The University of Waterloo says a research team from the school has developed new artificial intelligence (AI) models that can predict which COVID-19 patients are most likely to have severe kidney injury outcomes while they are in hospital.
According to the school, the researchers used data from previous COVID-19 patient cases with known clinical outcomes to develop the potentially life-saving software.
UWaterloo says the AI models use clinical and biochemical markers such as serum ferritin levels, use of therapeutic heparin, heart rate and blood pressure to determine patterns that will help predict severe kidney-related outcomes for patients.
“There is tremendous potential for predictive AI models like this as they can greatly aid clinicians in identifying who needs help the most, and most urgently, to increase survival rates and reduce rates of serious injury,” professor Alexander Wong stated.
The AI technolology will also allow doctors to see which predictors determined the program’s results, so the doctor can have more confidence in the findings.
“AI models that provide not just predictions but the rationale behind the predictions can greatly improve trust and widespread adoption to support clinicians in their decision-making processes along the entire clinical workflow,” Wong explained. “That’s the power of explainable AI.”
The research was part of the COVID-Net project, which the school says has been responsible for other important discoveries, with the open-source work being shared around the globe.
“Hospitals are already extremely overburdened by the pandemic, especially with the recent surges due to Omicron and its subvariants and recombinants,” Wong said.
“Having AI models to help health-care workers identify who needs care in an efficient and effective manner can significantly reduce the burden, as well as the costs of health care.”
Waterloo says the models created in the research will be applicable to other diseases and conditions and that its team is already looking for other potential applications.
The school says the model and an explanation of the research can be found online.