News / Tech News

    Artificial Intelligence Can Be Used to Diagnose Rare Disorders with Just A Picture

    Rare disorders like Noonan syndrome often show up in people’s appearance that is recognizable with artificial intelligence.



    Artificial Intelligence can be used to diagnose rare disorders with just a picture.


    Rare disorders often show up in someone’s appearance. Individuals with Noonan syndrome—a genetic condition that inhibits the body’s growth and development—can have wide-set eyes, for example, and those with Bain type intellectual disability—caused by a mutated gene on the X chromosomesport almond-shaped eyes and small chins.

    Now, researchers have trained artificial intelligence to recognize these features, paving the way for early—and cheap—diagnoses.

    Scientists built a computer program, DeepGestalt, and trained it on a publicly available data set of more than 17,000 photos of patients affected by more than 200 rare disorders.

    The program then used deep learning to recognize which patterns of markers were linked to hundreds of different genetic syndromes.

    In a test with 502 new images, DeepGestalt successfully placed the correct syndrome in its top 10 list 91% of the time.

    The program also outperformed doctors in spotting patients with Angelman syndrome and Cornelia de Lange syndrome—an inherited genetic mutation that can cause, among other symptoms, low-set ears and an upturned nose—versus other disorders, and in separating patients with different genetic subtypes of Noonan syndrome. (Tasnim News Agency)

    JANUARY 13, 2019



    YOU MAY ALSO LIKE

    Nanoparticles designed to target white fat and convert it to calorie-burning brown fat slowed weight gain in obese mice without affecting food intake.
    "Disordered" materials are so-called because they are made up of objects that are in total disarray. Their composition, whether of atoms, molecules, grains or cells, do not lie in a neat, orderly pattern, but, instead, are all jumbled up.
    An international group of scientists, including from the University of Cambridge, have developed a graphene composite that can ‘eat’ common atmospheric pollutants, and could be used as a coating on pavements or buildings.
    Researchers have created better biosensor technology using a newly developed instrument that may lead to safe stem cell therapies for treating Alzheimer's and Parkinson's diseases and other neurological disorders.
    With a brief glance, facial recognition software can categorize gender with remarkable accuracy. But if that face belongs to a transgender person, such systems get it wrong more than one third of the time, according to new CU Boulder research.
    A strip of chromatography paper similar to that used in rapid pregnancy tests is the basis of a bio-sensor for detecting malaria that has been developed by Brazilian researchers.

    © 1991-2023 The Titi Tudorancea Bulletin | Titi Tudorancea® is a Registered Trademark | Terms of use and privacy policy
    Contact