Early prediction of systemic lupus erythematosus using hybrid K-Means J48 decision tree algorithm

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    The objective of the paper is to propose an enhanced algorithm for the prediction of chronic, autoimmune disease called Systemic Lupus Erythematosus (SLE). The Hybrid K-means J48 Decision Tree algorithm (HKMJDT) has been proposed for the effective and early prediction of the SLE. The reason for combining both the clustering and classification algorithms is to obtain the best accuracy and to predict the disease in the early stage. The performance of algorithms such as Naïve Bayes, decision tree, random forest, J48 and Hoeffding tree has been combined with K-means clustering algorithm and compared in an effort to find the best algorithm for diagnosing SLE disease. The results of the statistical evaluation with the comparative study show that the effectiveness of different classification techniques depends on the nature and intricacy of the dataset used. K-means combined with J48 algorithm shows the best accuracy rate of 82.14% on the pre-processed data. The work-flow has been proposed to show the execution of the algorithm.


  • Keywords


    Use Data Mining; Auto-Immune; Lupus; J48; K-Means; Classification; Clustering; Chronic; Decision Tree; Sensitivity; Specificity; Accuracy

  • References


      [1] Gill JM, Quisel AM, Rocca PV, Walters DT. Diagnosis of systemic lupus erythematosus. J American family physician 2003; 12: 2179-2186.

      [2] Ben-Menachem E. Systemic lupus erythematosus: A review for anesthesiologists. J Anesthesia & Analgesia 2010; 9: 111(3):665-76.

      [3] [3] Wakoli, Leonard Wafula, Abkul Orto, and Stephen Mageto. Application of The K-Means Clustering Algorithm In Medical Claims Fraud/Abuse Detection. International Journal of Application or Innovation in Engineering & Management 2014; 7: 142-151.

      [4] [4] Kanungo T, Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY. An efficient k-means clustering algorithm: Analysis and implementation. IEEE transactions on pattern analysis and machine intelligence 2002; 7: 881-892.

      [5] Li T, Bai S, Ning J. K-means, an applicable and efficient clustering algorithm. Energy Procedia 2011; 11: 3189-3196.

      [6] Kaur G, Chhabra A. Improved J48 classification algorithm for the prediction of diabetes. International J of Computer Applications. 2014; 7: 13-17.

      [7] Wagh S, Khati A, Irani A, Inamdar N, Soni R. Effective Framework of J48 Algorithm using Semi-Supervised Approach for Intrusion Detection. International Journal of Computer Applications 2014; 5: 23-27.

      [8] Carreno LJ, Pacheco R, Gutierrez MA, Jacobelli S, Kalergis AM. Disease activity in systemic lupus erythematosus is associated with an altered expression of low‐affinity Fcγ receptors and costimulatory molecules on dendritic cells. J Immunology 2009; 11: 334-41.

      [9] Sayad, A. and Halkarnikar, P. Diagnosis of heart disease using neural network approach. In Proceedings of IRF International Conference, 13 April 2014; Pune, India: pp. 978–993.

      [10] Saigal, R., Kansal, A., Mittal, M., Singh, Y., Maharia, H. R. and Juneja, M. Clinical profile of systemic lupus erythematosus patients at a tertiary care centre in western india. J Indian Acad Clin Med 2011; 1: 27–32.

      [11] Lam GK, Petri M. Assessment of systemic lupus erythematosus. J Clinical and experimental rheumatology 2005; 9: 20-132.

      [12] Gladman DD, Urowitz MB, Esdaile JM, Hahn BH, Klippel J, Lahita R, Liang MH, Schur P, Petri M, Wallace D. Guidelines for referral and management of systemic lupus erythematosus in adults. J Arthritis and Rheumatism 1999; 9:1785-1796.

      [13] Gomathi, S. and Narayani, V. Preprocessing systemic lupus erythematosus (sle) data set with pentaho data integration (pdi). International J of Recent Innovation in Engineering and Research 2017; 3: 75-79.

      [14] Bouhmala N, Viken A, Lonnum JB. Enhanced Genetic Algorithm with K-Means for the Clustering Problem. Int J of Modelling and Optimization 2015; 3: 150-154.


 

View

Download

Article ID: 8982
 
DOI: 10.14419/ijet.v7i1.3.8982




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.