PREDICTION OF DIABETIC RETINOPATHY AMONG TYPE II DIABETIC PATIENTS USING DATA MINING TECHNIQUES
DOI:
https://doi.org/10.24191/mjoc.v5i2.10554Keywords:
Data Mining, Diabetic Retinopathy, Predictive Modelling, Type II Diabetes MellitusAbstract
Diabetic retinopathy is one of the leading causes of visual disability and blindness worldwide. It is estimated that 4.8% out of 37 million cases of blindness were due to diabetic retinopathy, globally. It affects patients suffering from prolonged diabetes, which probably results in permanent blindness. The earliest symptoms surfaced when the patients have vision problems. Therefore, regular eyes examination and early intervention normally controls this disease. Many studies for early intervention and prevention of diabetic retinopathy uses various predictive models. The booming of database and digital storage technology creates an abundance of health records. Thus, data mining techniques helps uncover meaningful patterns while attending to sensitivity health record issues. Hence, this study took the data mining approach in predicting the presence of diabetic retinopathy narrowing to only Type II diabetic patients as well as to determine the risk factors that contribute to the presence of diabetic retinopathy. The data mining models selected for this study is the Logistic Regression, Decision Tree and Artificial Neural Network. The dataset of 361 Type II diabetic patients from Ophthalmology Clinic, UiTM Medical Specialist Centre were selected between January 2014 to December 2018, consists of 17 variables. The result shows that the Logistic Regression using Forward selection method model is the best model since it had the highest sensitivity (Sen=50.0%), specificity (Spe=79.03%) and accuracy rate (Acc=66.36%) on the validation dataset compared to other Logistic Regression selection options. Meanwhile among the Decision Tree models, DT using Gini is the best model. Logistic Regression (Forward) and Decision Tree (Gini) were then compared with Artificial Neural Network model (Sen=56.25%, Spe=70.97%, Acc=64.55%). The results demonstrated that Logistic Regression using Forward selection method was the best model to predict the presence of diabetic retinopathy among the Type II diabetic patients compared to other models. The significant risk factors associated with the presence of the diabetic retinopathy obtained are duration of diabetes, HbA1C level, diabetic foot ulcer, nephropathy, and neuropathy.
References
Abougalambou, S. S. I., & Abougalambou, A. S. (2015). Risk Factors Associated With Diabetic Retinopathy among Type 2 Diabetes Patients at Teaching Hospital in Malaysia. Diabetes and Metabolic Syndrome: Clinical Research and Reviews, 9(2), 98–103. https://doi.org/10.1016/j.dsx.2014.04.019.
American Academy of Ophthalmology. (2016). AAO Guidelines for Diabetic Retinopathy. https://doi.org/10.1016/S0140-6736(09)62124-3.
Ananthapadmanabhan, K. R., & Parthiban, G. (2014). Prediction of Chances-Diabetic Retinopathy Using Data Mining Classification Techniques. Indian Journal of Science and Technology, 7(10), 1498–1503. https://doi.org/10.17485/IJST/2014/V7I10/51098
Balaji, S. A., & Baskaran, K. (2013). Design and Development of Artificial Neural Networking (ANN) System Using Sigmoid Activation Function to Predict Annual Rice Production in Tamilnadu. International Journal of Computer Science, Engineering and Information Technology (IJCSEIT), 3(1), 13–31. https://doi.org/10.5121/ijcseit.2013.3102.
Cardoso, C. R. L., Leite, N. C., Dib, E., & Salles, G. F. (2017). Predictors of Development and Progression of Retinopathy in Patients with Type 2 Diabetes : Importance of Blood Pressure Parameters. Scientific Reports, 7(4867), 1–10. https://doi.org/10.1038/s41598-017-05159-6.
Casanova, R., Saldana, S., Chew, E. Y., Danis, R. P., Greven, C. M., & Ambrosius, W. T. (2014). Application of Random Forests Methods to Diabetic Retinopathy Classification Analyses. PLoS ONE, 9(6), 1–8. https://doi.org/10.1371/journal.pone.0098587.
Clinical Practice Guidelines. (2011). Screening of Diabetic Retinopathy. Ministry of Health Malaysia. https://doi.org/10.1002/pdi.299.
