Insights & Analyses

Biometric facial recognition used to diagnose rare genetic disease

April 4, 2017

Facial recognition technology could have applications beyond secure authentication and identification — it could also be used to diagnose difficult-to-recognize diseases, new research shows.

The National Human Genome Research Institute has revealed that facial recognition software can help to diagnose a rare genetic disease known as DiGeorge syndrome. Found in African, Asian and Latin American children, it affects anywhere from 1 in 3,000 to 1 in 6,000 children.

Also known as velocardiofacial syndrome, it can cause multiple defects throughout a person’s body. But healthcare providers find it difficult to diagnose in diverse populations, which is where the National institutes of Health hope their research can help solve the issue.

The successful study utilized facial analysis technology to make correct diagnoses for all ethnic groups 96.6 percent of the time. The results were detailed in the latest issue of the American Journal of Medical Genetics.

Researchers hope to use the technology to be able to diagnose DiGeorge syndrome with a simple cell phone photo. Previously, facial recognition was also found to be accurate in diagnosing Down syndrome.

Researchers also plan to study biometric identification to diagnose Noonan and Williams syndromes, both of which are rare like DiGeorge, but are seen by many clinicians.

The NHGRI and its collaborators launched the Atlas of Human Malformations in Diverse Populations last September, cataloging photos and physical traits of people with different inherited diseases from around the world. Previously, diagnostic atlases featured photos of patients with northern European ancestry, but the new atlas includes people from Asia, the Indian subcontinent, the Middle East, South America, and sub-Saharan Africa.

“Human malformation syndromes appear different in different parts of the world,” said Paul Kruszka, M.D., M.P.H., a medical geneticist in NHGRI’s Medical Genetics Branch. “Even experienced clinicians have difficulty diagnosing genetic syndromes in non-European populations.”

The booming facial recognition market is expected to be driven in the near future by surveillance uses and government investment. But as the technology becomes more available and affordable, unexpected and unique uses for the technology, including diagnosing genetic issues, could become more common.