A look at your face might now be enough to reveal your genetic diseases as well as their causes.
As per a Daily Mail report, the new artificial intelligence (AI) technology, called DeepGestalt, out-preformed clinicians in identifying rare genetic diseases by just looking at photographs of patients’ faces.
The study co-author Dr Karen Gripp, from FDNA, the US company that developed the program, called this a “long-awaited breakthrough in medical genetics”.
“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.”
Many disorders are linked to distinct facial markers. For instance, Angelman syndrome is recognizable because of facial symptoms like a wide mouth with widely spaced teeth. Similarly, Down syndrome is associated with almond-shaped eyes, making it possible for automated facial analysis to be an efficient tool.
The Research
The scientists trained the ‘deep-learning’ software by using around 17000 facial images of patients with over 200 genetic disorders. In two separate sets of tests to identify a target syndrome among 502 selected images, the AI technology outperformed human experts.
DeepGestault identified the correct syndrome in its top 10 list of suggestions 91 percent of the time. In another test, the program had a success rate of 64 percent in identifying subtypes of Noonan syndrome, a great progress from clinicians’ success rate of just 20 percent.
CNN quotes Yaron Gurovich, chief technology officer at FDNA, “It demonstrates how one can successfully apply state of the art algorithms, such as deep learning, to a challenging field where the available data is small, unbalanced in terms of available patients per condition, and where the need to support a large amount of conditions is great. ”
However, researchers also warned about the potential misuse of information that this technology can provide, because of the easy accessibility of facial images. ‘Payers or employers could potentially analyse facial images and discriminate based on the probability of individuals having pre-existing conditions or developing medical complications.’
