Currently, clinicians can't diagnose autism until toddlers that are about 2, when the first behavioral and language symptoms of the developmental disorder become noticeable. Scientists are developing more sophisticated screening tests that rely on brain-imaging techniques or eye-tracking technologies that monitor an infant's gaze to pick up early autistic signs still there is no reliable way to diagnose the condition in younger infants.
The director of Eunice Kennedy Shriver National Institute of Child Health and Human Development in the US, Diana Bianchi and NIH-funded investigators at the University of North Carolina at Chapel Hill and Washington University School of Medicine in St. Louis used specific magnetic resonance imaging procedure to determine 82 percent of the newborns, who would go on to have autism (9 out of 11) and it correctly identified all of the children, who did not develop autism by using functional connectivity magnetic resonance imaging (fcMRI).
Currently, clinicians can't diagnose autism until toddlers that are about 2 years old
Photo Credit: iStock
Researchers used a computer-based technology called machine learning, which trains itself to look for differences that can separate the neuro imaging results into two groups, autism or non-autism, and predict future diagnoses. Joshua Gordon, director of the National Institute of Mental Health said that in the future, neuro imaging may be a useful tool to diagnose autism or help health care providers evaluate a child's risk of developing the disorder.
The team eventually found 974 functional connections in the brains of 6 month old infants that were associated with autism-related behaviors. The researchers claimed that a single neuro-imaging scan may accurately predict autism among high-risk infants, but caution that the findings need to be replicated in a larger group. The study is published in the journal of Science Translational medicine.
(With inputs from ANI)