Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 6, 31107

Toward the Autism Motor Signature: Gesture Patterns During Smart Tablet Gameplay Identify Children With Autism


Toward the Autism Motor Signature: Gesture Patterns During Smart Tablet Gameplay Identify Children With Autism

Anna Anzulewicz et al. Sci Rep.


Autism is a developmental disorder evident from infancy. Yet, its clinical identification requires expert diagnostic training. New evidence indicates disruption to motor timing and integration may underpin the disorder, providing a potential new computational marker for its early identification. In this study, we employed smart tablet computers with touch-sensitive screens and embedded inertial movement sensors to record the movement kinematics and gesture forces made by 37 children 3-6 years old with autism and 45 age- and gender-matched children developing typically. Machine learning analysis of the children's motor patterns identified autism with up to 93% accuracy. Analysis revealed these patterns consisted of greater forces at contact and with a different distribution of forces within a gesture, and gesture kinematics were faster and larger, with more distal use of space. These data support the notion disruption to movement is core feature of autism, and demonstrate autism can be computationally assessed by fun, smart device gameplay.

Conflict of interest statement

A.A. and K.S. were employed by start-up company Harimata Sp. z.o.o. with vesting options agreements. J.D.B. declares no competing financial interests.


Figure 1
Figure 1. The two serious tablet games employed for data capture.
(A) ‘Sharing’ where the main gameplay involved touching the fruit (centre forward), which sliced it into four equal pieces, then sliding each piece to a child’s plate. When all four children had a slice of fruit, they would jump for joy for 3 seconds before the fruit was replaced with another food, and the children would return to their neutral position. (B) ‘Creativity’ where the children were free to choose an object or animal shape, then trace the shape before colouring it in freely, choosing a colour from the colour wheel. When the children were satisfied, they could choose a new shape by selecting the return button in the top right-hand corner.
Figure 2
Figure 2. The child’s purposeful movements were sensed by the touch screen and the inertial sensors inside the tablet.
Figure 3
Figure 3. Receiver operating characteristic curves (ROC) of the RGF2 models.
For higher classification thresholds (moving to the left on the plot; higher specificity, lower sensitivity) Creativity is the best performer. The plot was obtained by aggregating all predictions from 10 repetitions of 10-fold cross-validation (740 observations).
Figure 4
Figure 4. Boxplots of the ten features with the greatest Kolmogorov-Smirnov distance between Autism and Control groups for the Creativity and Sharing games.
Descriptions of these features are given in Table 3. Boxplots show median values (horizontal line), interquartile range (box outline), minimum and maximum values of the upper and lower quartiles (whiskers) and outliers (circles).
Figure 5
Figure 5. The machine learning approach.

Similar articles

See all similar articles

Cited by 17 PubMed Central articles

See all "Cited by" articles


    1. Elsabbagh M. et al. Global Prevalence of Autism and Other Pervasive Developmental Disorders. Autism Research 5, 160–179, doi: 10.1002/aur.239 (2012). - DOI - PMC - PubMed
    1. Baio J. Prevalence of Autism Spectrum Disorder Among Children Aged 8 Years - Autism and Developmental Disabilities Monitoring Network, 11 Sites, United States, 2010. Morbidity and Mortality Weekly Report - Surveillance Summaries 63, 1–21 (2014). - PubMed
    1. Brugha T. S. et al. Epidemiology of autism spectrum disorders in adults in the community in England. Arch. Gen. Psychiatry 68, 459–465, doi: 10.1001/archgenpsychiatry.2011.38 (2011). - DOI - PubMed
    1. Jarbrink K. & Knapp M. The economic impact of autism in Britain. Autism: the international journal of research and practice 5, 7–22 (2001). - PubMed
    1. Hallmayer J., Cleveland S. & Torres A. et al. GEnetic heritability and shared environmental factors among twin pairs with autism. Arch. Gen. Psychiatry 68, 1095–1102, doi: 10.1001/archgenpsychiatry.2011.76 (2011). - DOI - PMC - PubMed