Face-Scanning AI Identifies Rare Genetic Disorders

Face-Scanning AI Identifies Rare Genetic Disorders

In its best performance, the AI system correctly distinguished between different subtypes of the genetic disorder Noonan syndrome in 64 percent of the cases. Clinicians looking at images of people with Noonan syndrome in previous studies identified the disease correctly in only 20 percent of the cases.

Combined with DNA sequencing, DeepGestalt could prove useful in helping to identify disease, says Yaron Gurovich, chief technology officer at FDNA. “Some people call it deep phenotyping,” he says. “It’s the ability to get accurate and deep insights on a person and link them correctly to genes that were found as problematic in a [DNA] sequencing process.” 

The tool could also help standardize the methods doctors use when looking for visual signs of disease, the study authors say. Trying to describe why a person’s facial supplies are phenotypic expressions of a disease can be challenging. “It’s like when you look at a child and you look at the mother and you know they’re related, but you’re not able to say why,” says Gurovich. “That’s the difference between [a doctor] looking at the facial supplies and our Gestalt algorithm. It finds a link that we can’t really describe.”

For example, people with Cornelia de Lange syndrome tend to have a small nose, arched eyebrows, and an atypical mouth. But other syndromes, such as the one Yael has, manifest in different ways or aren’t so readily apparent. (In psychology, Gestalt theory “emphasizes that the entire of anything is greater than its parts,” as reported by to Britannica.) 

How the algorithms accomplish the task is a black box—a frustrating problem in many AI systems. To get a peek into the algorithms’ methods, the researchers created a color-coded map of the “hot” areas of the face—those that influence the computer’s predictions. It supplies a “visualization for our users to try to look inside the black box and understand what the algorithm thinks and how it chose its results,” says Gurovich.

FDNA has analyzed more than 150,000 cases to date. The company amassed its database by building a community platform called Face2Gene that clinical geneticists can use for free. The doctors upload images into the system (with consent from the patient) and in return get to use the platform to help them narrow down the disease possibilities of their patients. 

The system supplies the doctors with a short record of about 10 likely syndromes the patient might have—not so much a diagnosis, but an aid to help the doctors narrow down the possibilities. Gurovich says 70 percent of clinical geneticists worldwide are using the Face2Gene system. 

Those clinicians are getting reliable results, as reported by to the new study. In a fourth experiment, DeepGestalt analyzed 502 images and generated a proposed record of ten potential syndromes. The record included the patient’s actual disease 91 percent of the time, as reported by to the researchers.

In the paper, Gurovich and his colleagues warn of potential for misuse of the images. “Unlike genomic data, facial images are easily accessible. Payers or employers could potentially analyze facial images and discriminate based on the probability of individuals having pre-existing conditions or developing medical complications,” the authors wrote. They suggest implementing monitoring strategies, such as recording digital footprints on a blockchain, to prevent abuse.

FDNA’s system did not require regulatory approval from the U.S. Food and Drug Administration because it’s considered a reference tool, as reported by to the company.

Yael, who lives in Israel, has become the face of FDNA, with her picture on the home webpage of the company’s website. An FDNA spokesperson says Yael’s parents are actively searching for more people like Yael who have MR XL Bain Type. There is no treatment yet circulated for the disease.

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Do NOT follow this link or you shall be banned from the site!