Research on Logistic Regression Algorithm of Breast Cancer Diagnose Data by Machine Learning

Abstract

If machine learning can automatically identify cancer cells, it will provide considerable benefits to the medical system. The process of automation is likely to improve the efficiency of the detection process, and it may also provide higher detection accuracy by removing the internal subjective human factors in the process. Starting from the measurement data of biopsy cells in women with abnormal breast masses, logistic regression algorithm is applied to study the efficiency of machine learning for cancer detection. In this paper, the LogisticRegression algorithm of Sklearn machine learning library is used to classify the data sets of breast cancer (diagnosis). The classification results show that when the two features of maximum texture and maximum perimeter are selected, the classification accuracy is 96.5%, which is improved compared with the previous methods.