• DocumentCode
    265026
  • Title

    Intelligent Breast Cancer Prediction Model Using Data Mining Techniques

  • Author

    Runjie Shen ; Yuanyuan Yang ; Fengfeng Shao

  • Author_Institution
    Dept. of Control Sci. & Eng., Tongji Univ., Shanghai, China
  • Volume
    1
  • fYear
    2014
  • fDate
    26-27 Aug. 2014
  • Firstpage
    384
  • Lastpage
    387
  • Abstract
    Breast cancer is the most common malignant tumor for women. In the past twenty years, the incidence of breast cancer continues to rise. Then, the diagnosis and treatment of the breast cancer have become an extremely urgent work to do. In this study, we intend to build a diagnostic model of breast cancer by using data mining techniques. A feature selection method, INTERACT is applied to select relevant features for breast cancer diagnosis, and the support vector machine is used to build the classification model. The results of the experiments show that the accuracy of the diagnostic model improves a lot by using feature selection method, and at the same time, nine relevant and important features for breast cancer diagnosis are chosen out. The diagnostic model for breast cancer built in this study has good generalization.
  • Keywords
    cancer; data mining; feature selection; medical diagnostic computing; patient treatment; support vector machines; tumours; INTERACT; breast cancer diagnosis; breast cancer treatment; data mining techniques; diagnostic model; feature selection method; intelligent breast cancer prediction model; malignant tumor; support vector machine; women; Accuracy; Breast cancer; Correlation; Data mining; Data models; Support vector machines; Breast cancer; diagnostic model; feature selection; support vector machine;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2014 Sixth International Conference on
  • Conference_Location
    Hangzhou
  • Print_ISBN
    978-1-4799-4956-4
  • Type

    conf

  • DOI
    10.1109/IHMSC.2014.100
  • Filename
    6917383