A new study has shown that researchers have successfully used facial analysis technology and clinical information to successfully identify patients with Williams-Beuren syndrome, a rare condition that causes cardiovascular problems and intellectual disability.
Though Williams-Beuren syndrome is a genetic condition, most case are not inherited. It affects about
1 in 7,500 to 10,000 people. People with the condition have distinctive facial features including puffiness around the eyes, a short nose with a broad tip, full cheeks, and a wide mouth with full lips.
Researchers at Children’s National Health System are working to create a simple tool that will enable doctors in clinics without state-of-the-art genetic facilities to take photos of their patients on a smartphone and receive instant results. The technology allows users to compare the most facial features characteristic of Williams-Beuren syndrome in diverse populations.
Researchers compared 286 African, Asian, Caucasian, and Latin American children and adults with Williams-Beuren syndrome with 286 people of the same age, sex and ethnicity without the disease. They were able to correctly identify patients with the disease from each ethnic group with 95 percent or greater accuracy. The study, led by the National Human Genome Research Institute, was published in the May 2018 issue of the American Journal of Medical Genetics.
“Our algorithm found that the angle at the nose root is the most significant facial feature of the Williams-Beuren syndrome in all ethnic groups and also highlighted facial features that are relevant to diagnosing the syndrome in each group,” said Marius George Linguraru, developer of the facial analysis technology and an investigator in the study from Children’s National.
This Williams-Beuren syndrome study will be used in the NIH’s Atlas of Human Malformation Syndromes in Diverse Populations, a free resource to help healthcare providers better recognize and diagnose the rare disease in non-Europeans and deliver critical, early interventions and better medical care.
Previous studies of the technology have found It accurate in identifying
Noonan syndrome, DiGeorge syndrome (22q11.2 deletion syndrome), and Down syndrome. The next study in the series will focus on Cornelia de Lange syndrome.
Photo: Marius George Linguraru, developer of the facial analysis technology and an investigator in the study from Children’s National