An experimental study for breast cancer prediction algorithms

Breast Cancer has turned into a typical disease around the globe and harvesting the life of young women and the main source of cancer death and caused 22.9% of a wide range of cancers in women. The development of massive breast cancer screening has led to earlier diagnosis and rapid management with a significant improvement in survival rate. The problem of automatically searching for information contained in medical images is urgently needed. In order to process this large volume of information, doctors are currently turning to the use of Machine Learning (ML) systems to assist in the analysis and interpretation of these images. In this paper, we have conducted an experimental study for three major ML algorithms such as K-Nearest Neighbor (KNN), Random Forest (RF) and Multilayer Perceptron (MLP) to classify Brest cancer. The experiments were conducted on WDBC dataset to obtain the best algorithms in term of accuracy. Finally, identify the most specific and relevant attributes of the malignant tumour classification through more than one feature selection algorithms.