Breast Cancer Prediction of Benign and Malignant Tumors by Classification Algorithms

Breast cancer is a disease that affects both males and females, but it is more commonly found in females. It is considered the most common form of cancer among women worldwide. Unfortunately, breast cancer can be fatal and is the most invasive cancer in women globally. The absence of symptoms in the early stages of the disease often leads to a delayed diagnosis, rendering medical treatment ineffective. However, early screenings can reduce the mortality rate associated with breast cancer. In addition to traditional medical diagnosis methods, machine learning techniques can be utilized to predict breast cancer risk using health data. In this study, we attempted to compare various machine learning classification algorithms, such as the Decision Tree Classifier, Logistic Regression, KNeighbors Classifier, and Naïve Bayes Classifier. The results indicate that the Naïve Bayes Classifier outperformed the other algorithms in terms of performance. Experimental results show that the Naïve Bayes Classifier yields the highest accuracy (93%). Future research will explore fuzzy logic, rule-based methods for accurate breast cancer diagnosis, and expert validation of the model.