Computerized Assessment of Motor Imitation as a Scalable Method for Distinguishing Children With Autism

Imitation deficits are prevalent in autism spectrum conditions (ASCs) and are associated with core autistic traits. Imitating others' actions is central to the development of social skills in typically developing populations, as it facilitates social learning and bond formation. We present a Computerized Assessment of Motor Imitation (CAMI) using a brief (1-min), highly engaging video game task.

Using Kinect Xbox motion tracking technology, we recorded 48 children (27 with ASCs, 21 typically developing) as they imitated a model's dance movements. We implemented an algorithm based on metric learning and dynamic time warping that automatically detects and evaluates the important joints and returns a score considering spatial position and timing differences between the child and the model. To establish construct validity and reliability, we compared imitation performance measured by the CAMI method to the more traditional human observation coding (HOC) method across repeated trials and two different movement sequences.

Results revealed poorer imitation in children with ASCs than in typically developing children (ps < .005), with poorer imitation being associated with increased core autism symptoms. While strong correlations between the CAMI and HOC methods (rs = .69-.87) confirmed the CAMI's construct validity, CAMI scores classified the children into diagnostic groups better than the HOC scores (accuracy_CAMI = 87.2%, accuracy_HOC = 74.4%). Finally, by comparing repeated movement trials, we demonstrated high test-retest reliability of CAMI (rs = .73-.86).

Findings support the CAMI as an objective, highly scalable, directly interpretable method for assessing motor imitation differences, providing a promising biomarker for defining biologically meaningful ASC subtypes and guiding intervention.