Using Logistic Regression and Support Vector Classification to Predict Cancer

Abstract

This study investigates the application of machine learning (ML) algorithms in the early diagnosis of breast cancer, focusing on logistic regression and Support Vector Classification (SVC). Utilizing a dataset from Kaggle, which includes diverse clinical features from breast mass samples, the research conducts a comparative analysis of these models in terms of accuracy and interpretability. Our findings reveal that both logistic regression and SVC demonstrate high precision in distinguishing between benign and malignant tumors, with SVC showing a marginally superior performance due to its higher sensitivity and lower rate of false negatives. The study emphasizes the potential of ML in enhancing cancer diagnostic processes, highlighting the importance of non-invasive, cost-effective, and accurate diagnostic alternatives. It also addresses the challenges of model interpretability and the need for more transparent ML applications in clinical settings. This research paves the way for future advancements in medical diagnostics, offering promising directions for integrating ML algorithms into clinical decision-making and patient care.