University of California San Francisco, University of Colorado and University of Calgary researchers teamed up to create a prototype tool that uses 3D facial imaging tech to help clinicians diagnose genetic syndromes.
For the study, published in June in Genetics in Medicine, the research team created a personalized library of 3D facial images of 3,327 children and adults with 396 different genetic syndromes as well as 727 of their unaffected relatives and 3,003 other unaffected individuals from the U.S., Canada and the United Kingdom.
The researchers then used a database, which is hosted by National Institutes of Health-funded international consortium FaceBase, to train a machine-learning algorithm to identify most genetic syndromes included in the dataset. Based on facial shape, 96 percent of study subjects could be correctly classified as either unaffected or having a syndrome.
"We have designed a prototype with significant potential to become a clinical tool around the world," said Richard Spritz, MD, director of the human medical genetics and genomics program at University of Colorado medical school. "Our hope is that one day soon, our patients can securely take a photo of their face with a smart phone and send it to their [physician] for analysis in a confidential database."
The researchers concluded that the study supports a proof-of-concept for facilitating genetic diagnoses, but more research needs to be done before deploying a clinically available, privacy-protected digital tool. Currently, the approach uses 3D cameras but is expected to adapt to smart-phone camera tech as it continues to advance.