Breast Cancer Subtype Classification using Clinical and Gene Expression Integration
Ala’a El-Nabawy, Nahla A. Belal, Nashwa El-Bendary · 2017
According to the World Health Organization (WHO), cancer is one of the leading causes of death worldwide. Breast cancer is considered the most common type of cancer among women and it has five subtypes. In research, when applying machine learning classification techniques, breast cancer subtypes are classified based on images, gene expression, or clinical datasets. This paper proposes a classification approach for breast cancer subtypes based on integrated clinical and dimensionally reduced gene expression dataset. Obtained experimental results showed that the proposed approach outperformed commonly used classification approaches that solely use either gene expression or clinical dataset. The highest classification accuracy achieved by the proposed approach was 86.96%, using Random Forest classifier.