Diallo, A. M., Novella, J. L., Lukas, C., Souchon, P. F., Dramé, M., François, M., … Delemer, B. (2018). Early predictors of diabetic retinopathy in type 1 diabetes: The Retinopathy Champagne Ardenne Diabète (ReCAD) study. Journal of Diabetes and Its Complications, 32(8), 753–758. https://doi.org/10.1016/j.jdiacomp.2018.05.011.
Gadekallu, T.R.; Khare, N.; Bhattacharya, S.; Singh, S.; Maddikunta, P.K.R.; Ra, I.-H.; Alazab, M.(2020. Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model. Electronics. 2020; 9(2):274.
Haque, M., Rahman, A., Hagare, D., & Chowdhury, R. K. (2018). A Comparative Assessment of Variable Selection Methods in Urban Water Demand Forecasting. Water, 10(419), 1–15. https://doi.org/10.3390/w10040419.
Harb, W., Harb, G., Chamoun, N., Kanbar, A., Harb, M., & Chanbour, W. (2018). Severity of diabetic retinopathy at the first ophthalmological examination in the Lebanese population. Therapeutic Advances in Ophthalmology, 10, 2515841418791950. https://doi.org/10.1177/2515841418791950.
Hosmer, D. W., & Lemeshow, S. (2000). Applied Logistic Regression (Second Edi). Canada: John Wiley & Sons, Inc. Retrieved from http://resource.heartonline.cn/20150528/1_3kOQSTg.pdf.
Karadeniz, Z. S., & Yilmaz, M. T. (2007). Duration of diabetes and prevalence of diabetic retinopathy : Istanbul Diabetic Retinopathy Study – IDRS results 1. Diabetes & Metabolic Syndrome: Clinical Research & Reviews, 1, 43–48. https://doi.org/10.1016/j.dsx.2006.11.008
Kim, K., Kim, E. S., & Yu, S. (2018). Longitudinal relationship between retinal diabetic neurodegeneration and progression of diabetic retinopathy in patients with type 2 diabetes. American Journal of Ophthalmology. https://doi.org/10.1016/j.ajo.2018.08.053.
Lee, J. (2013). Macrovascular and Microvascular Complications of Diabetes Mellitus. Drug Topics, 44–53. https://doi.org/10.5005/jp/books/10202.
Lek, S., & Gue, J. F. (1999). Artificial neural networks as a tool in ecological modelling , an introduction. Ecological Modelling, 120(2–3), 65–73. https://doi.org/10.1016/S0304-3800(99)00092-7.
Letchuman, G. R., Nazaimoon, W. M. W., Mohamad, W. B. W., Chandran, L. R., Tee, G. H., Jamaiyah, H., … Faudzi, Y. A. (2010). Prevalence of Diabetes in the Malaysian National Health Morbidity Survey III 2006 The Malaysian National Health Morbidity Survey III ( NHMS. Medical Journal of Malaysia, 65(3), 173–179. Retrieved from http://www.e-mjm.org/2010/v65n3/Diabetes.pdf.
Mahendran, G., & Dhanasekaran, R. (2015). Investigation of the severity level of diabetic retinopathy using supervised classifier algorithms. Computers and Electrical Engineering, 45, 312–323. https://doi.org/10.1016/j.compeleceng.2015.01.013.
Mallika, P., Lee, P., Cheah, W., Wong, J., Syed Alwi, S., Nor Hayati, H., & Tan, A. (2011). Risk Factors For Diabetic Retinopathy In Diabetics Screened Using Fundus Photography At A Primary Health Care Setting In East Malaysia. Malaysian Family Physician : The Official Journal of the Academy of Family Physicians of Malaysia, 6(2–3), 60–65. Retrieved from http://www.ncbi.nlm.nih.gov/pubmed/25606225%5Cnhttp://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4170425.
Maria, Z., Corrêa, S., & Freitas, A. M. (2003). Risk factors related to the severity of diabetic retinopathy. Arq Bras Oftalmol, 66(5), 739–743. https://doi.org/10.1590/S0004-27492003000700002.
