MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611112749 A) filed by Sharda University on September 21, 2026, for Explainable Autism Risk Assessment System.
Inventors include Chesta Bhatia; Meenal Dahiya; and Kapil Kumar.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: Abstract Disclosed is an explainable clinical decision-support system for autism risk assessment. The system receives individual autism-screening questionnaire responses and demographic attributes and stores a trained extreme gradient boosting classifier, a Shapley Additive Explanations routine, and vector representations of autism-screening clinical literature. A processing unit excludes an aggregate questionnaire score from classifier input, generates an autism-risk prediction, determines per-instance contribution values, selects contributing questionnaire responses, and converts identities of the selected responses into a semantic natural-language query. Clinical-literature passages are retrieved using the query, and an evidence-grounded explanation is generated from the prediction, contribution values, and retrieved passages. An output interface presents the prediction together with clinical evidence retrieved through the questionnaire responses that contributed to the prediction. Fig. 1 Dated September 17, 2026 / Kumar Tushar Srivastava IN/PA-3973 Agent for the Applicant
Disclaimer: Curated by HT Syndication.
