Machine Learning-Based Algorithms for Breast Cancer Prediction

Breast cancer detection is the process of identifying the presence of cancer cells or tumors in the breast tissue. It is a challenging task for doctors and researchers. Early detection of breast cancer is crucial for successful treatment and improved diagnosis and prognosis. There are several methods used for breast cancer detection. The diagnostic techniques used are time consuming and often costly. The goal of this paper is to propose a solution allowing to reduce the time to diagnosis breast cancer using Artificial Intelligence (AI) techniques. To this end, we propose an IA-based approach to train, test and validate three supervised Machine Learning algorithms: Logistic Regression, Random Forest Classification and Decision Tree for the classification of breast cancer into cancerous (malignant) and non-cancerous (benign). The performance of each algorithm is evaluated by some performance indicators such as accuracy and precision. A comparative study is conducted to determine which method gives the best results and outperforms the other methods. We prove that the Random Forest Machine approach outperforms the other studied Machine Learning algorithms with a score of 99.5% on the training data and 96.5% on testing data. As a result, we recommend it as the most effective algorithm for diagnosing breast cancer.