BREAST CANCER DETECTION USING MACHINE LEARNING

Abstract

Breast cancer is a prevalent disease worldwide, with women being more susceptible to it.Early detection is crucial for the successful treatment of breast cancer.Therefore, there have been numerous studies on breast cancer to improve early detection and lower mortality rates.Breast cancer has surpassed lung cancer as the most prevalent cancer in women worldwide today.In the medical industry, machine learning techniques are being employed more and more, particularly for diagnoses and decision-making.The effectiveness of many machinelearning methods for identifying breast cancer, such as logistic regression, decision trees, and random forests, was assessed.This study utilized the Wisconsin breast cancer datasets.The primary objective was to assess the effectiveness and efficiency of these algorithms in accurately categorizing breast cancer cases, based on metrics such as accuracy, precision, sensitivity, and specificity.The study also involved data visualization to gain insights into the characteristics of the dataset.The study's findings may contribute to the creation of breast cancer detection techniques that are more precise and effective, thereby improving patient outcomes.