Firms could use Facebook pictures to discriminate against employees with genetic diseases, scientists warn

Sarah Knapton
Profile pictures could reveal what genetic diseases users are suffering  - Bloomberg

Companies could use Facebook pictures to discriminate against employees with genetic diseases using AI, scientists fear, after showing that algorithms can spot rare conditions.

Developers at US biotech company FDNA have developed a programme which outperforms humans at diagnosing genetic syndromes by looking at slight variations in face shape.

The face analysis programme, known as DeepGestalt, could in future assist the diagnosis of rare disorders such as Fragile X which brings a long narrow face and prominent ears, or angelman syndrome, which is characterised by a prominent chin, deep set eyes and wide mouth.

But the researchers warn that the technology could be open to abuse from employers who could use it to filter out workers who are less healthy and may take more time off, or need greater support.

Profile pictures are now widely available on social media sites, such as Facebook or Instagram. 

The programme uses facial mapping to spot rare diseases 

Writing in the journal Nature Medicine, the team warns: “Unlike genomic data, facial images are easily accessible.

“Employers could potentially analyse facial images and discriminate based on the probability of individuals having pre-existing conditions or developing medical complications.”

The team trained the software using more than 17,000 facial images of patients with more than 200 different genetic disorders.

In subsequent tests DeepGestalt successfully included the correct syndrome in its top 10 list of suggestions 91 per cent of the time, out-performeding clinical experts in three separate trials.

Many genetic disorders are associated with distinct facial features. Some are easily recognisable while others are harder to spot.

People with Williams syndrome, for instance, have short, upturned noses and mouths, a small jaw and a large forehead.

Well-known features associated with Down's syndrome include almond-shaped eyes, a round, flat face, and a small nose and mouth.

Study co-author Dr Karen Gripp, from FDNA said: “This is a long-awaited breakthrough in medical genetics that has finally come to fruition.

“With this study, we've shown that adding an automated facial analysis framework, such as DeepGestalt, to the clinical workflow can help achieve earlier diagnosis and treatment, and promise an improved quality of life."

Yaron Gurovich, chief technology office at FDNA and first author of the research added: “The increased ability to describe physical characteristics in a standardised way opens the door to future research and applications, and the identification of new genetic syndromes.”