in variations of patterns across different cultural and ethnic groups, and help us understand early and late stages of patters of disease.” It could also help flag those who may ultimately develop permanent lung damage/fibrosis.

Dr. Savvas Nicolaou, Director of Emergency and Trauma Radiology at VGH—and leader of the project along with Dr. William Parker of VGH/UCBC—commented on the potential value of this tool: “We know the lungs of COVID-19 patients are white and hazy, like a white-out blizzard.” Dr. Nicolaou continued, “Currently, we can’t predict disease severity and its clinical impact in different patient populations. We’re confident this new tool will help us do that.”

What is next for the AI model?

Well, it isn’t complete yet. However, once it is fully developed, the AI model will be piloted at Vancouver General Hospital with the goal of embedding it into routine diagnostic procedures to improve accuracy of COVID-19 diagnostics.

Who is funding this initiative?

UBC Community Health and Wellbeing Cloud Innovation Centre (UBC CIC)—powered by Amazon Web Services (AWS) as well as the AWS Diagnostic Development Initiative.

UBC Community Health and Wellbeing Cloud Innovation Centre?

UBC and Amazon Web Services announced this first university-based cloud innovation center in Canada in 2019. The first of its kind, the center offers UBC students, staff, and faculty access to cloud technology to advance projects, along with employing Amazon’s innovation processes.

Lead Research/Investigators

Dr. Savvas Nicolaou, Director of Emergency and Trauma Radiology at VGH

Dr. William Parker, Radiology Resident, Vancouver General Hospital/UBC

Call to Action: Interested in learning more? TrialSite News will invite some of the participants on to the TrialSite News Podcast.


Pin It on Pinterest