A battery powered device known as LENA (Language Environment Analysis), which attaches to a child’s clothing, may change the face of autism screening by helping identify autism spectrum disorder through speech patterns.

Young children with autism tend to pronounce words differently. LENA records data from an entire day, and the data is then fed into a computer for analysis. Because LENA is used to identify sounds and speech patterns, not language, the device could be used to detect autism no matter what language the child speaks.

Through extensive research and experimentation involving 232 children ages ten months to four years, LENA detected early signs of autism in 75 of the children tested, and speech development delays in around 50 of the kids.

Steven F. Warren, an applied behavioral science professor at the University of Kansas who contributed to the study said, “A small number of studies had previously suggested that children with autism have a markedly different vocal signature, but until now, we have been held back from using this knowledge in clinical applications by the lack of measurement technology.”

Early detection in young children is often difficult, as there are currently no medical tests that can accurately diagnose autism. The process of identification is usually expensive and many insurance companies don’t cover the arduous testing and screening processes. Generally diagnosed through combined parent and doctor behavior analysis, autism can sometimes go undetected for years, making it difficult for the child to socially adjust to the world around him.

The speech pattern recognition analysis may be key to early diagnosis so young children can be recommended to a specialist.