Cervical Cancer Risk Factors: Classification and Mining Associations

Abstract

Women of all over the world suffer from a common cancer, named Cervical cancer. Cervical cancer cells grow slowly at the cervix. This cancer can be avoided if it is recognized and handled in its first stage. Now it is a key challenge for Medical experts to identify such cancer before it develops extremely. Nowadays, data mining models are popularly used to extract hidden patterns from huge medical dataset. This paper introduces data mining techinques for classification and finding associations in order to detect Cervical cancer at early stage. After preprocessing, the dataset was tested on Decision Tree, Random Forest, Logistic Model Tree and Artificial Neural Network. These methods achieve considerable success in case of both K-fold cross validations and randomly split dataset. Association rules has been established for detecting comparatively riskier factors which are more responsible for cancer development. The proposed methodology can help Medical experts to conduct their research on Cervical cancer.