Paper Contents
Abstract
Heart disease is one of the leading causes of mortality worldwide. Accurate and early detection is vital for improving patient outcomes and optimizing medical interventions. In this paper, we propose a hybrid machine learning framework integrating image-based feature extraction using Gray Level Co-occurrence Matrix (GLCM), traditional feature selection techniques, and robust classification algorithms including AdaBoost with Decision Trees (AdaBoost-DT), K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN). The proposed system emphasizes not only classification accuracy but also interpretability and computational efficiency. GLCM-based statistical texture features, which quantify spatial relationships in medical imagery, are extracted and used as input features for model training. Feature selection is employed to reduce dimensionality, eliminate redundancy, and enhance classifier performance.
Copyright
Copyright © 2025 Sudhir Carpenter, Dr. Rishikesh Rawat. This is an open access article distributed under the Creative Commons Attribution License.
