For the families of children with rare diseases, the journey to a diagnosis is often measured in years. Multiple specialists. Confusing, overlapping symptoms. A sense that no one is quite seeing the whole picture.
ThinkRare was built to change that.
Developed at Ottawa's CHEO Research Institute, ThinkRare is a world-first AI algorithm embedded directly into the hospital's electronic medical record system. It doesn't wait to be asked. It continuously scans incoming clinical data in real time — blood tests, visit notes, diagnostic codes — and silently alerts care teams when a child's pattern of symptoms may point to an undiagnosed rare genetic condition.
The results have been remarkable. Since implementation, 41 children identified by ThinkRare have been referred to CHEO Genetics for testing. Of those with results, 70% have received a confirmed rare disease diagnosis — an extraordinarily high success rate that could save these families years of searching for answers.
Now ThinkRare is going national.
The CHEO Research Institute has announced that McMaster Children's Hospital is finalising external validation and local integration of the system. Alberta Children's Hospital and Stollery Children's Hospital are at the implementation planning phase. Further expansion is planned.
"ThinkRare shows what happens when clinicians, data scientists, and families come together to build meaningful, responsible AI," said Dr. Jason Berman, CEO and Scientific Director of the CHEO Research Institute. "It's remarkable success at CHEO — and now its national expansion — means more children and families across Canada will get the answers they need sooner."
There are approximately 300 million people living with rare diseases worldwide, most of them children. The average time to diagnosis is four to five years. For many families, that wait is a fog — watching a child struggle while no one can name what's wrong.
ThinkRare cuts through that fog. And now it's being handed to the whole country. 🧬