Project taps into big data to determine the factors involved and develop a screening tool.
A new University of Alberta project aims to develop an AI-based screening tool to help doctors diagnose depression more precisely.
Depression affects millions of Canadians. It can affect quality of life, damage relationships, lower productivity and lead to suicide. A proper diagnosis is key to effective treatment, but making a precise diagnosis can be difficult because there are no biological tests and symptoms vary.
“We don’t have a clear picture of exactly where depression emerges, although researchers have made substantial progress in the biological underpinnings of depression,” said project leader Bo Cao, an assistant professor in the U of A’s Department of Psychiatry, Canada Research Chair in Computational Psychiatry and member of the Women and Children’s Health Research Institute.
“We know there are genetic and brain components but there could be other clinical, social and cognitive factors that can facilitate the precision diagnosis of depression.”
The project, backed by seed funding from a Precision Health Seed Fund Award, brings together scientists from Canada and the U.K. with expertise in computational psychiatry, artificial intelligence, psychology and cognitive neuroscience.
Using data from the U.K. Biobank, a biomedical database that contains genetic and health information for half a million people in the United Kingdom, the researchers will be able to access health records, brain scans, social determinants and personal factors for more than 8,000 individuals diagnosed with major depressive disorder (MDD). Researchers will compare their profiles with a control group of more than 200,000 people who have not had a diagnosis of depression. This will help determine whether MDD can be identified through social, personal and health records, and when genetic and MRI data are necessary to improve the diagnosis.
The team will develop and test a prototype of the machine learning tool over the next 18 months. If it proves effective, the model will be applied to Alberta health data to verify its effectiveness.
“Machine learning finds patterns in data,” explained collaborator Russ Greiner, professor in the Department of Computing Science and adjunct professor in the Department of Psychiatry, who was recently named as a Canada CIFAR AI Chair. In the last several years, his research has focused on using computational methods to help identify psychiatric problems, including attention deficit hyperactivity disorder, schizophrenia, autism and now depression.
Greiner says he is grateful to be in Alberta, where there is strong support for machine learning research. He helped start the Alberta Machine Intelligence Institute almost 20 years ago. It receives more than $2 million a year from the Alberta government for AI research.
Cao and Greiner, who are both members of the U of A’s Neuroscience and Mental Health Institute, are optimistic that advances in AI will lead to breakthroughs that help doctors diagnose mental illnesses and find the right treatment for each patient. The research is important—according to the Statistics Canada Community Health Survey on Mental Health, more than 11 per cent of Canadian adults will experience depression in their lifetimes.
“It will be a long journey,” said Cao. “Our goal is to provide precision medicine in mental health, but that’s going to take decades. However, we dare to work toward this goal now with the support of our university and other visionary philanthropists and agencies.”
Find out more about the innovative precision health research happening at the U of A.
Featured image: Psychiatry professor Bo Cao is leading a new project drawing on health data to develop an AI-based screening tool that could help doctors diagnose depression more precisely. (Photo: Ross Neitz)
This science news is confirmed by us from the University of Alberta
Provided by University of Alberta