“Think About A Hug”: Social Patterns in Brain Imaging to Diagnose Autism


The process of diagnosing autism typically consists of a combination of analyzing verbal and physical behavior. This might all change thanks to recent research from Carnegie Mellon University (CMU). PLoS One recently published a study demonstrating a new way to examine activation patterns in the brain that provide a highly accurate diagnosis. These brain-reading techniques use “neural representations of social thoughts to predict autism within a 97% accuracy.”

The study examined a control of 17 adult patients with neurotypical patterns and 17 adults with high-functioning autism. Each participant was asked to think about different social concepts such as “hug”, “persuade,” or “adore” while recording images of the brain.

Machine-learning algorithms analyzed the images of brain during the experiment. The brain image patterns greatly differed between the two groups and all of participants were successfully classified with a 97% accuracy rate.

Marcel Just of the CMU states, “This is potentially an extremely valuable method that could not only complement current psychiatric assessment. It could identify psychiatric disorders not just by their symptoms, but by the brain systems that are not functioning properly. It may eventually be possible to screen for psychiatric disorders using quantitative biological measures of thought that would test for a range of illnesses or disorders.”

For more information about how brain representations of social thoughts accurately predict autism diagnosis, watch Just discuss the research in a video lecture here.

To read the original article click here.

This entry was posted in Autism Diagnosis, Autism News, Autism Research and tagged , , , , , , . Bookmark the permalink. Post a comment or leave a trackback: Trackback URL.

Post a Comment

Your email is never published nor shared.

You may use these HTML tags and attributes <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>