A novel eXplainable AI agent for social interaction training of people with Autism Spectrum Disorder (ASD)

• Published in: International journal of information technology (Singapore. Online) Vol. 17; no. 5; pp. 2957 - 2969
• Main Authors: Gupta, Prashant K., Mazumdar, Bireshwar Dass, Mishra, Manmohan, Chadha, Rubina, Komaragiri, Rama S.
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.06.2025; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Autism; Computer Imaging; Computer Science; Deep learning; Explainable artificial intelligence; Image Processing and Computer Vision; Interaction models; Literature reviews; Machine Learning; Neurological diseases; Original Research; Pattern Recognition and Graphics; Social interaction; Software Engineering; Vision; EXplainable AI; Artificial intelligence (AI); Social interaction training; Autism spectrum disorder; Neurological disorders; AI Agent
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-025-02486-0

Autism Spectrum Disorder (ASD) is a neurological disorder that impacts a subject’s ability to be involved in a social interaction. Machine learning (ML) and deep learning (DL) models have been mainly used for ASD detection, which are however criticized for their ‘black-boxness’, advocating the use of eXplainable artificial intelligence (XAI) algorithms. As per the literature search so far, no social interaction model-based eXplainable Autism Spectrum Disorder (ASD) care agent exists for social interaction training of an ASD subject. Therefore, this work makes a beginning in this direction. A novel architecture of an eXplainable ASD care agent for social interaction training of ASD subjects, with an underlying intelligent AI algorithm is presented. Its working is elucidated through six representative social interaction scenarios and some practical considerations are also presented when the agent is put in practice with the ASD subject. The working of the proposed ASD care agent is also depicted through a suitable case study.