Multi-level Iterative Interdependency Clustering of Diabetic Data Set for Efficient Disease Prediction

  • B. V. BaijuEmail author
  • K. Rameshkumar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 750)


Clustering with diabetic data has been approached using several methods, though it suffers to achieve the required accuracy. To overcome the issue of poor clustering, multi-level iterative interdependency clustering algorithm has been presented here. The method generates initial cluster with random samples of the known classes and computes interdependency measure on different dimensions of the data point, and will be computed on the entire cluster samples for each data point identified. Then, the class with higher interdependency measure has been selected as the target class. This will be iterated for several times, until there is a movement of point. The number of classes is around the number of diseases considered and for each subspace, the interdependency measure has been estimated to identify the exact subspace of the data point. The method computes the multi-level disease dependency measure (MLDDM) on each disease class and their subspace, for prediction. A single disease class can be identified and their probability can be estimated according to the MLDDM measure. This method produces higher results in clustering and disease prediction.


Big data High dimensional clustering Interdependency measure MLDDM Subspace clustering 


  1. 1.
    Bansal, A.: Improved k-mean clustering algorithm for prediction analysis using classification technique in data mining. Int. J. Comput. Appl. 157(6), 0975–8887 (2017)Google Scholar
  2. 2.
    Jayalatchumy, D.: Prediction of diseases using Hadoop in big data–a modified approach. Artif. Intell. Trends Intell. Syst. pp. 229–238 (2017)Google Scholar
  3. 3.
    Umamaheswari, M., Isakki, P.: Myocardial infarction prediction using k-means clustering algorithm. Int. J. Innovative Res. Comput. Commun. Eng. 5(1) (2017)Google Scholar
  4. 4.
    Chikshe, N., Dixit, T., Gore, R., Akade, P.: Hybrid approach for heart disease detection using clustering and ANN. Int. J. Recent Innovation Trends Comput. Commun. 4(1), 119–122 (2016)Google Scholar
  5. 5.
    Jarad, A., Katkar, R., Shaikh, R.A., Salve, A.: Intelligent heart disease prediction system with MONGODB. Int. J. Emerg. Trends Technol. Comput. Sci. 4(1), 236–239 (2015)Google Scholar
  6. 6.
    Kaur, K., Singh, M.L.: Heart disease prediction system using ANOVA, PCA and SVM classification. Int. J. Adv. Res. Ideas Innovations Technol. 2(3), 1–6 (2016)Google Scholar
  7. 7.
    Prerana, T.H.M., Shivaprakash, N.C., Swetha, N.: Prediction of heart disease using machine learning algorithms-Naïve Bayes, introduction to PAC algorithm, comparison of algorithms and HDPS. Int. J. Sci. Eng. 3(2), 90–99 (2015)Google Scholar
  8. 8.
    Reddy, K.V.R., Raju, P.K., Kumar, J.M., Sujatha, C.H., Prakash, R.P.: Prediction of heart disease using decision tree approach. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 6(3), 530–532 (2016)Google Scholar
  9. 9.
    Shinde, R., Arjun, S., Patil, P., Waghmare, J.: An intelligent heart disease prediction system using k-means clustering and Naïve Bayes algorithm. Int. J. Comput. Sci. Inf. Technol. 6(1), 637–639 (2015)Google Scholar
  10. 10.
    Sahoo, P.K.: Analyzing healthcare big data with prediction for future health condition. IEEE Access, vol. 4 (2016)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Hindustan Institute of Technology and ScienceChennaiIndia

Personalised recommendations