Facial Analysis Technology Identifies Williams-Beuren Syndrome Patients

Facial analysis technology can help identify the most characteristic and relevant facial features found in Williams-Beuren syndrome (WBS) in diverse populations.

In a study led by the National Human Genome Research Institute (NHGRI) that was recently published by the American Journal of Medicine Genetics this month, facial analysis technology was found to help identify the most characteristic and relevant facial features found in Williams-Beuren syndrome (WBS) in diverse populations.

The National Human Genome Research Institute (NHGRI), which is connected with the National Institutes of Health, led the study and used objective digital facial analysis technology from the Sheikh Zayed Institute for Pediatric Surgical Innovation at Children’s National Health System.

WBS is a genetic condition; however, the majority of cases are not inherited. The condition is most often characterized by cardiovascular issues, such as high blood pressure, as well as disability and distinctive facial features that include puffiness around the eyes, a short nose with a broad tip, full cheeks, and a wide mouth with full lips. Approximately 1 in 7,500 to 10,000 individuals are affected by WBS.

In the study, researchers compared 286 African, Asian, Caucasian, and Latin American children and adults with WBS by utilizing facial analysis technology with 286 patients that were of the same age, sex, and ethnicity who did not have the disease. Researchers correctly identified patients with the disease from each ethnic group with an accuracy of 95% or higher.

Periorbital fullness and intellectual disability were the most common clinical phenotype elements and were present in greater than 90% of the cohort. Malar flattening, long philtrum, wide mouth, and small jaw were additional characteristics of 75% or greater of all individuals with WBS.

When specific ethnic populations were analyzed as cohorts (P&#8208;value&thinsp;<&thinsp;0.001 for all comparisons), the test accuracy of the facial recognition technology significantly increased. There were also accuracies for Caucasian, African, Asian, and Latin American groups of 0.92, 0.96, 0.92, and 0.93, respectively. Overall, consistent clinical findings from global populations with WBS were presented and demonstrated the significance of facial analysis technology for clinicians when determining accurate WBS diagnoses.

“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,” stated Marius George Linguraru, DPhil, developer of the facial analysis technology and an investigator in the study from Children’s National in a recent statement.

Currently, Linguraru and his team are trying to create an easy tool that will allow doctors in clinics without state-of-the-art genetic facilities to image their patients on a smartphone and receive instant results.

The technology was also found to be highly accurate in identifying Noonan syndrome according to a study published in September 2017, DiGeorge syndrome (22q11.2 deletion syndrome) in April 2017 and Down syndrome in December 2016. Cornelia de Lange syndrome will be focalized in the next studies in the series.

For more news from the rare disease community, subscribe to Rare Disease Report®’s e-newsletter.