Data preprocessing in knowledge discovery in breast cancer: systematic mapping study

Abstract

ABSTRACT Data Mining (DM) is a set of techniques that allow to analyse data from different perspectives and summarising it into useful information. Data mining has been increasingly used in medicine, especially in oncology. Data preprocessing is the most important step of knowledge extraction process and allows to improve the performance of the DM models. Breast cancer (BC) becomes the most common cancer among females worldwide and the leading cause of women's death. This paper aims to perform a systematic mapping study to analyse and synthesise studies on the application of preprocessing techniques for a DM task in breast cancer.Therefore, 66 relevant articles published between 2000 and October 2018 were selected and analysed according to five criteria: year/channel of publication, research type, medical task, empirical type and preprocessing task. The results show that Conferences and journals are the most targeted publication sources, researchers were more interested in applying preprocessing techniques for the diagnosis of BC, historical-based evaluation was the most used empirical type in the evaluation of preprocessing techniques in BC, and data reduction was the most investigated task of preprocessing in BC. However, A low number of papers discussed treatment which encourages researchers to devote more efforts to this task.