Matthew Kolisnyk and Karnig Kazazian, PhD candidates from Ontario, Canada-based Western University, have combined fMRI and machine learning to predict the survival of severe brain injury patients in the ICU. Their findings are published in the Journal of Neurology.
Kolisnyk and Kazazian study under neuroscientist Adrian Owen, PhD, at Schulich School of Medicine & Dentistry. “For years we’ve lacked the tools and techniques to know who is going to survive a serious brain injury,” says Owen.
Under the guidance of Loretta Norton, PhD, from King’s University College, who pioneered ICU brain activity measurement, a team from Western University, London Health Sciences Centre, and Lawson Institute assessed brain activity in 25 patients after severe injuries in a London ICU to predict survival outcomes.
“We previously found that information about the potential for recovery in these patients was captured in the way different brain regions communicate with each other,” says Norton. “Intact communication between brain regions is an important factor for regaining consciousness.”
The breakthrough occurred when the team realized they could combine this imaging technique with an application of AI known as machine learning. They found they could predict patients who would recover with an accuracy of 80%, which is higher than the current standard of care.
“Modern artificial intelligence has shown incredible predictive capabilities. Combining this with our existing imaging techniques was enough to better predict who will recover from their injuries,” says Kolisnyk.
While encouraging, the researchers say the prediction was not perfect and needs further research and testing. “Given that these models learn best when they have lots of data, we hope our findings will lead to further collaborations with ICUs across Canada,” says Kazazian.
Featured image: Using fMRI imaging and machine learning, graduate students Matthew Kolisnyk (left), Karnig Kazazian and their collaborators discovered they could predict which patients would recover from a serious brain injury with an accuracy of 80%. (Jeff Renaud/Western Communications)
