Information retrieval using machine learning from breast cancer diagnosis

Breast cancer is one of the most common cancers among females. Patients with breast cancer are regularly rising. The survival of patients can be improved by early diagnosis and treatment. Because of its success, machine learning is commonly used in most fields. In this paper, numerous methods for early detection of this disease are employed for machine learning. Here, we consider C 5.0, Naive Bayes, logistic regression, random forest, ctree, KNN, K-Mean, GBM, adaBoost, decision tree model to classify the breast cancer tumor and evaluate their performances based on Wisconsin and SEER datasets. The demonstrations of the classifiers were assessed using accuracy, precision, recall, and F1 measure. We also predict whether the tumor is dead or alive, considering the tumor size, the various cancer stages, and months' survival. The general research will increase people's understanding of breast cancer and reduce tumor fears.