Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 25:12:635696.
doi: 10.3389/fpsyg.2021.635696. eCollection 2021.

Using Technology to Identify Children With Autism Through Motor Abnormalities

Roberta Simeoli  1 , Nicola Milano  2 , Angelo Rega  1   3 , Davide Marocco  1
Affiliations

Using Technology to Identify Children With Autism Through Motor Abnormalities

Roberta Simeoli et al. Front Psychol. .

Abstract

Autism is a neurodevelopmental disorder typically assessed and diagnosed through observational analysis of behavior. Assessment exclusively based on behavioral observation sessions requires a lot of time for the diagnosis. In recent years, there is a growing need to make assessment processes more motivating and capable to provide objective measures of the disorder. New evidence showed that motor abnormalities may underpin the disorder and provide a computational marker to enhance assessment and diagnostic processes. Thus, a measure of motor patterns could provide a means to assess young children with autism and a new starting point for rehabilitation treatments. In this study, we propose to use a software tool that through a smart tablet device and touch screen sensor technologies could be able to capture detailed information about children's motor patterns. We compared movement trajectories of autistic children and typically developing children, with the aim to identify autism motor signatures analyzing their coordinates of movements. We used a smart tablet device to record coordinates of dragging movements carried out by 60 children (30 autistic children and 30 typically developing children) during a cognitive task. Machine learning analysis of children's motor patterns identified autism with 93% accuracy, demonstrating that autism can be computationally identified. The analysis of the features that most affect the prediction reveals and describes the differences between the groups, confirming that motor abnormalities are a core feature of autism.

Keywords: assessment technologies; autism spectrum disorder; classification; machine learning; motion analysis; sensory-motor impairment.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. The reviewer, GT, declared a shared affiliation, with no collaboration, with one of the author, NM, to the handling editor at the time of the review.

Figures

FIGURE 1
FIGURE 1
Panel (A) depicts the Leiter-3 test in its original version; on the right, panel (B) is an example of a test scene in its digital version.
FIGURE 2
FIGURE 2
An example of dragging movement during the performance of a CA task. The users are required to drag the moving cards from the bottom to the corresponding placeholders at the top of the screen, according to the task demand.
FIGURE 3
FIGURE 3
Accuracy during the training process. Data refer to the average accuracy of all the models of the 10-fold CV with five repetitions. Mean and 90% bootstrapped confidence intervals of the mean (shadow area) across all the replications.
FIGURE 4
FIGURE 4
Receiver operating characteristics curves (ROC) of the ANN model. The curve is derived from the sensitivity and specificity index, the rate of correctly classified samples in the positive and negative classes.
FIGURE 5
FIGURE 5
Classification accuracy, specificity, and sensitivity rates in relation to the number of features analyzed by the ANN. Features have been withdrawn as follows: (1) sdAcc, (2) STH, (3) sdSpeed, (4) sdDC, (5) MaxSpeed, (6) DC, (7) MeanRow, (8) MinSpeed, (9) MeanSpeed, (10) MinAcc, (11) MaxAcc, and (12) MeanAcc.
FIGURE 6
FIGURE 6
Boxplots of the 12 kinematics features extracted from coordinates of movement and compared between the groups. Features definition in Table 1.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Adrien J. L., Lenoir P., Martineau J., Perrot A., Hameury L., Larmande C., et al. (1993). Blind ratings of early symptoms of autism based upon family home movies. J. Am. Acad. Child Adolesc. Psychiatry 32 617–626. 10.1097/00004583-199305000-00019 - DOI - PubMed
    1. Albinali F., Goodwin M. S., Intille S. (2012). Detecting stereotypical motor movements in the classroom using accelerometry and pattern recognition algorithms. Pervasive Mob. Comput. 8 103–114. 10.1016/j.pmcj.2011.04.006 - DOI
    1. Albinali F., Goodwin M. S., Intille S. S. (2009). “Recognizing stereotypical motor movements in the laboratory and classroom: a case study with children on the autism spectrum,” in Proceedings of the ACM International Conference Proceeding Series, (New York, NY: ACM Press; ), 71–80. 10.1145/1620545.1620555 - DOI
    1. Anzulewicz A., Sobota K., Delafield-Butt J. T. (2016). Toward the autism motor signature: gesture patterns during smart tablet gameplay identify children with autism. Sci. Rep. 6:31107. 10.1038/srep31107 - DOI - PMC - PubMed
    1. Baranek G. T. (1999). Autism during infancy: a retrospective video analysis of sensory-motor and social behaviors at 9–12 months of age. J. Autism Dev. Disord. 29 213–224. 10.1023/A:1023080005650 - DOI - PubMed

LinkOut - more resources