MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641074987 A) filed by Sr University on June 17, 2026, for Hybrid Machine Learning Approach For Early Detection Of Ovarian Cancer Using Svm And Knn Models With Feature Selection.
Inventors include B. Vijaya Kumari; Dr. C. Madan Kumar; and K. Swetha.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: HYBRID MACHINE LEARNING APPROACH FOR EARLY DETECTION OF OVARIAN CANCER USING SVM AND KNN MODELS WITH FEATURE SELECTION The invention presents a hybrid machine learning framework for the early detection of ovarian cancer by integrating biomarker data with physiological features and combining Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers through a majority voting ensemble. The system applies optimized feature selection techniques, including Recursive Feature Elimination and statistical methods, to identify the most relevant predictors and reduce noise. By leveraging the global classification strength of SVM and the local decision-making capability of KNN, the hybrid model achieves improved sensitivity and specificity, particularly for early-stage ovarian cancer. The framework is adaptive, scalable, and cost-effective, utilizing routine clinical and blood test data without reliance on expensive imaging. Experimental evaluation demonstrates higher accuracy, reduced false positives and negatives, and enhanced robustness compared to existing diagnostic methods. The invention provides a reliable, explainable, and practical decision-support tool for clinicians, enabling timely detection and improved patient outcomes.
Disclaimer: Curated by HT Syndication.
