MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202541122631 A) filed by Easwari Engineering College, Chennai, Tamil Nadu, on Dec. 5, 2025, for 'explainable multimodal ai framework for remote dementia monitoring and early detection.'
Inventor(s) include Lekhsha P; Harshavardhini P M; Jayachandran E K; and S. Maheswari.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to an explainable multimodal Al framework for early detection 10 and remote monitoring of dementia by integrating brain MRI scans, clinical information, and speech features. MRI images are processed using convolutional neural networks to extract deep visual features, clinical records are structured into numerical vectors, and speech data is analyzed to capture temporal patterns. These multimodal features are fused and classified using the XGBoost algorithm to predict 15 dementia stages with improved accuracy. An explainability module based on Gradient-weighted Class Activation 'Mapping (Grad-CAM) highlights critical MRI regions' and key contributing factors, thereby enhancing clinical trust and interpretability. The system is deployed as a Flask-based web platform with SQLite storage, enabling remote patient data upload and clinician access. Cognitive 20 assessments, including memory games and speech tasks, support non-real-time monitoring. The invention ensures interpretability, scalabity, and usability, advancing dementia"detection and healthcare delivery."
Disclaimer: Curated by HT Syndication.
