Various Preprocessing Methods for Neural Network Based Heart Disease Prediction

  • Kavita Burse
  • Vishnu Pratap Singh Kirar
  • Abhishek Burse
  • Rashmi BurseEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 851)


Medical diagnosis focuses on previous knowledge and behavior of the disease. Sometimes it is very difficult for a doctor to predict the disease accurately and fast, based on his knowledge and experience. With the development of machine learning algorithms diagnosis solutions can be developed for many personalized medical problems. Artificial Neural Network (ANN) is going to become an essential part of medical diagnosis. ANN provides self-learning mechanism for complex problems like medical diagnosis. In this research, we are going to propose a novel Multi-Layer Pi-Sigma Neuron Model (MLPSNM) for medical diagnosis. This MLPSNM can diagnose different medical conditions. Proposed MLPSNM is trained by using standard BP algorithm. The bipolar sigmoidal function is used as an activation function. Normalization, PCA, and LDA preprocessing is used for data preprocessing. SVM model with LDA is also proposed in this research. For testing of proposed MLPSNM we select the UCI machine learning datasets.


Heart disease Artificial neural network Preprocessing PCA LDA 


  1. 1.
    Perelson A.S., Oster G.F.: Theoretical studies of clonal selection: minimal antibody repertoire size and reliability of self-nonself discrimination. J. Theor. Biol. 81, 645–670 (1979)Google Scholar
  2. 2.
    Şahan, S., Polat, K., Kodaz, H., Gunes, S.: The medical application of attribute weighted artificial immune system (AWAIS): diagnosis of heart and diabetes disease. In: ICARIS’ vol. 2005, pp. 456–468 (2005)Google Scholar
  3. 3.
    Das, R., Turkoglu, I., Sengur, A.: Diagnosis of valvular heart disease through neural networks ensembles. Comput. Methods Programs Biomed. 93(2), 185–191 (2009)CrossRefGoogle Scholar
  4. 4.
    Karayilan, T., Kiliç, Ö.: Prediction of heart disease using neural network. In: 2017 International Conference on Computer Science and Engineering (UBMK), pp. 719–723 (2017)Google Scholar
  5. 5.
    Jabbar, M.A., Deekshatutu, B.L., Chandra, P.: Classification of heart disease using artificial neural network and feature subset selection. Glob. J. Comput. Sci. technol. Neural Artif. Intell. 13(3), 5–14 (2013)Google Scholar
  6. 6.
    Kavitha, K.S., Ramakrishnan, K.V., Singh, M.K.: Modeling and design of evolutionary neural network for heart disease detection. Int. J. Sci. Issues 7(5), 272–283 (2010)Google Scholar
  7. 7.
    Polat, K., Güneş, S., Tosun, S.: Diagnosis of heart disease using artificial immune recognition system and fuzzy weighted pre-processing. Pattern Recogn. 39(11), 2186–2193 (2006)CrossRefGoogle Scholar
  8. 8.
    Uyar, K., İlhan, A.: Diagnosis of heart disease using genetic algorithm based trained recurrent fuzzy neural networks. Procedia Comput. Sci. 120, 588–593 (2017)CrossRefGoogle Scholar
  9. 9.
    Shah, S.M.S., Batool, S., Khan, I., Ashraf, M.S., Abbas, S.H., Hussain, S.A.: Feature extraction through parallel probabilistic principal component analysis for heart disease diagnosis. Phys. Stat. Mech. Appl. 482, 796–807 (2017)CrossRefGoogle Scholar
  10. 10.
    Nilashi, M., Ibrahim, O.B., Ahmadi, H., Shahmoradi, L.: An analytical method for diseases prediction using machine learning techniques. Comput. Chem. Eng. 106, 212–223 (2017)CrossRefGoogle Scholar
  11. 11.
    Kelwade J.P., Salankar S.S.: Comparative study of neural networks for prediction of cardiac arrhythmias. In: International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT), pp. 1062–1066 (2016)Google Scholar
  12. 12.
    Burse K., Yadav, R.N., Srivastava, S.C.: Fully complex multiplicative neural network model and its application to channel equalization, in advances of neural network research and applications. In: Zeng Z., Wang, J. (eds.) Springer Lecture Notes in Electrical Engineering, vol. 67, pp. 493–501 (2010)Google Scholar
  13. 13.
    UCI Machine Learning Repository. Heart disease data set. (2015)

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Kavita Burse
    • 1
  • Vishnu Pratap Singh Kirar
    • 2
  • Abhishek Burse
    • 3
  • Rashmi Burse
    • 4
    Email author
  1. 1.Department of Electronics & CommunicationTechnocrats Institute of TechnologyBhopalIndia
  2. 2.Department of Computer ScienceUniversity of BedfordshireLutonUK
  3. 3.Department of Computer ScienceOriental Institute of Science and TechnologyBhopalIndia
  4. 4.Department of Computer ScienceMaulana Azad National Institute of TechnologyBhopalIndia

Personalised recommendations