Sign In

Communications of the ACM

ACM TechNews

Facial Recognition Software Helps Diagnose Rare Genetic Disease

View as: Print Mobile App Share:
A young boy undergoes facial recognition software analysis.

Researchers with the National Human Genome Research Institute, part of the U.S. National Institutes of Health, and their collaborators, have successfully used facial recognition software to diagnose a rare genetic disease in Africans, Asians, and Latin Am

Credit: Paul Kruszka, et al.

Researchers at the National Institutes of Health's National Human Genome Research Institute have used facial-recognition software to diagnose a rare genetic disease in Africans, Asians, and Latin Americans known as DiGeorge syndrome and velocardiofacial syndrome.

The team examined clinical data of 106 participants and photos of 101 participants with the disease from 11 African, Asian, and Latin American countries.

Using facial analysis technology, the researchers compared a cohort of 156 Caucasians, Africans, Asians, and Latin Americans with the syndrome to people who did not have it. Researchers made correct diagnoses for all ethnic groups 96.6% of the time using 126 individual facial features.

The researchers added DiGeorge syndrome to the Atlas of Human Malformations in Diverse Populations, which will feature photos of physical traits of people with different genetic diseases, along with written descriptions. The Atlas will be searchable by phenotype, syndrome, continental region of residence, and genomic and molecular diagnosis.

From National Institutes of Health
View Full Article


Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account