Breast Cancer Prediction Based on K-Means and SOM Hybrid Algorithm

Abstract

Breast cancer is one of the most serious diseases that threaten women's health, affecting about 12.5% of women worldwide. Early detection of breast cancer is critical to saving lives. Therefore, If the physical examination indicators related to the human body can be extracted and the breast cancer can be analyzed through machine learning, which will play a key role in predicting and preventing breast cancer. As the high complexity and low precision of SOM neural network algorithm and shortcomings of K-means clustering algorithm needs to determine the number of clustering advanced and randomly select initial clustering centers, a hybrid algorithm combining K-means and SOM neural network is proposed in this study. The results show that the hybrid algorithm can accurately cluster the data sets, and compared with K means model and SOM neural network model, the performance of the hybrid algorithm model is better in clustering accuracy and computing speed.