Ensemble swarm behaviour based feature selection and support vector machine classifier for chronic kidney disease prediction

  • Authors

    • S Belina V.J. Sara
    • K Kalaiselvi
    2018-05-29
    https://doi.org/10.14419/ijet.v7i2.31.13438
  • Chronic Kidney Disease (CKD), Enhanced Immune Clonal Selection (EICS), filter, wrapper methods, Feature selection, prediction, Support Vector Machine (SVM), University of California Irvine (UCI).
  • Kidney Disease and kidney failure is the one of the complicated and challenging health issues regarding human health. Without having any symptoms few diseases are detected in later stages which results in dialysis. Advanced excavating technologies can always give various possibilities to deal with the situation by determining important realations and associations in drilling down health related data.   The prediction accuracy of classification algorithms depends upon appropriate Feature Selection (FS) algorithms decrease the number of features from collection of data. FS is the procedure of choosing the most relevant features, removing irrelevant features. To identify the Chronic Kidney Disease (CKD), Hybrid Wrapper and Filter based FS (HWFFS) algorithm is proposed to reduce the dimension of CKD dataset.   Filter based FS algorithm is performed based on the three major functions: Information Gain (IG), Correlation Based Feature Selection (CFS) and Consistency Based Subset Evaluation (CS) algorithms respectively. Wrapper based FS algorithm is performed based on the Enhanced Immune Clonal Selection (EICS) algorithm to choose most important features from the CKD dataset.  The results from these FS algorithms are combined with new HWFFS algorithm using classification threshold value.  Finally Support Vector Machine (SVM) based prediction algorithm be proposed in order to predict CKD and being evaluated on the MATLAB platform. The results demonstrated with the purpose of the SVM classifier by using HWFFS algorithm provides higher prediction rate in the diagnosis of CKD when compared to other classification algorithms.

     

     

  • References

    1. [1] Zhang QL & Rothenbacher D, “Prevalence of chronic kidney disease in population-based studies: systematic reviewâ€, BMC public health, Vol.8, No.1, (2008).

      [2] Baumgarten M & Gehr T, “Chronic kidney disease: detection and evaluationâ€, American family physician, Vol. 84, No.10, (2011).

      [3] Moyer VA, “Screening for chronic kidney disease: Us preventive services task force recommendation statementâ€, Annals of internal medicine, Vol.157, No.8, (2012), pp.567–570.

      [4] Keane WF, Zhang Z & Lyle PA, “Risk scores for predicting outcomes in patients with type 2 diabetes and nephropathy: the RENAAL studyâ€, Clin J Am SocNephrol., Vol.1, No.4, (2006), pp.761-767.

      [5] Keith DS, Nichols GA & Gullion CM, “Longitudinal follow-up and outcomes among a population with chronic kidney disease in a large managed care organizationâ€, Arch Intern Med., Vol.164, No.6, (2004), pp.659-663.

      [6] Taal MW & Brenner BM, “Predicting initiation and progression of chronic kidney disease: developing renal risk scoresâ€, Kidney Int., Vol.70, No.10, (2006), 1694-1705.

      [7] Taal MW & Brenner BM, “Renal risk scores: progress and prospectsâ€, Kidney Int., Vol.73, No.11, (2008), pp.1216-1219.

      [8] Koh HC & Tan G, “Data mining applications in healthcareâ€, Journal of Healthcare Information Management, Vol.19, No.2, (2005), pp.64–72.

      [9] Han J & Kamber M, Data mining: concepts and techniques, 3rd ed. Burlington, MA: Elsevier, (2011).

      [10] Liu Y & Zheng YF, “FS-SFS:A novel feature selection method for support vector machinesâ€, Pattern Recognit., Vol.39, (2006), pp.1333–1345.

      [11] Reunanen J, “Overfitting in making comparisons between variable selection methodâ€, J. Mach. Learn. Res., Vol.3, (2003), pp.1371–1382.

      [12] Brown G, Pocock A, Zhao MJ & Luján M, “Conditional likelihood maximisation: a unifying framework for information theoretic feature selectionâ€, J. Mach. Learn. Res., Vol.13, No.1, (2012), pp.27–66.

      [13] Kohavi R & John GH, “Wrappers for feature subset selectionâ€, Artif. Intell., Vol.97, (1997), pp.273–324.

      [14] Chen G & Chen J, “A novel wrapper method for feature selection and its applicationsâ€, Neuro computing, Vol.159, (2015), pp.219–226.

