Improving ICU Capacity During COVID-19 Outbreaks
Harnessing AI to better manage ICU capacity during crisis.
Project Budget*- $1.3M
Partner Co-investment* - $0.4M
Supercluster Co-investment* - $0.9M
Access to intensive care is critical for public health. Prior to the COVID-19 pandemic, Canadian intensive care units (ICUs) were already operating at ~90% capacity and exceeded capacity on 50 days per year, on average. ICU overcrowding causes delays in critical care for patients that need it most – every hour that ICU admission is delayed for a patient results in a 1.5% increased risk of death.
Respiratory infections like pneumonia and influenza account for 20% of ICU admissions and are a leading cause of death worldwide prior to COVID-19. With COVID-19 driving an increased demand for the ventilators, specialized treatments, and close monitoring by doctors provided in ICUs, the entire health system is at greater threat of being overwhelmed.
The Predicting the Need for Intensive Care During COVID-19 Outbreaks project aims to change that by developing software that can predict COVID-19 in-patient outcomes based on radiological imaging. The software will predict if and when a patient will likely need to be admitted to the ICU as well as their expected date of discharge. This information will help clinicians better plan for ICU bed capacity, staffing, and ventilator availability.
Led by Altis Labs in partnership with Bayer AG, University Health Network, Trillium Health Partners, and QIPCM, the project will help ICUs manage capacity in the wake of COVID-19, which will deliver higher quality care, efficiency gains, and better patient outcomes. Hospitals will see less overcrowding.
The project will apply prediction technology to standard-of-care medical images of inpatients with pulmonary infections to predict ICU admission and their expected date of discharge. In addition, the machine learning-based software takes into account features in the chest that are indicative of comorbidities like pulmonary hypertension, cardiovascular disease, and COPD, all of which can impact outcomes of COVID-19 patients. This delivers a more comprehensive, robust, and generalizable predictions for clinicians. Published test results have shown that the software can improve prognostication by 68% for lung cancer patients.
The coalition will integrate the technology into a medical imaging platform that is already deployed in hospitals, so that the software can be quickly implemented across the health care system.
The project will start rolling out in the Greater Toronto area before expanding across Canada and potentially beyond to the rest of the world.
*amounts at time of project selection