IJSER Home >> Journal >> IJSER
International Journal of Scientific and Engineering Research
ISSN Online 2229-5518
ISSN Print: 2229-5518 10    
Website: http://www.ijser.org
scirp IJSER >> Volume 2, Issue 10, October 2011 Edition
Analysis of A Population Of Cataract Patients Databases In Weka Tool
Full Text(PDF, 3000)  PP.  
C.sugandhi, P.Yasodha, M.Kannan
Data Mining, Classification, Decision Tree Algorithm, Weka tool
Data mining refers to extracting knowledge from large amount of data. Real life data mining approaches are interesting because they often present a different set of problems for data miners. The process of designing a model helps to identify the different Cataract Diseases. A cataract can cause a decrease in visual function, which in turn can be classified as a visual disability. Thus, cataract can be defined in three ways. The first definition is an objective lens change. The second is a lens opacity that is associated with a defined level of visual acuity loss. The third relates to the functional consequences of lens opacification. This guideline focuses on the last definition. It deals with care of the patient with functional impairment due to cataract and improvement in function as a result of treatment for the condition. Taking into account the prevalence of cataract among men and women the study is aimed at finding out the characteristics that determine the presence of cataract and to track the maximum number of men and women suffering from cataract with 790 population using weka tool. In this paper the data classification is cataract patients data set is developed by collecting data from hospital repository consists of 790 instances with 11 different attributes. The instances in the Dataset are pertaining to the categories of Kerato meter reading (RE), Kerato meter reading (LE), Axil Length(RE), Axil Length(LE), Power(RE), Power(LE), Cataract Disease . WEKA tool is used to classify the data and the data is evaluated using 10-fold cross validation and the results are compared.
[1] D. R. Iskander, M. J. Collins, and B. Davis, “Optimal modeling of corneal surfaces with zernike polynomials,” IEEE Trans Biomed Eng, vol. 48, no. 1, pp. 87–95., 2001.

[2] D. R. Iskander, M. J. Collins, B. Davis, and R. Franklin, “Corneal surface characterization: How many zernike terms should be used? (arvo abstract),” Invest Ophthalmol Vis Sci, vol. 42, no. 4, p. S896, 2001.

[3] M. D. Twa, S. Parthasarathy, T. W. Raasch, and M. A. Bullimore, “Automated classification of keratoconus: A case study in analyzing clinical data,” in SIAM Int’l Conference on Data Mining, San Francisco, CA, 2003.

[4] Forbes “The deficit in cataract surgery in England and Wales and the escalating problem of visual impairment”: epidemiological modelling of the population dynamics of cataract. Br J Ophthalmol 2000; 84: 4-8.

[5] Ruth W. Age-related utilisation of cataract surgery in Sweden during 1992-1999. A retrospective study of cataract surgery rate in one-year age groups based on the Swedish National Cataract Register. Acta Ophthalmol Scand 2001; 79: 342-349.

[6] Harris WF. Direct, vec and other squares, and sample variance-covariance of dioptric power.Harris WF:Astigmatism. Ophthal Physiol Opt. 2000;20:11–30.

[11] N. Maeda, S. D. Klyce, M. K. Smolek, and H. W. Thompson, “Automated keratoconus screening with corneal topography analysis,” Invest Ophthalmol Vis Sci, vol. 35, no. 6, pp. 2749–57, 1994.

[7] Y. S. Rabinowitz and K. Rasheed, “KISA% - minimal topographic criteria for diagnosing keratoconus,” J Cataract Refract Surg, vol. 25, no. 10, pp. 1327–35, 1999.

[8] M. K. Smolek and S. D. Klyce, “Screening of prior refractive surgery by a wavelet-based neural network,” J Cataract Refract Surg, vol. 27, no. 12, pp. 1926–31., 2001.

[9] N. Maeda, S. D. Klyce, and M. K. Smolek, “Neural network classification of corneal topography. preliminary demonstration,” Invest Ophthalmol Vis Sci, vol. 36, no. 7, pp. 1327–35., 1995.

[10] K. Marsolo and S. Parthasarathy, “Alternate representation of distance matrices for characterization of protein structure,” in 5th IEEE International Conference on Data Mining (ICDM05), 2005.

Untitled Page