Reviewed by Lexie CornerAug 12 2024
In a recent study published in Heliyon, researchers from Yale School of Medicine report an artificial intelligence (AI) model that can accurately diagnose individuals with Marfan Syndrome based on a simple facial photograph.
About 1 in 3,000 people have Marfan syndrome, a genetic condition that affects the connective tissues in the body.
Patients living with Marfan Syndrome are usually very tall and thin. They have long faces and are prone to spine and joint issues. However, many are not diagnosed.
John Elefteriades, Study Senior Author and Professor of Surgery, Yale School of Medicine
Marfan Syndrome raises the risk of aortic dissection, in which the aorta abruptly divides after enlarging.
It is often lethal, and when the patient survives, urgent surgery is needed. Being able to identify individuals from a photograph with AI will enhance diagnosis and enable protective therapies.
John Elefteriades, Study Senior Author and Professor of Surgery, Yale School of Medicine
In a recent pilot study, researchers compiled 672 facial images of individuals with and without Marfan Syndrome. They trained a Convolutional Neural Network (CNN) on 80 % of these images and then tasked it with classifying the remaining 20 % as either Marfan or non-Marfan faces. The model achieved an impressive 98.5 % accuracy in distinguishing between the two.
The researchers plan to make this technology available online in the future.
“We are planning to extend this work beyond this initial pilot project. We anticipate that many individuals may self-test once we put the test online,” said Elefteriades.
Yale School of Medicine faculty and students are leading the way in developing novel applications of AI to recognize and diagnose diseases, including rare diseases, earlier when we can have the greatest impact.
Nancy J. Brown, MD, Dean, Yale School of Medicine
Co-authors include Sandip Mukherjee, Mohammad A. Zafar, and Bulat Ziganshin. The AI investigation was carried out by Emerge's Danny Saksenberg, who also holds a post at Yale.
Journal Reference:
Saksenberg, D., et al. (2024) Pilot study exploring artificial intelligence for facial-image-based diagnosis of Marfan syndrome. Heliyon. doi.org/10.1016/j.heliyon.2024.e33858.