Analysis of SEER Dataset for Breast Cancer Diagnosis using C4.5 Classification Algorithm

Abstract: Medical professionals need a reliable prediction methodology to diagnose cancer and distinguish between the different stages in cancer. Classification is a data mining function that assigns items in a collection to target groups or classes. C4.5 classification algorithm has been applied to SEER breast cancer dataset to classify patients into either “Carcinoma in situ” (beginning or pre-cancer stage) or “Malignant potential” group. Pre-processing techniques have been applied to prepare the raw dataset and identify the relevant attributes for classification. Random test samples have been selected from the pre-processed data to obtain classification rules. The rule set obtained was tested with the remaining data. The results are presented and discussed.

Keywords: Breast Cancer Diagnosis, Classification, Clinical Data, SEER Dataset, C4.5 Algorithm