Sponsored By

The scourge of celebrities, who can no longer satisfy fans with a simple autograph, selfies may serve a higher purpose than documenting chance encounters with stars thanks to researchers at the Department of Physiology, Anatomy, and Genetics at the University of Oxford in the United Kingdom. They have developed a computer program that identifies a number of genetic disorders based on photographs. They don't have to be selfies; any headshot will do, even if it's from the 19th century.

Norbert Sparrow

July 3, 2014

2 Min Read
Selfies can reveal genetic disorders

The scourge of celebrities, who can no longer satisfy fans with a simple autograph, selfies may serve a higher purpose than documenting chance encounters with stars thanks to researchers at the Department of Physiology, Anatomy, and Genetics at the University of Oxford in the United Kingdom. They have developed a computer program that identifies a number of genetic disorders based on photographs. They don't have to be selfies; any headshot will do, even if it's from the 19th century. Applying this software to photographs of Abraham Lincoln's face, for example, allowed the program to determine that the former president probably suffered from Marfan syndrome, which results in unusually large features.

The program analyzes facial features and looks for similarities with faces in its database of people with Down's syndrome, Angleman syndrome, Progeria, and other disorders. It returns matches ranked by likelihood.

selfie-stockimages-240.jpg

Image courtesy Stockimages/
freedigitalphotos.net

The researchers are continuing to add reference faces to the database—currently it stores more than 2700 portrait photographs representing up to 90 disorders—and the software itself is learning as it goes. Patients sharing the same condition are automatically clustered together, and the algorithm refines its performance as it sees more photos of people with an identical condition.

Genetic disorders can affect an estimated one in 17 people, but many are not identified and treated because of limited access to specialists with the expertise to diagnose these conditions. This is especially true in the developing world.

"A doctor should in the future, anywhere in the world, be able to take a smartphone picture of a patient and run the computer analysis to quickly find out which genetic disorder the person might have,' says lead researcher Dr Christopher Nellåker of the MRC Functional Genomics Unit at the university. "This objective approach could help narrow the possible diagnoses, make comparisons easier, and allow doctors to come to a conclusion with more certainty," he adds in a statement issued by the University of Oxford. The research has been published in the journal eLife.

The team of researchers also included first author Quentin Ferry, a DPhil research student, and Professor Andrew Zisserman of the Department of Engineering Science, who brought expertise in computer vision and machine learning.

About the Author(s)

Norbert Sparrow

Editor in chief of PlasticsToday since 2015, Norbert Sparrow has more than 30 years of editorial experience in business-to-business media. He studied journalism at the Centre Universitaire d'Etudes du Journalisme in Strasbourg, France, where he earned a master's degree.

www.linkedin.com/in/norbertsparrow

Sign up for the PlasticsToday NewsFeed newsletter.

You May Also Like