MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202531129677 A) filed by Guru Nanak Institute Of Technology, Kolkata, West Bengal, on Dec. 20, 2025, for 'using machine learning techniques to predict stroke risk in patients.'
Inventor(s) include Priyanka Ghosh; Pallabi Das; Moloy Dhar; Sankalan Roy; Sovon Roy; Mousoom Samanta; Soyel Uddin Munshi; and Arpan Mandal.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "A modular supervised machine-learning system and method for predicting heart stroke risk from patient clinical features is disclosed that loads a clinical dataset (for example heart.csv), performs exploratory data analysis and preprocessing (scaling, encoding, feature selection), trains multiple supervised classifiers (including Logistic Regression, Decision Tree, Random Forest, Naive Bayes, XGBoost, SVM and KNN), evaluates classifiers using accuracy, precision, recall, F1-score and confusion matrices, and visualizes comparative results to support clinician interpretation; the system supports selection and deployment of a best performing model for integration with Electronic Health Records (EHR) and offers secure, scalable deployment options including encryption, cloud and optional decentralised data management technologies, and is demonstrated on the disclosed dataset with Random Forest yielding the highest reported accuracy of approximately 90.16%."
Disclaimer: Curated by HT Syndication.
