Autism is a growing problem in America. One in one-hundred-and-ten kids in the United States is on the Autism scale, according to the CDC. But, until now, there has been no objective way to diagnose early autism. Fortunately, a new study may have found a way to change that.
Scientists have long known that autistic children show early problems in their speech development, but because toddler babbling (a key part of speech development that helps them learn how to pronounce sounds and syllable) varies tremendously it has always been very difficult to judge which distortions are hints at an autism diagnosis and which are normal.
This new study has found, however, that by recording baby babble and feeding it into a specially developed computer program they can distinguish between the speech of normal children and those with autism. All toddlers mangle their syllables while learning to talk, but children with autistic tendencies do it far longer than normal children – that makes it easy for the software to pick out the autistic kid’s voices. Even though this is really just the first attempt at analyzing audio recordings for signs of autism, the program can already correctly identify more than 85% of autistic and nonautistic children.
“We had no idea that this was possible,” Kim Oller of the University of Memphis, head of the research team, told AOL News. “It’s very surprising that you can use a totally objective system and get this much information so quickly.”
If the program continues to be successful, it will be a tremendous tool for those trying to help children with the disorder. The earlier autism is diagnosed, the earlier therapies to help the child’s brain develop in ways that compensate for the impairment and the better chance a child has at a somewhat normal life.
