Classify Breast Cancer Patients using Hybrid Data-Mining Techniques

Abstract

According to the World Health Organization (WHO), breast cancer is a disease that leads to death, especially for women who have neglected or ignored the risk factors. Doctors can classify patients according to clinical information, famous disease symptoms, or similar cases. But, some cases are difficult to detect early or diagnose accurately. Therefore, the most important challenge faced by researchers in this field is how to classify patient data by extracting important information that leads to the detection of the disease early and correctly. This article proposes the enhanced system of a decision support system based on hybrid classification algorithms to classify Breast cancer patients accurately and quickly. The main contribution of this article is to develop an algorithm that filters the data and solves the problem of missing data in some records to facilitate the classification of data. In the experiments conducted, the proposed system was learned by several algorithms on a standard Electronic Health Records (HER) dataset to determine the appropriate test factors. Four experiments were performed to measure the accuracy and speed of the different data mining techniques. The proposed ensemble process achieved a high accuracy rate up to 99% in a good time.