Detailed characterization of motor abnormalities in autism holds a great deal of promise for identifying diagnostically sensitive motor indicators and developing individualized approaches to intervention. However, extracting subtle differences in motor behavior can involve high technological costs.
The Proof of Concept (PoC) enabled us to develop a portable, non-invasive, low-cost device - the Kinematics Detector (KiD) - to track movement kinematics continuously in real-world settings.
The PoC also allowed us to develop machine learning algorithms appropriate for clinical prediction and to learn important lessons for translating advances in autism movement science into clinical practice.
