Health care data analysis using evolutionary algorithm

Article
  • 44 Downloads

Abstract

Assessment of huge amount of data is the difficult task in the health care industry. Hence, it here brings the important need of the data mining in identifying the relationship between the data attributes. In this research work, an assessment model for the health care analysis is developed with the preprocessing steps of performing data cleaning by applying normalization with outlier detection by applying the k-means clustering. Then, the preprocessed data are subjected to the dimensionality reduction process by performing the Feature Selection task. Then, the selected features are analyzed by the wrapper model named SVM-based improved recursive feature selection, and its accuracy is evaluated and compared with the other traditional classifiers such as Naïve Bayes. The analysis demonstrates that the planned perfect has accomplished a regular correctness of 98.79% of health care dataset such as Pima Indians diabetes. It demonstrates that the planned technique has achieved improved consequences.

Keywords

Recursive feature selection-based support vector machine (RFS-SVM) Health care analysis Conventional classifiers Medical data mining Pima diabetes 

References

  1. 1.
    Zhou J (2007) Feature selection in data mining—approaches based on information theory. VDM Verlag, SaarbrückenGoogle Scholar
  2. 2.
    Bu F, Chen Z, Zhang Q, Yang LT (2016) Incomplete high-dimensional data imputation algorithm using feature selection and clustering analysis on cloud. J Supercomput 72(8):2977CrossRefGoogle Scholar
  3. 3.
    Han J, Kamber M (2000) Data mining: concepts and techniques, 1st edn. Morgan Kaufmann Publishers, BurlingtonMATHGoogle Scholar
  4. 4.
    Rahm E, Do HH (2000) Data cleaning: problems and current approaches. IEEE Bull Tech Comm Data Eng 23(4):3–13Google Scholar
  5. 5.
    Lemke F, Mueller J-A (2003) Medical data analysis using self-organizing data mining technologies. Syst Anal Model Simul 43(10):1399–1408CrossRefGoogle Scholar
  6. 6.
    Matheny ME, Ohno-Machado L, Resnic FS (2005) Discrimination and calibration of mortality risk prediction models in interventional cardiology. J Biomed Inform 38(5):367–375CrossRefGoogle Scholar
  7. 7.
    Quinlan J (1993) C4.5: programs for machine learning. Morgan Kaufmann, San MateoGoogle Scholar
  8. 8.
    Pang-Ning T, Steinbach M, Kumar V (2006) Introduction to data mining. Library of Congress, WashingtonGoogle Scholar
  9. 9.
    Koh HC, Tan G (2005) Data mining applications in healthcare. J Health Care Inf Manag 19(2):64–72Google Scholar
  10. 10.
    Ordonez C (2004) Improving Heart Disease Prediction Using Constrained Association Rules. Seminar presentation at University of TokyoGoogle Scholar
  11. 11.
    Leskovec J, Rajaraman A, Ullman JD (2014) Mining massive datasets. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  12. 12.
    Lin K-C, Zhang K-Y, Huang Y-H, Hung JC, Yen N (2016) Feature selection based on an improved cat swarm optimization algorithm for big data classification. J Supercomput 72(8):3210CrossRefGoogle Scholar
  13. 13.
    Carlsson G, Mémoli F (2010) Characterization, stability and convergence of hierarchical clustering methods. J Mach Learn Res 11:1425–1470MathSciNetMATHGoogle Scholar
  14. 14.
    Osl M, Dreiseit S, Cerqueira F, Netzer M, Pfeifer B, Baumgartner C (2009) Demoting redundant features to improve the discriminatory ability in cancer data. J Biomed Inform 42(4):721–725CrossRefGoogle Scholar
  15. 15.
    Cios KJ, William Moore G (2002) Uniqueness of medical data mining. Artif Intell Med 26(1):1–24CrossRefGoogle Scholar
  16. 16.
    Sufi F (2011) Diagnosis of cardiovascular abnormalities from compressed ECG: a data mining-based approach. IEEE Trans Inf Technol Biomed 15(1):3–39CrossRefGoogle Scholar
  17. 17.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines. Cambridge University Press, CambridgeMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNehru Institute of Engineering and TechnologyCoimbatoreIndia
  2. 2.Department of Electronics and Instrumentation EngineeringNational Institute of Technology, NagalandDimapurIndia
  3. 3.Department of Electronics and Communication EngineeringSri Ramanujar Engineering CollegeChennaiIndia

Personalised recommendations