Facial recognition tech helps with disease diagnosis
Researchers at the National Institutes of Health have successfully used facial recognition software to diagnose a rare, genetic disease in Africans, Asians and Latin Americans.
Affecting children, DiGeorge syndrome is a genetic disorder that results in multiple defects throughout the body, including cleft palate, heart defects, a characteristic facial appearance and learning problems. Diagnosing the disease is difficult, especially in non-European populations, because the appearance of those with the disease varies widely and the only available diagnostic tool until now featured photos of patients with northern European ancestry.
Using facial analysis technology similar to that used in airports and on Facebook, researchers at the National Human Genome Research Institute (NHGRI) compared a group of 156 Caucasians, Africans, Asians and Latin Americans with the disease to people without the disease. Based on 126 individual facial features, researchers made correct diagnoses for all ethnic groups 96.6 percent of the time, according to NIH officials.
This technology was also very accurate in diagnosing Down syndrome, according to a study published in December 2016. The same team of researchers will next study Noonan syndrome and Williams syndrome, both of which are characterized by mildly unusual facial features.
DiGeorge syndrome and Down syndrome are now part of the Atlas of Human Malformations in Diverse Populations, which was launched by NHGRI September 2016. When completed, the web-based atlas will consist of photos of physical traits of people with inherited diseases around the world. In addition to the photos, the atlas will include written descriptions of affected people and will be searchable by phenotype (a person's traits), syndrome, continental region of residence and genomic and molecular diagnosis.
"Healthcare providers here in the United States as well as those in other countries with fewer resources will be able to use the atlas and the facial recognition software for early diagnoses," said Dr. Maximilian Muenke, atlas co-creator and chief of NHGRI's Medical Genetics Branch. "Early diagnoses mean early treatment along with the potential for reducing pain and suffering experienced by these children and their families."
Researchers hope to further develop the facial recognition technology so that healthcare providers can one day take a cell phone picture of a patient, have it analyzed and receive a diagnosis.
Connect with the GCN staff on Twitter @GCNtech.