HKUST Builds AI Agent for Autism Screening and Family Support

On November 11, 2026, The Hong Kong University of Science and Technology (HKUST) announced ASD Super Agent, an AI platform for autism screening and family support, with a preliminary area under the curve score of 0.92, a measure of discriminative precision. Further clinical studies and real-world validation are planned before deployment.

The platform combines early risk screening, personalized intervention recommendations and continuous follow-up for parents and caregivers. HKUST describes it as Asia’s first integrated AI platform for autism support.

HKUST says autism spectrum disorder affects approximately one in 100 children worldwide, while lengthy assessment waits, high treatment costs and fragmented intervention information can prevent families from obtaining timely support. The platform is intended to assist families from initial risk assessment through home-based training recommendations and longer-term follow-up.

Kani Chen, a professor in HKUST’s Department of Mathematics and Department of Industrial Engineering and Decision Analytics, leads the project. During development, the team visited special education institutions, child development centers and psychiatric hospitals in Hong Kong, the Greater Bay Area and Beijing, and engaged with nearly 500 parents of children with autism. The researchers used that work to shape a practical support tool around the difficulties families reported.

Home Videos Support Early Risk Screening

Parents can record short videos of a child’s everyday activities with a smartphone or another smart device, complete standardized questionnaires and provide basic developmental information. ASD Super Agent uses those inputs to generate a risk assessment and analytical report. The report is intended as a reference when families seek professional evaluation, not as a replacement for that evaluation.

The privacy design follows a data-minimization approach. It prioritizes extracting posture features on the user’s device and processes only information described as essential for analysis, an important consideration because the screening inputs include home videos and children’s developmental information.

Personalized Intervention and Professional Knowledge

Parents can describe challenges including emotional regulation difficulties, limited eye contact, communication difficulties or repetitive behaviors and receive customized support suggestions. Recommendations can include academic literature and background references to inform discussions with healthcare or educational professionals.

The platform’s 20+1 framework incorporates more than 20 autism intervention models and allows therapists, special education providers and organizations to add their own methods and practical experience to its knowledge base. Named approaches include Applied Behaviour Analysis, Naturalistic Developmental Behavioural Interventions, TEACCH Structured Teaching and the Localized BSR Model.

This structure combines research-based methodologies with frontline professional experience. It also gives professionals a route to contribute their own intervention knowledge rather than limiting the system to its initial set of models.

Follow-Up Profiles and a Research Database

For continuing support, the system combines text records, video assessments and developmental information supplied by families and professionals into a dynamic developmental profile for each child. It can divide long-term goals into manageable daily actions, track progress over time and support discussions between families and professionals. Voice interactions are currently supported in Cantonese, Putonghua and English.

The team has also built a multimodal autism database containing more than 1.1 million video, posture and behavioral records. HKUST says the database provides a foundation for AI model development and autism research, with continued data collection and analysis intended to improve risk-assessment accuracy, refine intervention recommendations and deepen understanding of autism development and support strategies.

The researchers plan to refine the user experience, expand clinical validation studies and strengthen system performance, with the goal of making autism support more accessible in Hong Kong, the Greater Bay Area and beyond. The central question for the next stage is whether clinical and real-world testing can substantiate the preliminary screening result and the platform’s integrated approach to family support.