MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202611101523 A) filed by Chandigarh University on August 22, 2026, for Integrated Deep Learning System For Autism Diagnosis With Explainable Multimodal Risk Stratification.
Inventors include Binod Kumar Mishra; Munish Kumar; and Vishal Sharma.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention discloses a multimodal, explainable artificial intelligence system for early screening and risk stratification of Autism Spectrum Disorder (ASD). The system integrates speech signal processing, natural language processing, and computer vision based behavioural analysis to evaluate verbal and non-verbal indicators. Multimodal data acquired through microphones and cameras are adaptively pre-processed using environment-aware modules, ensuring robustness under noisy or incomplete conditions. A dynamic confidence-weighted fusion engine combines acoustic, linguistic, and behavioural features, while machine learning and deep learning models estimate ASD risk levels. An embedded explainable AI module generates clinician-readable rationales and feature contribution maps, enhancing transparency and trust. The system outputs stratified risk categories with confidence scores, supports multilingual adaptation, and enables lightweight edge deployment with privacy preservation. This invention provides rapid, objective, and scalable ASD screening across diverse linguistic and resource-constrained healthcare environments.
Disclaimer: Curated by HT Syndication.