Masconi, K. L., Matsha, T. E., Echouffo-tcheugui, J. B., Erasmus, R. T., & Kengne, A. P. (2015). Reporting and handling of missing data in predictive research for prevalent undiagnosed type 2 diabetes mellitus : a systematic review. The EPMA Journal, 6(7), 1–11. https://doi.org/10.1186/s13167-015-0028-0.
Matignon, R. (2007). Data Mining Using SAS® Enterprise Miner TM. South San Francisco, CA: A John Wiley & Sons, Inc. Retrieved from https://doc.lagout.org/Others/Data Mining/Data Mining using SAS Enterprise Miner %5BMatignon 2007-08-03%5D.pdf.
Mohd Ali, M. H., Draman, N., Mohamed, W. M. I. W., Yaakub, A., & Embong, Z. (2016). Predictors of proliferative diabetic retinopathy among patients with type 2 diabetes mellitus in Malaysia as detected by fundus photography. Journal of Taibah University Medical Sciences, 11(4), 353–358. https://doi.org/10.1016/j.jtumed.2016.03.002
Naveen Kumar, T., Nagi Reddy, T., & Radha Kishan, T. (2014). Diabetic eye screening in multi ethnic population of Malaysia : epidemiological risk factors for development of diabetic retinopathy. International Journal of Research in Medical Sciences, 2(3), 1045–1049. https://doi.org/10.5455/2320-6012.ijrms201408069.
Park, H.-A. (2013). An Introduction to Logistic Regression : From Basic Concepts to Interpretation with Particular Attention to Nursing Domain. Korean Society of Nursing Science, 43(2), 154–164. http://dx.doi.org/10.4040/jkan.2013.43.2.154.
Reddy, G. T., Bhattacharya, S., Ramakrishnan, S. S., Chowdhary, C., Hakak, S., Kaluri, R., et al. (2020). An ensemble based machine learning model for diabetic retinopathy classification. International Conference on Emerging Trends on Information Technology and Engineering,2020, 1–6.
SAS Institute Inc. (2010). Applied Analytics Using SAS® Enterprise MinerTM. Retrieved from https://is.muni.cz/el/1431/podzim2012/M9DM2/um/LWAAEM61_002_2010.pdf.
Senthilvel, V., & Radhakrishnan, R Sathiyamoorthi, R. (2012). Prediction of Diabetic Rretinopathy Among Diabetics using Binary Logistic Regression Approach. Indian Journal of Medical Specialities, 3(1), 18–20. https://doi.org/10.7713/ijms.2012.0005.
Shriwas, S. R., Isa, A. B., Reddy, S. C., & Mohammad, M. (1996). Risk Factors for Retinopathy in Diabetes Mellitus in Kelantan Malaysia. Med J Malaysia, 51(4), 447–452. Retrieved from https://e-mjm.org/1996/v51n4/Diabetes_Mellitus.pdf.
Tsao, H., Chan, P., & Su, E. C. (2018). Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms. BMC Bioinformatics, 19(283), 195–205. https://doi.org/https://doi.org/10.1186/s12859-018-2277-0.
Witten, I. H., & Frank, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques. (J. Gray, Ed.) (Second Edi). Morgan Kaufmann Publishers. Retrieved from ftp://ftp.ingv.it/pub/manuela.sbarra/Data Mining Practical Machine Learning Tools and Techniques - WEKA.pdf.
Wu, X., Kumar, V., Quinlan, J. R., Ghosh, J., Yang, Q., Motoda, H., … Dan, J. H. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, 14(1), 1–37. https://doi.org/10.1007/s10115-007-0114-2.
Zhang, J., Wang, Y., Li, L., Zhang, R., Guo, R., & Li, H. (2018). Diabetic retinopathy may predict the renal outcomes of patients with diabetic nephropathy, 6049. https://doi.org/10.1080/0886022X.2018.1456453.
Published
Issue
Section
License
Copyright (c) 2020 Zuraida Khairudin, Nurfatin Adila Abdul Razak, Hezlin Aryani Abd Rahman, Norbaizura Kamarudin, Nor Azimah Binti Abd Aziz
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
