Comparison of Several Machine Learning Algorithms in the Diagnosis of Cervical Cancer
Canfei Luo, Bingxiang Liu, Jingwen Xia · International Conference on Frontiers of Electronics, Information and Computation Technologies · 2021
Cervical cancer is a major disease endangering the health of women around the world. Every year, a large number of people die because of it. It also causes a huge economic burden to the families of patients. The application of machine learning algorithm in the diagnosis of cervical cancer can reduce the cost of manpower and material resources and achieve better diagnostic results. This paper aims to find a classification model with higher accuracy and better effect to classify cervical cancer patients. In this paper, the survey data for cervical cancer provided by UCI database are used, and the combination of up-sampling and down-sampling is used to balance the data set. Then, the data are predicted through SVM, KNN and CART respectively. After repeated experiments, we found that the prediction effect of CART algorithm has been significantly improved with BOOSTING. The model performed well in the identification of cervical cancer patients. All cervical cancer patients in the data were correctly classified, and the overall accuracy was 98.76%.