      [15] Uncu O & Turksen IB, “A novel feature selection approach: combining feature wrappers and filtersâ€, Inf. Sci., Vol.177, (2007), pp.449–466.

      [16] Kunwar V, Chandel K, Sabitha AS & Bansal A, “Chronic Kidney Disease analysis using data mining classification techniquesâ€, 6th International Conference Cloud System and Big Data Engineering (Confluence), (2016), pp.300-305.

      [17] Boukenze B, Haqiq A & Mousannif H, “Predicting Chronic Kidney Failure Disease Using Data Mining Techniquesâ€, Advances in Ubiquitous Networking, (2017), pp.701-712.

      [18] Salekin A & Stankovic J, “Detection of Chronic Kidney Disease and Selecting Important Predictive Attributesâ€, IEEE International Conference on Healthcare Informatics (ICHI), (2016), pp.262-270.

      [19] Di Noia T, Ostuni VC, Pesce F, Binetti G, Naso D, Schena FP & Di Sciascio E, “An end stage kidney disease predictor based on an artificial neural networks ensembleâ€, Expert Systems with Applications, Vol.40, No.11, (2013), pp.4438-4445.

      [20] Padmanaban KA & Parthiban G, “Applying Machine Learning Techniques for Predicting the Risk of Chronic Kidney Diseaseâ€, Indian Journal of Science and Technology, Vol.9, No.29, (2016), pp.1-6.

      [21] Mohammed Siyad B, Manoj M, Mohammed Siyad B & Manoj M, “Fused features classification for the effective prediction of chronic kidney diseaseâ€, International Journal, Vol.2, (2016), pp.44-48.

      [22] Potharaju SP & Sreedevi M, “Ensembled Rule Based Classification Algorithms for predicting Imbalanced Kidney Disease Dataâ€, Journal of Engineering Science and Technology Review, Vol.9, No.5, (2016), pp.201-207.

      [23] Misir R, Mitra M & Samanta RK, “A reduced set of features for chronic kidney disease predictionâ€, Journal of Pathology Informatics, Vol.8, No.1, (2017), pp.24-29.

      [24] Levey AS & Coresh J, “Chronic kidney diseaseâ€, The Lancet, Vol.379, (2012), pp.165-180.

      [25] Levey AS, Coresh J, Bolton K, Culleton B, Harvey KS, Ikizler TA & Levin A, “K/DOQI clinical practice guidelines for chronic kidney disease: evaluation, classification, and stratificationâ€, American Journal of Kidney Diseases, Vol.39, (2002).

      [26] Anderson J & Glynn LG, “Definition of chronic kidney disease and measurement of kidney function in original research papers: A review of the literatureâ€, Nephrol Dial Transplant, Vol.26, (2011), pp.2793‑2798.

      [27] Lee IH, Lushington GH & Visvanathan M, “A filter-based feature selection approach for identifying potential biomarkers for lung cancerâ€, Journal of Clinical Bioinformatics, Vol.1, No.1, (2011), pp.1-8.

      [28] Hall MA, “Correlation-based feature selection for machine learningâ€, PhD, Department of Computer Science, The University of Waikato, Hamilton, (1999).

      [29] Arauzo-Azofra A, Benitez JM & Castro JL, “Consistency measures for feature selectionâ€, Journal of Intelligent Information Systems, Vol.30, No.3, (2008), pp.273-292.

      [30] Wang Q, Wang C & Gao XZ, “A hybrid optimization algorithm based on clonal selection principle and particle swarm intelligenceâ€, Sixth International Conference on Intelligent Systems Design and Applications, Vol.2, (2006), pp.975-979.

      [31] Jansen T & Zarges C, “Analyzing different variants of immune inspired somatic contiguous hyper mutationsâ€, Theoretical Computer Science, Vol.412, No.6, (2011), pp.517–533.

      [32] Pavone M, Narzisi G & Nicosia G, “Clonal selection: an immunological algorithm for global optimization over continuous spacesâ€, Journal of Global Optimization, Vol.53, No.4, (2012), pp.769–808.

      [33] Xie J & Wang C, “Using support vector machines with a novel hybrid feature selection method for diagnosis of erythematosquamous diseasesâ€, Expert Syst. Appl., Vol.38, (2011), pp.5809–5815.

  • Downloads

  • How to Cite

    Belina V.J. Sara, S., & Kalaiselvi, K. (2018). Ensemble swarm behaviour based feature selection and support vector machine classifier for chronic kidney disease prediction. International Journal of Engineering & Technology, 7(2.31), 190-195. https://doi.org/10.14419/ijet.v7i2.31.13438