Tech

This application can diagnose rare diseases from a child’s face

In 2012, my death Shniberg sold his facial recognition startup to Facebook and began looking for a new challenge. “We wanted to take our experience and do something good,” he says.

Then he met the head of the Medical Genetics Center who explained the difficulty of diagnosing rare genetic disorders in children. Specialists sometimes use the shape and appearance of a child’s face as a guide because some conditions, such as Down syndrome, give a child’s face a distinct appearance. But for many other diseases, the signs are more subtle, and cases are very rare.

This got Schneeberg’s mind racing. “We knew right away that we could really help,” he says.

In 2014, Shniberg’s new startup, FDNA, launched an app called Face2Gene. It is built around a machine learning algorithm like the one he used earlier to identify individuals. Only the FDNA algorithm analyzes the face to suggest genetic disorders a person may have.

Face2Gene is now used by thousands of geneticists around the world. Its basic algorithm can identify around 300 disturbances with high accuracy from a patient’s face. This is a boon for geneticists and families looking for a diagnosis – but the facial algorithm still can’t see most genetic conditions. And for the rarer, the FDNA does not have the seven or more images from different patients needed to train the disorder detection algorithm.

Last month, scientists from FDNA and several international institutions published results from a new algorithm called GestaltMatcher that they say can discriminate about 1,000 cases — nearly three times more than the original FDNA algorithm. It’s now available in the Face2Gene app.

A tough case from 2017 helped demonstrate the new approach. Two unrelated families in Norway and Germany sought help from local doctors for a son with developmental problems, tremor, and an unusually triangular face. For the two boys, tests for known genetic conditions turned out to be blank. Doctors in each country independently used genetic sequencing to discover that each child had a previously undescribed mutation in a gene called LEMD2.

The two teams were linked through a site called GeneMatcher that helps researchers find others confused about conditions involving the same gene. The boys’ similar symptoms strongly suggest that the rare mutation they share is the cause, but the researchers looked for additional clues. They obtained it from a combination of traditional biology research and an experimental algorithm from researchers at the University of Bonn collaborating with FDNA.

Laboratory studies have suggested that the boys’ mutation has similar effects on their cells to progeria, a potentially fatal genetic disorder in which patients also have distinct triangular faces. It is caused by mutations in genes with functions similar to LEMD2.

An experimental algorithm, a prototype inspired by the Face2Gene device, backed up those results. He did not attempt to identify the specific disorder of a person in the photograph. Instead, it calculated how similar the face was to the other patients. She stated that Norwegian and German boys have very similar faces, despite their different moral backgrounds. Their faces were similar to children with progeria but different from it and other known disorders. “It helped validate our impression that this is something new,” says Felix Marbach, a doctor at Heidelberg University who worked on the project while at the University of Cologne. The team of European researchers published their discovery of the disorder in 2019. Identifying the gene has not opened up new treatment options, but it may lead to later research, Marbach says.

The project showed that it was possible to use a face algorithm to help identify circumstances in which data is scarce or missing entirely. “It was the first time it worked,” says Peter Krawetz, chief scientific officer of FDNA and head of the Institute of Genomes at the University of Bonn, Germany. “We are now able to work on disorders that the system has not learned or been trained in.”

This application can diagnose rare diseases from a child’s face

Source link This application can diagnose rare diseases from a child’s face

Back to top button