FDNA publishes breakthrough in AI for rare disease ID

By The Science Advisory Board staff writers

February 14, 2022 -- FDNA has published breakthrough findings in Nature Genetics on February 10 that involve the use of facial analysis as a tool to help detect rare genetic disorders. The study showed that FDNA's artificial intelligence (AI) technology could accelerate the clinical diagnosis of patients with ultrarare disorders and facial dysmorphism, as well as enable the definition of new syndromes.

The proprietary technology strengthens next-generation phenotyping -- the capture, structuring, and analysis of complex human physiological data -- by allowing medical professionals to identify hundreds of additional disorders using facial analysis.

The paper describes FDNA's GestaltMatcher AI technology that can be used to identify the facial representations of more than 1,000 rare genetic diseases and distill facial features into a multidimensional space. GestaltMatcher achieves a comparable top-10 accuracy on all previously supported disorders and matches one-third of cases with an ultrarare or novel disorder, according to the company. The study was conducted using 17,560 portrait photos from patients with 1,115 rare disorders (Nat Genet, February 22, 2022).

FDNA was founded and is led by experts in clinical genomics and rare disease identification, drug development, and treatment. Its technologies are used by clinicians and researchers in human genetics, representing more than 2,000 clinical sites from over 130 countries around the world.


Copyright © 2022 scienceboard.net
 


Email Address:

First Name:

Last Name:

Learn about ScienceBoard

Get the latest life sciences research and industry news, delivered straight to your inbox, for free.

Why subscribe?

ScienceBoard is uniquely focused on the business of research, addressing the biggest problems that the biomedical industry face. You’ll get breaking news, events coverage, and deep dives into the science that drives innovation, delivered to your inbox daily.

I have read and agree to the privacy policy and terms of service and wish to opt-in for ScienceBoard.net.