Intellectual Property India Publishes Patent Application for System And Method For Cerebrovascular Accident Prediction Using Machine Learning And Deep Learning Techniques

MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202621048310 A) filed by Symbiosis International Deemed University on April 15, 2026, for System And Method For Cerebrovascular Accident Prediction Using Machine Learning And Deep Learning Techniques.

Inventors include Dr. Gagandeep Kaur; Dr. Latika Pinjarkar; Shafaq; Samar Jaiswal; and Sejal Dhande.

The application for the patent was published on June 12, 2026, under issue no. 24/2026.

Abstract: ABSTRACT SYSTEM AND METHOD FOR CEREBROVASCULAR ACCIDENT PREDICTION USING MACHINE LEARNING AND DEEP LEARNING TECHNIQUES The present invention relates to a system (100) and method for predicting cerebrovascular accidents using integrated machine learning and deep learning techniques. The system (100) comprises a data acquisition module (110) for receiving clinical patient data, a data preprocessing module (120) for handling missing values and transforming categorical variables using one-hot encoding, a dataset balancing module (130) implementing Synthetic Minority Over-sampling Technique (SMOTE) for addressing class imbalance, an exploratory data analysis module (140) for feature analysis, a model deployment module (150) incorporating Logistic Regression classifier (151), Random Forest Classifier (152), and Convolutional Neural Network (153), and a model evaluation module (160) for computing performance metrics. The Random Forest Classifier (152) achieves 95% accuracy and 98.99% ROC-AUC, demonstrating superior stroke prediction performance. The invention enables healthcare providers to assess stroke risk in patients based on clinical parameters with high accuracy, facilitating timely intervention and improved patient outcomes. [

Disclaimer: Curated by HT Syndication.