MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641085098 A) filed by Sasi Institute Of Technology And Engineering; P V V S Eswara Rao; G Prasanth Kumar; Lakshmanarao Talapakula; and P C S Nagendra Setty on July 11, 2026, for A Hybrid Multi-Modal Deep Learning Framework For Heart Stroke Prediction Using Clinical Parameters And Mri Imaging.

Inventors include P V V S Eswara Rao; G Prasanth Kumar; Lakshmanarao Talapakula; and P C S Nagendra Setty.

The application for the patent was published on July 17, 2026, under issue no. 29/2026.

Abstract: Stroke is a critical neurological disorder and one of the leading causes of death and long-term disability worldwide. Early prediction of stroke risk can significantly improve patient outcomes by enabling timely medical intervention and preventive care. This project presents a hybrid multi-modal deep learning framework that combines clinical health data and MRI brain imaging for accurate and reliable stroke risk assessment. The proposed system utilizes machine learning techniques to analyze structured clinical parameters such as age, hypertension, glucose level, body mass index, smoking history, and other relevant health indicators. Simultaneously, a deep learning model based on the ResNet50 architecture processes MRI brain scans to identify stroke-related abnormalities and pathological patterns. To enhance model interpretability and support clinical decision-making, SHAP (SHapley Additive exPlanations) is employed to explain the influence of individual clinical features on prediction outcomes. The predictions obtained from both clinical and imaging modalities are integrated through a fusion mechanism to generate a comprehensive risk score and classify patients into low, moderate, or high stroke-risk categories. Experimental evaluation demonstrates that the hybrid approach outperforms conventional single-modality methods by achieving higher predictive accuracy, robustness, and reliability. The proposed framework serves as an intelligent decision-support system for healthcare professionals, facilitating early diagnosis, personalized treatment planning, and improved stroke prevention strategies.

Disclaimer: Curated by HT Syndication.