Breast Cancer Prediction Using Hybrid Logistic Regression

Breast cancer is more frequently diagnosed in women than in males, and it starts in the breast cells. Breast cancer frequently begins as a noticeable lump in the breast that can be felt; approximately 80% of cases are found by these kinds of self-examinations. Timely and accurate diagnosis is essential for effective therapy, since early identification greatly improves patient outcomes. In this study, we investigate the use of machine-learning methods in breast cancer early detection. The use of machine learning in cancer diagnosis and detection has shown to be quite successful. We used a dataset from the reputable and well-known data science project site Kaggle for our investigation. Using this Kaggle dataset, we applied a range of machine-learning algorithms, including sophisticated deep learning techniques. Our model proved to be a useful tool for early breast cancer detection, with a 95% accuracy rate and a 96% sensitivity. This study offers compelling evidence that using machine-learning algorithms on datasets from sites like as Kaggle can predict breast cancer with a high degree of accuracy.