Vitiligo is growing at a good speed among the population and people have to go repeated surgeries to get rid of this disease. Though it’s not easy to define the stability, but it`s indispensable in the treatment of vitiligo. There have been many cases where people had gone for skin replacement surgery, but after sometime, white patches redeveloped on the skin. So the treatment goes on forever and patients get disheartened. The aim is to help people to identify the saturation of the disease before seeking the remedy which is skin transplantation. In this paper, improved J48 algorithm is used to predict the stability of vitiligo which gives optimal results. This algorithm uses the medical history of patients, Koebner phenomenon and VIDA score of sample data to feed into the systems and draw patterns to predict stability in the patients. We use various algorithms of data mining to extract useful information from data and check the accuracy of their medical history. The data includes the vitiligo patients, healthy people, the ones who have undergone surgery and the patients who haven’t undergone skin replacement and are still experiencing growth in their patches. With the prediction of various parameters, an optimal target value is predicted. In the end, we conclude with the most optimal algorithm which can be used to determine the stability of this disease and help the doctors and patients to determine the precise time of surgery.

J48 algorithm, Vitiligo, White patches, Patch development, data mining, prediction

[1] Witten, I. H. & Frank, E. (2005). Data Mining: Practical machine learning tools and techniques, (2ndEd.) San Francisco: Morgan Kaufmann.
[2] WEKA: Data Mining Software in Java.
[3] Falabella R. Surgical treatment of Vitiligo: Why, when and how. J Eur Acad Dermatol Venereol. 2003;17:518–20.
[4] Yusuf Perwej, Md. Husamuddin, Fokrul Alom Mazarbhuiya ,“An Extensive Investigate the MapReduce Technology”, International Journal of Computer Sciences and Engineering (IJCSE), E-ISSN : 2347-2693, Volume-5, Issue-10, Page no. 218-225, Oct-2017, DOI : 10.26438/ijcse/v5i10.218225
[5] M. Mohammad, “Performance Impact of Addressing Modes on Encryption Algorithms”, In the Proceedings of the 2001 IEEE International Conference on Computer Design (ICCD 2001), Indore, USA, pp.542-545, 2001.
[6] H.R. Singh, “Randomly Generated Algorithms and Dynamic Connections”, International Journal of Scientific Research in Network Security and Communication, Vol.2, Issue.1, pp.231-238, 2014.
[7] Rao A, Gupta S, Dinda AK, Sharma A, Sharma VK, Kumar G, et al. Study of clinical, biochemical and immunological factors determining stability of disease in patients with generalized vitiligo undergoing melanocyte transplantation. Br J Dermatol. 2012;166:1230–6.
[8] A. Mardin, T. Anwar, B. Anwer, “Image Compression: Combination of Discrete Transformation and Matrix Reduction”, International Journal of Computer Sciences and Engineering, Vol.5, Issue.1, pp.1-6, 2017.
[9] H.R. Singh, “Randomly Generated Algorithms and Dynamic Connections”, International Journal of Scientific Research in Network Security and Communication, Vol.2, Issue.1, pp.231-238, 2014.
[10] Ines D, Sonia B, Riadh BM, Amel el G, Slaheddine M, Hamida T, et al. A comparative study of oxidant-antioxidant status in stable and active vitiligo patients. Arch Dermatol Res. 2006;298:147–52.
[11] V. Krishnaiah, G. Narsimha, N. Subhash Chandra, “Heart Disease Prediction System using Data Mining Techniques and Intelligent Fuzzy Approach: A Review”, International Journal of Computer Applications, February 2016.
[12] Pattekari SA, Parveen A, “Prediction system for heart disease using naive bayes”, International Journal of Advanced Computation.
[13] R. Alizadehsani, J. Habibi, B. Bahadorian, et al., “Diagnosis of coronary artery stenosis using data mining”,J MED Signals Sens, vol. 2, pp. 153-9,2012.
[14] Upasana Juneja et. al., “Multi Parametric Approach Using Fuzzification on Disease Analysis”, IJESRT, Juneja et al., 3(5) ISSN: 2277-9655, Page No.492-497,2014.
[15] Hann SK, Shin HK, Park SH, Reynolds SR, Bystryn JC. Detection of antibodies to melanocytes in vitiligo by western immunoblotting. Yonsei Med J. 1996;37:365–70.
[16] Thirumal, P. C., & Nagarajan, N. (2015). Utilization of data mining techniques for diagnosis of diabetes mel-litus - A case study. ARPN Journal of Engineering and Applied Sciences, January, 10(1), 8-13.
[17] Naughton GK, Reggiardo D, Bystryn JC. Correlation between vitiligo antibodies and extent of depigmentation in vitiligo. J Am Acad Dermatol. 1986;15:978–81.
[18] Baharav E, Merimski O, Shoenfeld Y, Zigelman R, Gilbrund B, Yecheskel G, et al. Tyrosinase as an autoantigen in patients with vitiligo. Clin Exp Immunol. 1996;105:84–8.
[19] Xie Z, Chen D, Jiao D, Bystryn JC. Vitiligo antibodies are not directed to tyrosinase. Arch Dermatol. 1999;135:417–22.
[20] Hann SK, Park YK, Lee KG, Choi EH, Im S. Epidermal changes in active vitiligo. J Dermatol. 1992;19:217–22.
[21] Kumar R, Parsad D, Kanwar AJ. Role of apoptosis and melanocytorrhagy: A comparative study of melanocyte adhesion in stable and unstable vitiligo. Br J Dermatol. 2011;164:187–91.
[22] Ahn SK, Choi EH, Lee SH, Won JH, Hann SK, Park YK. Immunohistochemical studies from vitiligo: Comparison between active and inactive lesions. Yonsei Med J. 1994;35:404–10.