AI tool mproves motor imitation assessment for children with autism

Researchers at Kennedy Krieger Institute and Penn Engineering announcing the development of an advanced artificial intelligence system that measures a child's ability to imitate simple body movements using ordinary video recordings. The Computerized Assessment of Motor Imitation, or CAMI-2DNet, brings researchers one step closer to a scalable, objective method for evaluating imitation which is an important behavioral marker associated with autism.

Children with autism often imitate movements differently than their neurotypical peers, making motor imitation an important marker during developmental evaluations.

"Motor imitation is a critical building block for social development," said Dr. Stewart H. Mostofsky, director of the Center for Neurodevelopmental and Imaging Research at Kennedy Krieger Institute and a study co-author. "Our long-term goal is to better understand individual differences in autism and help inform interventions that address those differences."

Traditionally, measuring motor imitation has required specialized motion-capture systems or painstaking manual analysis by trained experts, limiting where and how often these assessments can be performed.

"By replacing specialized hardware and manual analysis with intelligent computer vision, we can help make objective behavioral assessments more accessible to clinicians and families," said René Vidal, Rachleff University professor, director of the Innovation in Data Engineering and Science Initiative, and senior author of the study.

CAMI-2DNet is not designed to diagnose autism on its own or replace the expertise of clinicians. Instead, it provides an objective measurement that can complement existing evaluations, helping clinicians make more informed decisions and allowing researchers to track changes over time.

 "Our hope is that tools like CAMI-2DNet can reduce barriers to timely, high-quality assessments," said lead author and Ph.D. candidate Kaleab Kinfu.

The study on CAMI-2DNet was published in IEEE Transactions on Biomedical Engineering.