MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641049328 A) filed by Sr University, Warangal, Telangana, on April 17, for 'an intelligent multimodal stroke assessment framework for early diagnosis and outcome prediction using deep learning.'
Inventor(s) include Burgula Sowmya; Dr. Johnson Kolluri; and Dr. P. Shailaja.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "Stroke (CVA) is a major cause of both death and disability throughout the world, and prompt and accurate diagnosis of CVA is essential to provide timely treatment via clinical intervention. This article outlines a multimodal assessment framework for CVA detection and outcome prediction via deep learning-based techniques. The proposed CVA assessment system integrates several types of heterogeneous data sources including multiple neuroimaging modalities (MRI, CT, etc.), clinical and demographic information, and provides an overall assessment of the pathological conditions that exist in patients who have had a CVA. The CVA assessment system employs deep learning techniques utilizing advanced machine learning models, including CNNs (convolutional neural networks) for lesion detection and segmentation and either recurrent or transformer-based model architectures for analyzing both temporal and clinical data to improve diagnosis accuracy. In addition to providing diagnosis, the CVA assessment system provides a prognostic module for predicting patient outcomes as well as a decision support service to assist clinicians with treatment decisions via an XAI (explainable artificial intelligence) component. Results from experimental evaluations indicate that the CVA Assessment System provides significantly better performance than traditional techniques in terms of accuracy, sensitivity, and specificity with respect to CVA detection and outcome prediction. Thus, the CVA assessment system provides a reliable and scalable solution for providing an accurate and timely diagnosis and outcome prediction for patients with CVAs, thereby enhancing patient management and decreasing the burden on the healthcare system. Keywords Stroke diagnosis, Deep learning, Multimodal data integration, Medical imaging analysis, Outcome prediction, Explainable artificial intelligence."
Disclaimer: Curated by HT Syndication.
