基于机器学习的乳腺癌诊断框架

Ravi Kumar Sachdeva, Priyanka Bathla
{"title":"基于机器学习的乳腺癌诊断框架","authors":"Ravi Kumar Sachdeva, Priyanka Bathla","doi":"10.4018/ijsi.301221","DOIUrl":null,"url":null,"abstract":"Machine learning is used in the health care sector due to its ability to make predictions. Nowadays major cause of death in women is due to breast cancer. In this paper, a machine learning-based framework for the diagnosis of breast cancer has been proposed. The authors have used different feature selection methods on Breast Cancer Wisconsin (Diagnostic) dataset i.e. Chi-square, Pearson correlation between features and Feature importance. The competency of the feature selection methods has been analyzed using different machine learning classifiers on different performance parameters like accuracy, sensitivity, specificity, precision, and F-measure. Random Forest (RF), Extra Tree Classifier (ETC), and Logistic Regression (LR) machine learning classifiers have been used by the authors. Results reveal that FI (Feature Importance) is the preeminent feature selection method among all others used when applied with different classifiers. Results also show that the ETC machine learning classifier gives the best accuracy result in comparison with RF and LR classifiers.","PeriodicalId":396598,"journal":{"name":"Int. J. Softw. Innov.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"A Machine Learning-Based Framework for Diagnosis of Breast Cancer\",\"authors\":\"Ravi Kumar Sachdeva, Priyanka Bathla\",\"doi\":\"10.4018/ijsi.301221\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Machine learning is used in the health care sector due to its ability to make predictions. Nowadays major cause of death in women is due to breast cancer. In this paper, a machine learning-based framework for the diagnosis of breast cancer has been proposed. The authors have used different feature selection methods on Breast Cancer Wisconsin (Diagnostic) dataset i.e. Chi-square, Pearson correlation between features and Feature importance. The competency of the feature selection methods has been analyzed using different machine learning classifiers on different performance parameters like accuracy, sensitivity, specificity, precision, and F-measure. Random Forest (RF), Extra Tree Classifier (ETC), and Logistic Regression (LR) machine learning classifiers have been used by the authors. Results reveal that FI (Feature Importance) is the preeminent feature selection method among all others used when applied with different classifiers. Results also show that the ETC machine learning classifier gives the best accuracy result in comparison with RF and LR classifiers.\",\"PeriodicalId\":396598,\"journal\":{\"name\":\"Int. J. Softw. Innov.\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Int. J. Softw. Innov.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4018/ijsi.301221\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Int. J. Softw. Innov.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijsi.301221","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

摘要

机器学习因其预测能力而被用于医疗保健领域。现在妇女死亡的主要原因是乳腺癌。本文提出了一种基于机器学习的乳腺癌诊断框架。作者对乳腺癌威斯康星(诊断)数据集使用了不同的特征选择方法,即特征之间的卡方、Pearson相关性和特征重要性。使用不同的机器学习分类器对不同的性能参数(如准确性、灵敏度、特异性、精度和F-measure)进行特征选择方法的能力分析。随机森林(RF),额外树分类器(ETC)和逻辑回归(LR)机器学习分类器已被作者使用。结果表明,当使用不同的分类器时,FI (Feature Importance)是所有其他方法中最优的特征选择方法。结果还表明,与RF和LR分类器相比,ETC机器学习分类器的准确率最高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Machine Learning-Based Framework for Diagnosis of Breast Cancer
Machine learning is used in the health care sector due to its ability to make predictions. Nowadays major cause of death in women is due to breast cancer. In this paper, a machine learning-based framework for the diagnosis of breast cancer has been proposed. The authors have used different feature selection methods on Breast Cancer Wisconsin (Diagnostic) dataset i.e. Chi-square, Pearson correlation between features and Feature importance. The competency of the feature selection methods has been analyzed using different machine learning classifiers on different performance parameters like accuracy, sensitivity, specificity, precision, and F-measure. Random Forest (RF), Extra Tree Classifier (ETC), and Logistic Regression (LR) machine learning classifiers have been used by the authors. Results reveal that FI (Feature Importance) is the preeminent feature selection method among all others used when applied with different classifiers. Results also show that the ETC machine learning classifier gives the best accuracy result in comparison with RF and LR classifiers.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信