ML: Early Breast Cancer Diagnosis

Abstract

Breast cancer is the most common malignancy among women worldwide, often characterized by the uncontrolled proliferation of breast cells, leading to the formation of lumps or tumors that can be detected through medical imaging such as X-rays. Distinguishing between benign and malignant tumors presents a significant challenge in the diagnosis of breast cancer.

In this study, machine learning methods, including Logistic Regression, Gradient Boosting, Ada Boost, Random Forest, and Gaussian NB with Grid Search, were employed to differentiate between healthy individuals and those with malignancies. The results revealed that the Random Forest algorithm exhibited the highest performance in predicting breast cancer, accurately identifying 99 % of both healthy and affected individuals. Additionally, both Gradient Boosting and Ada Boost demonstrated a similar level of accuracy, correctly distinguishing 98 % of healthy and affected individuals.

Conversely, Gaussian NB performed the least effectively, with an accuracy of 91 % in differentiating between healthy and affected individuals, highlighting its comparatively lower predictive capability for breast cancer.