The method could reduce the amount of time needed to diagnose the developmental condition by 95 percent.
Diagnosing autism spectrum disorder usually takes lots of time. Children and their parents have to complete large questionnaires along with interviews with psychiatrists before treatment can start.
In the latest issue of Nature Translational Psychiatry, researchers from the Center for Biomedical Informatics at Harvard Medical School published a new algorithm to detect autism much quicker. They developed a web-based tool to complete these questionnaires and tested the contribution of each survey question individually to diagnose the autism disorder. They found that only seven questions were sufficient for an accurate diagnosis. The new smaller set of questions can be answered online and submitted together with a short home video of the patient. This procedure could reduce the time for autism diagnosis from hours to minutes, and could be integrated into routine child screening practices.
Dennis Wall, director of computational biology initiative at the Center for Biomedical Informatics, was cited in the press release:
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. The 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, which can be a tremendous burden for families in remote areas. With this mobilized approach, the parent or caregiver will be able to take the crucial first steps to diagnosis and treatment from the comfort of their own home, and in just a few minutes.
- More from Harvard: Detecting autism in matter of minutes...
- Abstract in Translational Psychology: Use of machine learning to shorten observation-based screening and diagnosis of autism
- Link: Autworks...
This post also appears on medGadget, an Atlantic partner site.
We want to hear what you think about this article. Submit a letter to the editor or write to firstname.lastname@example.org.