Want to get an autism diagnosis but are just too darn busy?

Researchers at Harvard Medical School are here to help.  Yes, the process of diagnosing autism is complex and subjective but what about if qualified people are not there to help or you are in a rush?

Autism used to be diagnosed through a careful analysis of an individual's behavior. Children took the Autism Diagnostic Interview, Revised, known as the ADI-R, a 93-question questionnaire, and/or the Autism Diagnostic Observation Schedule, known as the ADOS exam, which measures several behaviors in children. Those evaluations can take up to three hours to complete and must be administered by a trained clinician. In autism, there is a delay of more than a year between initial warning signs and diagnosis because of the waiting times to see a clinical professional who can administer the tests and deliver the formal diagnosis. 

Three hours?  That's just crazy. Clearly what autism needs is a fast-food version of a diagnosis.

Dennis Wall, associate professor of pathology and director of computational biology initiative at the Center for Biomedical Informatics at Harvard Medical School, says they have discovered a highly accurate strategy that could significantly reduce the complexity and time in getting a diagnosis process. Traditional diagnostic surveys for autism can be prohibitive for families and caregivers because they are lengthy and have to be administered by a licensed clinician, often in an environment that is unfamiliar to the child so Wall has been developing algorithms and associated deployment mechanisms to detect autism rapidly and, they say, with high accuracy. With now as many as 1 in 88 people being diagnoses with autism, more accuracy is likely needed. 

How does it work?  They use a small set of questions and a short home video of the subject so this could reduce the time for autism diagnosis by nearly 95 percent, from hours to minutes, and could be easily integrated into routine child screening practices to enable a dramatic increase in reach to the population at risk.  Is that really going to be more accurate? Your call.

"We believe this approach will make it possible for more children to be accurately diagnosed during the early critical period when behavioral therapies are most effective," said Wall.

Using machine learning techniques, an 'artificial intelligence' method where machines are trained to make decisions, Wall and his team studied results of the ADI-R from the Autism Genetic Research Exchange for more than 800 individuals diagnosed with autism to find redundancies across the exam. They found that only seven questions were sufficient to diagnose autism with nearly 100 percent accuracy, equivalent to the full 93-question exam. They validated the accuracy of the seven question survey against answer sets from more than 1,600 individuals from the Simons Foundation and more than 300 individuals from the Boston Autism Consortium. 

Wall applied similar techniques to the ADOS exam, this time classifying more than 1,050 individuals with near perfect sensitivity and slightly less than 95 percent specificity. The outcome of this work was not only a shortened mechanism for evaluating a child (8 out of 29 steps), but also a roadmap for evaluating short home video clips. Together these results have tremendous potential to move a substantial percentage of the effort into a mobilized electronic health framework with broad reach and applications.

"This approach is the first attempt to retrospectively analyze large data repositories to derive a highly accurate, but significantly abbreviated classification tool," said Wall, who is also associate professor of pathology at Beth Israel Deaconess Medical Center. "This kind of rapid assessment should provide valuable contributions to the diagnostic process moving forward and help lead to faster screening and earlier treatment," he said.

Want to try it youself? Join 25,000 other satisfied customers and try the survey.  If you find you have a child with autism, upload a video if the tyke to their video site. Then 'like' their Facebook page so more people will so even more people will circumvent the pesky bureaucracy of qualified professionals making clinical determinations.

Published in Nature Translational Psychiatry.