A study published this month on the magazine Nature Medicine describes how the facial recognition together with the artificial intelligence can help identifying facial phenotypes of genetic disorders, so accelerating the syndrome identification.
Realized by the American company FDNA, the study presents their facial recognition software DeepGestalt, which was trained on a dataset of over 17,000 images representing more than 200 syndromes, using an ad-hoc smartphone application named Face2Gene.
In the first two tests, DeepGestalt was used to find out specific diseases: Syndrome of Cornelia de Lange and Syndrome of Angelman. Both are complex conditions which influence the intellectual development and the mobility. The facial traits are distinct: arched eyebrows that meet in the middle for Cornelia de Lange syndrome, and unusually fair skin and hair for Angelman syndrome.
When tasked with distinguishing between pictures of patients with one syndrome or another, random syndrome, DeepGestalt was more than 90 percent accurate, beating expert clinicians, who were around 70 percent accurate on similar tests. When tested on 502 images showing individuals with 92 different syndromes, DeepGestalt identified the target condition in its guess of 10 possible diagnoses more than 90 percent of the time.
In a more challenging experiment, the algorithm was shown images of individuals with Noonan syndrome, and asked to identify which one of five specific genetic mutations might have caused it. Here the software was slightly less accurate, with a hit rate of 64 percent.
However, experts say this sort of algorithmic tests aren’t a silver bullet for identifying rare genetic disorders. Dr. Bruce Gelb, professor at the Icahn School of Medicine at Mount Sinai and an expert on Noonan syndrome, expressed his doubts on the real efficiency of the software; nevertheless, he said the algorithms were “impressive.”
Gelb also noted that DeepGestalt was developed and tested on a limited dataset of children, and might struggle to identify disorders in older individuals, where facial characteristics become less distinct. Third-party research of FDNA’s tools has also suggested a racial bias: the algorithms are much more effective on Caucasian than African faces.
FDNA seems aware of these shortcomings, and the company’s research refers to DeepGestalt’s potential as “a reference tool” — something that, like other AI-powered software, would assist, not replace, human diagnoses.
Christoffer Nellåker, an expert in the field at the University of Oxford, echoed this judgement, telling New Scientist: “The real value here is that for some of these ultra-rare diseases, the process of diagnosis can be many, many years […] For some diseases, it will cut down the time to diagnosis drastically. For others, it could perhaps add a means of finding other people with the disease and, in turn, help find new treatments or cures.”