Chronic Disease Risk (CDR) Prediction in Biomedical Data Using Machine Learning Approach

  • Lambodar JenaEmail author
  • Soumen Nayak
  • Ramakrushna Swain
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 109)


Prediction of the target class accurately is a major problem in dataset. The objective of this work is mainly to predict the risk in chronic diseases using machine learning strategies such as feature selection and classification. The biomedical dataset on chronic kidney disease is considered for analysis of classification model. By taking biomedical dataset into our consideration, we have concentrated our focus on the implementation of classification algorithms in medical data and bioinformatics. In this work, two experiments have been carried out to study the nature and effectiveness of the classification methods on the given biomedical dataset (a) by considering all the features and (b) after feature reduction using genetic search algorithm. Here, three classifiers have been considered for the said purpose. Their performance is judged on various criteria to determine the best classifier for the prediction of chronic kidney disease (CKD). The results of both the experiments are estimated to determine the best classifier for prediction of the target class.


Machine learning Classification Genetic search Feature selection Accuracy Prediction 


  1. 1.
    Dhamodharan S (2014) Liver disease prediction using Bayesian classification, Special Issues. In: 4th National conference on advance computing, application technologies, May 2014Google Scholar
  2. 2.
    Solanki AV (2014) Data mining techniques using WEKA classification for sickle cell disease. Int J Comput Sci Inf Technol 5(4):5857–5860Google Scholar
  3. 3.
    Joshi J, Rinal D, Patel J (2014) Diagnosis and prognosis of breast cancer using classification rules. Int J Eng Res General Sci 2(6):315–323Google Scholar
  4. 4.
    David SK, Saeb AT, Al Rubeaan K (2013) Comparative analysis of data mining tools and classification techniques using WEKA in medical bioinformatics. Comput Eng Intell Syst 4(13):28–38Google Scholar
  5. 5.
    Vijayarani S, Sudha S (2013) Comparative analysis of classification function techniques for heart disease prediction. Int J Innov Res Comput Commun Eng 1(3):735–741Google Scholar
  6. 6.
    Kumar MN (2013) Alternating decision trees for early diagnosis of dengue fever. arXiv preprint arXiv:1305.7331
  7. 7.
    Durairaj M, Ranjani V (2013) Data mining applications in healthcare sector a study. Int J Sci Technol Res IJSTR 2(10)Google Scholar
  8. 8.
    Sugandhi C, Ysodha P, Kannan M (2011) Analysis of a population of cataract patient database in WEKA tool. Int J Sci Eng Res 2(10), October 2011Google Scholar
  9. 9.
    Yasodha P, Kannan M (2011) Analysis of population of diabetic patient database in WEKA tool. Int J Sci Eng Res 2(5), May 2011Google Scholar
  10. 10.
    Bin Othman MF, Yau TMS (2007) Comparison of different classification techniques using WEKA for breast cancer. In: 3rd Kuala Lumpur international conference on biomedical engineering 2006. Springer, Heidelberg, pp 520–523, Jan 2007CrossRefGoogle Scholar
  11. 11.
    Jena L, Kamila NK (2015) Distributed data mining classification algorithms for prediction of chronic- kidney-disease. Int J Emerg Res Manage Technol 4(11):110–118. ISSN 2278-9359Google Scholar
  12. 12.
    Jena L, Swain R (2017) Chronic disease risk prediction using distributed machine learning classifiers. In: Proceedings of IEEE International Conference on Information Technology (ICIT)-2017. doi:, 978-1-5386-2924-6/17 © 2017 IEEE
  13. 13.
    Jena L, Kamila NK (2014) A model for prediction of human depression using apriori algorithm. In: IEEE Xplore Digital Library proceedings, pp 240–244. ISBN 978-1-4799-4152-0Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Lambodar Jena
    • 1
    Email author
  • Soumen Nayak
    • 1
    • 2
  • Ramakrushna Swain
    • 3
  1. 1.Department of Computer Science and EngineeringSiksha O Anusandhan (Deemed to Be University)BhubaneswarIndia
  2. 2.Department of Computer Science and EngineeringIndian Institute of Technology (ISM)DhanbadIndia
  3. 3.Department of Computer Science and EngineeringSilicon Institute of TechnologyBhubaneswarIndia

Personalised recommendations