Autism: video diagnosis

Short home videos may become a powerful tool for diagnosing autism, according to new findings from associate professor Dennis Wall, PhD, and colleagues. Wall’s team scored the level of autistic-type behaviors in brief YouTube videos of 100 children. The method, described April 16 in PLOS ONE, identified autism with 97 percent accuracy.

Though video-based diagnosis won’t likely replace traditional assessments, it could speed the now-sluggish diagnostic process. “We could use this system for clinical triage, as a way to channel traffic so that children can get the kind of attention they need as early as possible,” Wall says. Children who clearly have autism might be diagnosed with videos and started on therapy, freeing clinicians to spend more time evaluating kids whose condition is less clear cut.