Medical errors are considered as the leading cause of death and injury. Breast cancer becomes one of the leading causes of death among women, not only in the Philippines but worldwide. In this paper, data mining was used to predict the stage of breast cancer using a hybrid of fuzzy logic and decision tree. This aims to help experts to make decisions rather than replacing them. The result will only give an expert a recommendation, but the final decision is still on the hands of the experts. Feature selection was used to determine the best attribute in the dataset from Surveillance Epidemiology and End Results(SEER). The data set consists of incidence from 1975 to 2016, but the study limits the analysis from 2010 to 2016. Different cleaning and preprocessing of data are conducted. After thorough preprocessing of data, six(6) attributes are selected, and one(1) target class. Performance comparison shows that the fuzzy decision tree achieved a higher accuracy of 99.96%, sensitivity of 99.26% and specificity of 99.98% than the decision tree classification technique. The simulation result shows a correctly classified instance of 165,124, which is equivalent to 99.97% and only 351 incorrect classified instances or 0.21%. Thus, a fuzzy decision tree is more robust than the traditional decision tree classifier for predicting the stage of breast cancer.
类型: 国际会议
作者: Mylene J. Domingo,Bobby D. Gerardo,Ruji P. Medina
来源: 2019 International Conference on Advanced Information Science and System (AISS 2019) 2019-11-15
年度: 2019
分类: 基础科学,医药卫生科技
专业: 数学,外科学,肿瘤学
分类号: R737.9;O225
DOI: 10.26914/c.cnkihy.2019.078756
页码: 74-79
总页数: 6
文件大小: 354k
本文来源: https://www.lunwen90.cn/article/7dba9c9e85dee5ac104f2562.html