AI algorithm successfully flags children with undiagnosed rare disorders

The CHEO Research Institute in Ottawa, Canada, is using artificial intelligence (AI) to identify children who might have an undiagnosed rare genetic disease.

The ThinkRare algorithm scans the hospital’s electronic health records with certain criteria to identify children seen by numerous specialists and clinics who have not been diagnosed with a rare genetic disorder. Those flagged by the algorithm then undergo genetic testing.

The first 3 children flagged by the algorithm have all been diagnosed with a rare disorder.

Dr. Kym Boycott, senior scientist at the CHEO Research Institute and chief of genetics at CHEO, estimates that the algorithm can identify up to 50 children with undiagnosed rare diseases a year.

“The ThinkRare algorithm is incredibly exciting and promising because it means we can help families find answers and get the care and support they need sooner,” said Dr. Boycott in a press release. “This algorithm is a game changer. Using AI to scour CHEO’s electronic health record based on set criteria, ThinkRare can accurately identify kids who may have an undiagnosed rare genetic disease and refer them to our clinic – something that may have never happened without it.”

References

Payne E. In a world-first, CHEO researchers use AI to find children with undiagnosed rare diseases. Ottawa Citizen. May 23, 2024. Accessed May 24, 2024. https://ottawacitizen.com/news/local-news/in-a-world-first-cheo-researchers-use-ai-to-find-children-with-undiagnosed-rare-diseases

World-first AI algorithm developed at CHEO leads to rare disease diagnosis for families. CHEO press release. May 23, 2024. Accessed May 24, 2024. https://www.cheo.on.ca/en/news/world-first-ai-algorithm-developed-at-cheo-leads-to-rare-disease-diagnosis-for-families.aspx