Researchers are using artificial intelligence to diagnose rare genetic diseases by scanning a person’s face or a photograph, according to a study published this month.
The technology, called DeepGestalt, outperformed physicians in three separate experiments and was more than 90 percent accurate in identifying diseases in more than 500 different images.
About 8 percent of the population has diseases that cause specific facial deformities.
For example, Hajdu-Cheney syndrome affects bones and causes the eyes to spread apart and the ears to droop. The disease is so rare that only about 100 cases are documented in medical literature, according to the National Institutes of Health.
DeepGestalt builds on other attempts to fine-tune artificial intelligence to help doctors diagnose such conditions.
“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,” Yaron Gurovich, lead author of the study and chief technology officer at FDNA, an artificial intelligence and precision medicine company, told CNN.