Performance Evaluation of Classification Algorithms for Early Detection of Behavior Determinant Based Cervical Cancer

Cervical cancers are very common and dangerous woman cancer which is caused from human papillomavirus. Transmission of this virus is happening during sexual intercourse and this cancer type is very common in low-income countries as condom usage rate is very low. This study is conducted to analyze performances of 8 different machine learning algorithms namely Bayesian Net, Naïve Bayes, J48, Random Tree, Random Forest, k-Nearest Neighbor, Logistic Regression and Support Vector Machine for classification of cancer and non-cancer patients. WEKA have been used as analyze tool. As a result of the study, it is stated that all applied algorithms could perform high accuracies while Support Vector Machine could reach to highest accuracy level with 91,67%.