This project develops the Predictive ASD Clinical Assessor (PACE), a machine-learning framework for predicting one-year developmental outcomes in children with autism spectrum disorder (ASD). Using real-world intervention data from rehabilitation institutions in China, the study integrates standardized assessments, including PEP-3, VB-MAPP, and Gesell scales, with clinical variables. Through statistical modeling and machine-learning methods, the project aims to identify key prognostic factors and support personalized intervention planning. The study also explores science communication strategies to improve public understanding of autism intervention outcomes and evidence-based rehabilitation practices.
