New Method for Rapid Diagnosis of Hepatitis Disease based on Reduction Feature and Machine Learning

  • Khorashadizade N
  • Rezaei H
  • 5

    Readers

    Mendeley users who have this article in their library.
  • N/A

    Citations

    Citations of this article.

Abstract

Hepatitis disease is caused by liver injury. Rapid diagnosis of this disease prevents its development and suffering to cirrhosis of the liver. Data mining is a new branch of science that helps physicians for proper decision making. In data mining using reduction feature and machine learning algorithms are useful for reducing the complexity of the problem and method of disease diagnosis, respectively. In this study, a new algorithm is proposed for hepatitis diagnosis according to Principal Component Analysis (PCA) and Error Minimized Extreme Learning Machine (EMELM). The algorithm includes two stages; in reduction feature phase, missing records were deleted and hepatitis dataset was normalized in [0,1] range. Thereafter, analysis of the principal component was applied for reduction feature. In classification phase, the reduced dataset is classified using EMELM. For evaluation of the algorithm, hepatitis disease dataset from UCI Machine Learning Repository (University of California) was selected. The features of this dataset reduced from 19 to 6 using PCA and the accuracy of the reduced dataset was obtained using EMELM. The results revealed that the proposed hybrid intelligent diagnosis system reached the higher classification accuracy and shorter time compared with other methods.

Author-supplied keywords

  • classification
  • dimensionality reduction
  • error minimized extreme learning
  • hepatitis disease
  • machine
  • principal component analysis

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Nahid Khorashadizade

  • Hassan Rezaei

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free