Behavioural and neural basis of anomalous motor learning in children with autism

Abstract

Autism spectrum disorder is a developmental disorder characterized by deficits in social and communication skills and repetitive and stereotyped interests and behaviours. Although not part of the diagnostic criteria, individuals with autism experience a host of motor impairments, potentially due to abnormalities in how they learn motor control throughout development. Here, we used behavioural techniques to quantify motor learning in autism spectrum disorder, and structural brain imaging to investigate the neural basis of that learning in the cerebellum. Twenty children with autism spectrum disorder and 20 typically developing control subjects, aged 8-12, made reaching movements while holding the handle of a robotic manipulandum. In random trials the reach was perturbed, resulting in errors that were sensed through vision and proprioception. The brain learned from these errors and altered the motor commands on the subsequent reach. We measured learning from error as a function of the sensory modality of that error, and found that children with autism spectrum disorder outperformed typically developing children when learning from errors that were sensed through proprioception, but underperformed typically developing children when learning from errors that were sensed through vision. Previous work had shown that this learning depends on the integrity of a region in the anterior cerebellum. Here we found that the anterior cerebellum, extending into lobule VI, and parts of lobule VIII were smaller than normal in children with autism spectrum disorder, with a volume that was predicted by the pattern of learning from visual and proprioceptive errors. We suggest that the abnormal patterns of motor learning in children with autism spectrum disorder, showing an increased sensitivity to proprioceptive error and a decreased sensitivity to visual error, may be associated with abnormalities in the cerebellum.

Keywords: autism; cerebellum; error sensitivity; motor learning; proprioception; reaching.

Figure 1

Experimental task. (A) Children made reaching movements to a target while holding the handle of a robotic manipulandum. On random trials, the robot perturbed the reach, causing an error. Learning from this error was measured through error-clamp trials, in which the error was clamped to zero and the forces that the children produced against the clamp walls were measured. (B and C) Hand path and cursor paths for a representative typically developing (TD) and ASD subject (B) and for the group (C). For both groups, hand error increased with increasing field strength and cursor error increased with increasing visual gain. Data were sampled at 100 Hz, and error bars represent SEM. (D) Time course of error during the reach in the perturbation trials, as quantified via velocity perpendicular to the direction of the target. Perpendicular velocity reflects both the perturbation to the hand and the online-feedback response. Perpendicular velocity increased with increasing perturbation strength, reflecting the effect of field size, but was not different between groups. (E) Proprioceptive error, experienced by the hand, measured at 50% of the maximum velocity for each movement for all perturbation conditions. Increasing field strength increased the proprioceptive error, but increasing visual gain did not. The errors experienced by the children were not different between groups.

Figure 2

Learning in response to visual and proprioceptive errors. All error bars are between-subject SEM. (A) Adaptive response (left) and sensitivity (right) to proprioceptive errors. We found children with ASD showed increased adaptation and sensitivity to proprioceptive errors of different sizes. (B) Adaptive response to the b = 13 force field (left) and to the b = 6.5 force field (right). There was no group difference in adaptation in response to proprioceptive and visual errors given together, most clearly demonstrated by the g = 1 condition. (C) Sensitivity to visual error alone. We found children with ASD exhibited less sensitivity to visual error than typically developing (TD) children.

Figure 3

Relationship between sensitivity to visual and proprioceptive errors. (A) Average proprioceptive sensitivity (x-axis) and visual sensitivity (y-axis) for each subject. We found a significant trade-off between sensitivities, such that as sensitivity to error in one modality increased, sensitivity in the other modality decreased. (B) Overall response to error. We found children with ASD to have a greater sensitivity to proprioceptive errors and greater adaptation in response to a proprioceptive error, and typically developing (TD) children to have greater sensitivity to visual errors and greater adaptation in response to visual errors.

Figure 4

Volume of the sensorimotor cerebellar regions. (A) Example typically developing subject (top) and example ASD subject (bottom), highlighting the coarse-scale sensorimotor region in red and the fine-scale sensorimotor region in purple. The ASD subject had a smaller than normal volume for both regions. (B) Group data for the volume of both the coarse- and fine-scale sensorimotor regions, demonstrating a smaller sensorimotor cerebellar volume for children with ASD. Error bars are between-subject SEM. TD = typically developing.