Improving quality of breast cancer data through pre-processing

摘要

Using data mining for medical prognosis becomes a promising approach recently. In the mining process, theraw data are commonly suffering from outlier and imbalanced problems which affect the performance of themodel in predicting the unseen data. Thus, choosing appropriate data mining algorithms has a straightforward impact on the prediction model. The objective of this study is to investigate the use of three kinds ofdata pre-processing techniques including outlier filtering, Synthetic Minority Over-sampling TEchnique(SMOTE) and attribute selections for improving the quality of breast cancer data at Srinagarind Hospital inThailand. Three types of decision rule building techniques, i.e. Decision Table with Na?ve Bays (DTNB),Repeated Incremental Pruning to Produce Error Reduction (RIPPER) and PART Decision List were employed.The performance of proposed approaches was evaluated through the Area Under the receiver operatingcharacteristics Curve (AUC) of the decision rules. Experimental results have shown that applying the suitabledata pre-processing, especially the outlier filtering method, can lead to the significant improvement of theprediction performance of decision rule models.