<![CDATA[Cancer is a leading cause of death globally, with over 10 million deaths reported in 2020, according to the World Health Organization (WHO). Early detection and accurate diagnosis are crucial to improving survival rates. However, conventional diagnostic methods such as biopsies and histopathological analysis have several limitations, including being invasive, time-consuming, and reliant on subjective interpretation by pathologists. With technological advancements, artificial intelligence (AI) and machine learning (ML) offer promising alternatives in cancer diagnosis. This study explores the effectiveness of the Support Vector Machine (SVM) algorithm in classifying cancer cells using the Breast Cancer Wisconsin dataset. The dataset consists of 699 cell samples obtained through fine needle aspiration, each described by 10 morphological features and labeled as benign or malignant. The results show that SVM with a Radial Basis Function (RBF) kernel can classify cancer cells with high accuracy. Data preprocessing, including cleaning and normalization, significantly improves model performance. Additionally, parameter optimization using grid search enhances the model’s reliability. This study highlights the strong potential of SVM as an efficient, accurate, and practical decision-support tool in medical diagnosis, particularly for cancer detection.]]>
Copyrights © 2023
