AI accurately diagnoses genetic condition from facial photographs

A Yale School of Medicine team reports in a new study that an artificial intelligence (AI) model was able to reliably diagnose people living with Marfan Syndrome from a simple facial photograph.

In a pilot study recently published in Heliyon, researchers assembled 672 facial photographs of people with and without Marfan syndrome. A Convolutional Neural Network was trained on 80% of the photographs, then asked to identify the other 20% as Marfan or non-Marfan faces. The model successfully distinguished between Marfan and non-Marfan faces with 98.5% accuracy. 

Researchers say they plan to make the tool available online in the future.

Yale release on Newswise