Facial Recognition Software Helps In Diagnosing Rare Genetic Disease
Researchers have successfully employed a facial recognition software in the process of diagnosing a rare genetic disorder in Africans, Asians and Latin Americans. The disease is known as the DiGeorge syndrome and it affects 1 in 3,000 to 1 in 6,000 children.
The research was carried out by scientists with the National Human Genome Research Institute, as part of the National Institutes of Health, along with their collaborators, and was published March 23 in the American Journal of Medical Genetics.
Facial Recognition Software Used In Detecting DiGeorge Syndrome
Although the disease is popular by the name DiGeorge or velocadriofacial syndrome, its medical name is 22q11.2 deletion syndrome.
The disorder causes multiple defects of the body, including heart problems, cleft palate, learning problems and a characteristic facial appearance. However, because of the very unusual symptoms, health specialists can't always pinpoint the disease, especially among very diverse populations.
The main purpose of the study is to help specialists and health care providers to recognize and diagnose the syndrome more easily, in order to deliver medical interventions earlier and more efficiently.
The software is all the more necessary as, according to Paul Kruszka, M.D., medical geneticist in NHRGI's Medical Genetics Branch, different syndromes appear differently depending on the part of the world, which makes it more difficult for specialists to promptly diagnose a series of diseases, especially among non-European populations.
As part of the research, the scientists analyzed information from 106 participants, as well as photographs of 101 subjects who suffered from the disease. The subjects were chosen from 11 different countries in Africa, Latin America and Asia, as the appearance of different subjects suffering from the disease was very different inside this group.
Then the team used facial analysis technology to address the disorder, comparing a group of 156 Caucasians, Latin Americans, Asians and Africans, who either suffered with the disease or who formed the control groups.
The diagnoses were then made, comparing 126 facial features. The diagnoses were correct 96.6 percent of the time, which makes this software a success in addressing this syndrome. Additionally, this technology is very helpful when it comes to diagnosing Down syndrome.
"[...] we present the varied findings from global populations with 22q11.2 DS and demonstrate how facial analysis technology can assist clinicians in making accurate 22q11.2 DS diagnoses. This work will assist in earlier detection and in increasing recognition of 22q11.2 DS throughout the world," noted the research.
Following this discovery, the researchers will focus on Noonan syndrome and Williams syndrome. Both of these diseases are rare. However, many clinicians reported having encountered them throughout their careers.
The Atlas Of Human Malformations In Diverse Populations
DiGeorge syndrome and Down syndrome are both included in the Atlas of Human Malformations in Diverse Populations, a program launched in 2016. Upon its completion, this atlas will represent a comprehensive and exhaustive database of distinct inherited diseases worldwide.
Additionally, the photos of these conditions will be accompanied by short descriptions of affected people. These descriptions would allow clinicians to search diseases based on a series of categories, from continental region to the phenotype or the syndrome.