Heart Disease Diagnosis Using Diverse Neural Network Categories

  • Mostafa Ibrahem HassanEmail author
  • Ahmed Hamza OsmanEmail author
  • Eltahir Mohamed HusseinEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1073)


This study indicated an intelligent diagnosis method about the heart disease based on the diversity of artificial neural networks algorithms. The major objective was to improve the heart disease diagnosis accuracy, and reducing the miss-diagnosis results. One of the disadvantages of the current heart disease diagnosis methods that the diagnosis is expensive and not accurate enough to confirm the diagnosis of the heart disease. Our study will help the medical doctors to make appropriate diagnosis process and thus take specific treatment of the heart diseases easily. Our suggested method used Heart Diseases Database (Cleveland database) for training and testing phases. We used five neural networks: Quick, RBFN, Multiple, Prune, and Exhaustive. Our results revealed that the dynamic neural network algorithm was the best method diagnosing heart diseases accurately. We recommend using Dynamic neural network algorithm as the routine and sensitive method for diagnosis of heart disease easily and specifically.


Neural networks Heart disease Cleveland 


  1. 1.
    Severs, N.J.: The cardiac muscle cell. BioEssays 22(2), 188–199 (2000)CrossRefGoogle Scholar
  2. 2.
    Kastor, J.A.: Cardiac Arrhythmias, Encyclopedia of Life Sciences. Macmillan Publishers Ltd., Nature Publishing Group. e LS (2001)Google Scholar
  3. 3.
    National Heart Foundation of Australia: Understanding abnormal heart rhythm, Heart Foundation, pp. 1–9 (2017)Google Scholar
  4. 4.
    Curran, T., Sheppard, G.: Cardiac arrhythmias: mechanisums of arrhythmias – atrial, ventricular, conduction and ST changes, canterbury district health board, pp. 1–74 (2011)Google Scholar
  5. 5.
    Hakim, A.N.: Predicting heart attacks in patients using artificial intelligence methods. Mod. Appl. Sci. 10(3), 66–78 (2016)CrossRefGoogle Scholar
  6. 6.
    UK Factsheet - British Heart Foundation. Accessed 25 July 2019
  7. 7.
    UCI Machine Learning Repository - Center for Machine Learning and Intelligent Systems. Accessed 25 July 2019
  8. 8.
    Padma, T., Latha, M., Jayakumar, K.: Decision making algorithm through LVQ neural network for ECG arrhythmias. In: 13th International Conference on Biomedical Engineering, vol. 23, pp. 85–88. Springer, Heidelberg (2009)Google Scholar
  9. 9.
    Jadhav, S.M., Nalbalwar, S.L., Ghatol, A.A.: Artificial neural network based cardiac arrhythmia diseases diagnosis. In: International Conference on Process Automation, Control and Computing, pp. 1–6. IEEE Xplore,‏ 12 August 2011Google Scholar
  10. 10.
    Dessai, I.S.F.: Intelligent heart disease prediction system using probabilistic neural network. Int. J. Adv. Comput. Theory Eng. (IJACTE) 2(3), 2319–2526 (2013)Google Scholar
  11. 11.
    Shouman, M., Turner, T., Stocker, R.: Applying k-nearest neighbors in diagnosing heart diseases patients. Int. J. Inform. Educ. Technol. 2(3), 220–223 (2012)CrossRefGoogle Scholar
  12. 12.
    Purusothaman, G., Krishnakumari, P.: A survey of data mining techniques on risk prediction: heart diseases. Indian J. Sci. Technol. 8(12), 1–5 (2015)CrossRefGoogle Scholar
  13. 13.
    Chandna, D.: Diagnosis of heart diseases using data mining algorithm. Int. J. Comput. Sci. Inform. Technol. (IJCSIT) 5(2), 1678–1680 (2014)Google Scholar
  14. 14.
    Prabhavathi, S., Chitra, D.M.: Analysis and prediction of various heart diseases using DNFS techniques. Int. J. Innov. Sci. Eng. Res. (IJISER) 2(1), 1–7 (2016)Google Scholar
  15. 15.
    Ajam, N.: Heart diseases diagnoses using artificial neural network, network and complex systems, vol. 5, no. 4, pp. 7–11 (2015). ISSN 2224-610X (Paper), ISSN 2225-0603(Online)Google Scholar
  16. 16.
    Rabbi, M.F., Uddin, M.P., Ali, M.A., Kibria, M.F., Afjal, M.I., Islam, M.S., Nitu, A.M.: Performance evaluation of data mining classification techniques for heart diseases prediction. Am. J. Eng. Res. (AJER), 7(2), 278–283Google Scholar
  17. 17.
    Mitra, M., Samanta, R.: Cardiac arrhythmia classification using neural networks with selected features. Proc. Technol. 10, 76–84 (2013)CrossRefGoogle Scholar
  18. 18.
    Özbay, Y., Ceylan, R., Karlik, B.: A fuzzy clustering neural network architecture for classification of ECG arrhythmias. Comput. Biol. Med. 36(4), 376–388 (2006)CrossRefGoogle Scholar
  19. 19.
  20. 20.
    SOURCEFORGE. Accessed 25 July 2019
  21. 21.
  22. 22.
  23. 23.
  24. 24.
    UCI Machine Learning Repository - Center for Machine Learning and Intelligent Systems. Accessed 25 July 2019

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Administration of IT, Faculty of Igraa for Computer StudiesInternational University of AfricaKhartoumSudan
  2. 2.Sudan Academic for Graduate StudiesAfrica City of TechnologyKhartoumSudan
  3. 3.Department of Information System, Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahKingdom of Saudi Arabia
  4. 4.Department of Information System, Faculty of EngineeringSudan University of Science and TechnologyKhartoumSudan

Personalised recommendations