MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202611109114 A) filed by Dr Devesh Katiyar; and Dr Adarsh Kumar Singh on September 11, 2026, for Samvedna- Ai: A Privacy Preserving Explainable Multimodal Artificial Intelligence System And Method For Early Mental Health Risk Prediction, Personalized Screening And Clinical Decision Support Among Transgender And Divyang Individuals.
Inventors include Dr Devesh Katiyar; Dr Vinodani Katiyar; Bhanu Singh; Alka Patel; Dr Neeraj Kumar; Vikas Dixit; Mohd Sayeed Khan; and Dr Adarsh Kumar Singh.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention relates to SAMVEDNA- AI, a privacy preserving explainable multimodal artificial intelligence system and method for early prediction of depression, anxiety, psychosomatic disorders and related mental health conditions among transgender and Divyang transgender individuals. The invention integrates psychological assessments, behavioural indicators, psychosocial determinants, demographic variables, optional speech derived features, digital behavioural patterns and clinical information within a unified AI framework. The collected data are preprocessed, transformed into predictive features and analyzed using machine learning or deep learning models capable of generating individualized mental health risk scores. An explainable artificial intelligence module provides transparent interpretation of prediction outcomes through feature importance analysis and confidence estimates, while a privacy preserving framework employs anonymization, encryption, secure authentication, and privacy enhancing computation. Based on predicted risk, the system generates personalized intervention recommendations, referral pathways, clinician alerts and follow up schedules. Accessibility features support multilingual interaction and disability friendly interfaces to improve usability among transgender and Divyang populations. The invention enables scalable, equitable, and interpretable digital mental healthcare while maintaining confidentiality and facilitating timely clinical decision making.
Disclaimer: Curated by HT Syndication.
