[ad_1]
Researchers Stanford University School of Medicine in California, they designed and tested eight models of automated learning to diagnose autism in children through the analysis of home videos.
The result, published in the scientific journal PLOS Medicine, indicates that "The use of personal videos for diagnostic purposes has the potential to streamline the process and make it much more efficient"said Dennis Wall, professor of pediatrics and biomedical data science at Stanford and lead author of the study.
Each of the models contained "a set of algorithms consisting of 5 to 12 behavioral characteristics of children and producing a general score indicating whether the child was autistic"he explained.
To evaluate the models, the researchers asked the families recruited as part of the study to send home videos of one to five minutes showing the faces and hands of the children and then captured . "their social interaction, as well as the use of toys, pencils and utensils".
Of the videos received, 116 involved children with autism (average age four years and 10 months) and 46 children with autism (average age 2 years and 11 months) .
Nine expert reviewers will analyze the videos using a 30-question quiz with "yes" or "no" answers, based on typical autistic behaviors.
The data from each video, along with the 30 responses to questions about the child's behavior, were incorporated into the eight mathematical models.
The best-performing model identified 94.5% of autistic children and 77.4% of non-autistic children.
To check the results, another 66 videos were evaluated, half of them autistic children.
The same model correctly identified 87.8% of children with autism and 72.7% of those with non autistic children.
"Across the United States, the average waiting list for accessing a standardized service (for the diagnosis of autism in the child) can go up to one year."said the wall.
Another advantage of using home-made videos for diagnosis is that they "take the child to his or her natural environment", as opposed to the clinical evaluation carried out in a "medium" which can be rigid and artificial and provoke atypical behavior in children "
"We have demonstrated that we can identify a small group of behavioral characteristics that are highly aligned with clinical outcomes and that non-experts can quickly and independently qualify these characteristics in a virtual online environment in minutes"said the wall.
[ad_2]
Source link
