Development and evaluation of robotic detection technology for assessing autism

Area of Science:

• Robotics and Artificial Intelligence in Healthcare
• Developmental Pediatrics
• Autism Spectrum Disorder Research

Background:

• Objective and standardized autism assessment tools are crucial for early intervention.
• Current diagnostic methods can be time-consuming and require specialized expertise.
• Identifying key behavioral markers like atypical eye gaze and motor movements is vital.

Purpose of the Study:

• To develop and validate a robotic system for detecting autism-related behaviors.
• To assess the efficacy of the HUMANE robot in identifying atypical eye gaze and repetitive movements.
• To evaluate the robotic system's performance against a gold-standard diagnostic tool.

Main Methods:

• The HUMANE robot, equipped with computer vision and recognition technology, monitored 119 children (3-6 years old).
• The robot autonomously detected atypical eye gaze and repetitive motor movements during storytelling.
• Performance was evaluated against the Autism Diagnostic Observation Schedule-second edition (ADOS-2) scores.

Main Results:

• The robotic detection achieved an average sensitivity and specificity of 0.80.
• The Diagnostic Odds Ratio exceeded 30, and the Area Under the Curve (AUC) was 0.85.
• The system demonstrated strong performance in distinguishing between children with and without autism.

Conclusions:

• Robotic detection of atypical eye gaze and repetitive motor movements is a viable tool.
• This technology can significantly aid in the diagnostic process for autism spectrum disorder.
• Further integration of such technologies may enhance early identification and intervention efforts.