Autism spectrum disorder is most often diagnosed between the ages of 3 and 5, although it is often diagnosed later. In recent years, scientists have increasingly turned to artificial intelligence and computer models to help doctors identify specific symptoms in children early. Researchers in the United States decided to conduct a game-based assessment and developed a technology to evaluate a child's movements, which can be used to assess the presence of ASD.
During the assessment, the child is asked to imitate the dance movements of a video avatar for one minute. During this time, a computer assessment of the child's imitation is performed. The accuracy of the new system was evaluated in 183 children aged 7 to 13. The results are published on the Kennedy Krieger Institute website.
The test demonstrated 80% accuracy in identifying ASD and 70% accuracy in distinguishing ASD from attention deficit hyperactivity disorder. "This is a crucial advantage, as ADHD and autism often co-occur, making it difficult for even experienced clinicians to determine the diagnosis," the authors emphasize.
The researchers now plan to adapt the diagnostics for young children and expand testing to more serious developmental issues. Ultimately, this should be a simple, accurate, and convenient tool for both patients and physicians, suitable for use in any medical facility.
Recently, other scientists have discovered signs of autism in disrupted gut microbiota. This discovery also suggests the possibility of creating a simple and accurate test for autism, independent of gender, age, and other factors.
