Early Detection of Diabetic Retinopathy Using Ensemble Learning Approach

Mehrbakhsh Nilashi, Sarminah Samad, Elaheh Yadegaridehkordi, Azar Alizadeh, Elnaz Akbari, Othman Ibrahim


Diabetes has been one of the leading health problems in all over the world. Diabetic retinopathy is the most common retinal vascular disease. Supervised data mining techniques have been successful in detecting diabetic retinopathy through a set of datasets. However, the most methods developed by supervised methods do not support the ensemble learning of data. The aim of this paper is to take the advantages of ensemble learning and develop a new method for diabetic retinopathy using data mining techniques. We use Non-linear Iterative Partial Least Squares for data dimensionality reduction, Self-Organizing Map for clustering task and ANFIS ensemble to classify unlabeled retinal images with high accuracy. We test our method on a publicly available Messidor dataset and present our results in comparison with the latest results of previous studies. For classification task, features of retinal images used for experimental analysis have been extracted by two algorithms, anatomical part recognition and lesion detection. The experimental analysis showed that the proposed method is robust in classifying the retinal images with Accuracy= 0.915, Sensitivity=0.946 and Specificity=0.917. The results of experimental analysis also demonstrated that our method performance is superior to Neural Network (NN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Decision Trees (DT), K-Nearest Neighbor (KNN) and Support Vector Machine (SVM). The hybrid intelligent system has potential to assist medical practitioners in the healthcare practice for early detection of diabetic retinopathy.


Healthcare, Early detection, Diabetic Retinopathy, NIPALS, SOM, Ensemble Learning

Full Text:

Abstract PDF


Abràmoff, M. D., Niemeijer, M., Suttorp-Schulten, M. S., Viergever, M. A., Russell, S. R., & Van Ginneken, B. (2008). Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes. Diabetes care, 31(2), 193-198.

Ahani, A., Nilashi, M., Ibrahim, O., Sanzogni, L., & Weaven, S. (2019). Market segmentation and travel choice prediction in Spa hotels through TripAdvisor’s online reviews. International Journal of Hospitality Management, 80, 52-77.

Amin, J., Sharif, M., Yasmin, M., Ali, H., & Fernandes, S. L. (2017). A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions. Journal of Computational Science.

Court, S., Sein, E., McCowen, C., Hackett, A. F., & Parkin, J. M. (1988). Children with diabetes mellitus: perception of their behavioural problems by parents and teachers. Early human development, 16(2-3), 245-252.

Egede, L. E., & Miohel, Y. (2001). Perceived difficulty of diabetes treatment in primary care: does it differ by patient ethnicity?. The Diabetes Educator, 27(5), 678-684.

Frandsen, C. S., Dejgaard, T. F., & Madsbad, S. (2016). Non-insulin drugs to treat hyperglycaemia in type 1 diabetes mellitus. The Lancet Diabetes & Endocrinology, 4(9), 766-780.

Gulbinat, W. (1997). What is the role of WHO as an intergovernmental organisation In: The coordination of telematics in healthcare. World Health Organisation. Geneva, Switzerland at http://www. hon. ch/libraray/papers/gulbinat. html.

Hamburg, B. A., & Inoff, G. E. (1982). Relationships between behavioral factors and diabetic control in children and adolescents: a camp study. Psychosomatic Medicine, 44(4), 321-339.

Han, J., & Kamber, M. (2001). Data mining: concepts and techniques. Morgan Kaufmann, San Francisco, Calif, USA, 2nd edition, 2011.

Hansen, L. K., & Salamon, P. (1990). Neural network ensembles. IEEE transactions on pattern analysis and machine intelligence, 12(10), 993-1001.

Huang, G., Song, S., Gupta, J. N., & Wu, C. (2014). Semi-supervised and unsupervised extreme learning machines. IEEE Transactions on Cybernetics, 44(12), 2405-2417.

Jang, J-SR. "ANFIS: adaptive-network-based fuzzy inference system." IEEE transactions on systems, man, and cybernetics 23.3 (1993): 665-685.

Knowler, W. C., Pettitt, D. J., Bennett, P. H., & Williams, R. C. (1983). Diabetes mellitus in the Pima Indians: genetic and evolutionary considerations. American Journal of Physical Anthropology, 62(1), 107-114.

Kohonen, T., Oja, E., Simula, O., Visa, A., & Kangas, J. (1996). Engineering applications of the self-organizing map. Proceedings of the IEEE, 84(10), 1358-1384.

Kononenko, I. (2001). Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in medicine, 23(1), 89-109.

Kramer, C. K., Zinman, B., & Retnakaran, R. (2013). Short-term intensive insulin therapy in type 2 diabetes mellitus: a systematic review and meta-analysis. The lancet Diabetes & endocrinology, 1(1), 28-34.

Kuncheva, L. I. (2004). Combining pattern classifiers: methods and algorithms. John Wiley & Sons.

Mardani, A., Streimikiene, D., Nilashi, M., Arias Aranda, D., Loganathan, N., & Jusoh, A. (2018). Energy Consumption, Economic Growth, and CO2 Emissions in G20 Countries: Application of Adaptive Neuro-Fuzzy Inference System. Energies, 11(10), 2771.

Newman, D. J., Hettich, S., Blake, C. L., & Merz, C. J. (1998). {UCI} Repository of machine learning databases.

Nilashi, M., Ahani, A., Esfahani, M. D., Yadegaridehkordi, E., Samad, S., Ibrahim, O., . . . Akbari, E. (2019). Preference learning for eco-friendly hotels recommendation: A multi-criteria collaborative filtering approach. Journal of Cleaner Production, 215, 767-783.

Nilashi, M., Ahmadi, H., Shahmoradi, L., Ibrahim, O., & Akbari, E. (2019). A predictive method for hepatitis disease diagnosis using ensembles of neuro-fuzzy technique. Journal of infection and public health, 12(1), 13-20.

Nilashi, M., Ahmadi, H., Shahmoradi, L., Mardani, A., Ibrahim, O., & Yadegaridehkordi, E. (2017). Knowledge Discovery and Diseases Prediction: A Comparative Study of Machine Learning Techniques. Journal of Soft Computing and Decision Support Systems, 4(5), 8-16.

Nilashi, M., Ahmadi, H., Shahmoradi, L., Salahshour, M., & Ibrahim, O. (2017). A soft computing method for mesothelioma disease classification. Journal of Soft Computing and Decision Support Systems, 4(1), 16-18.

Nilashi, M., Bagherifard, K., Rahmani, M., & Rafe, V. (2017). A recommender system for tourism industry using cluster ensemble and prediction machine learning techniques. Computers & Industrial Engineering, 109, 357-368.

Nilashi, M., bin Ibrahim, O., & Ithnin, N. (2014). Multi-criteria collaborative filtering with high accuracy using higher order singular value decomposition and Neuro-Fuzzy system. Knowledge-Based Systems, 60, 82-101.

Nilashi, M., bin Ibrahim, O., Ahmadi, H., & Shahmoradi, L. (2017). An analytical method for diseases prediction using machine learning techniques. Computers & Chemical Engineering, 106, 212-223.

Nilashi, M., Cavallaro, F., Mardani, A., Zavadskas, E., Samad, S., & Ibrahim, O. (2018). Measuring Country Sustainability Performance Using Ensembles of Neuro-Fuzzy Technique. Sustainability, 10(8), 2707.

Nilashi, M., Ibrahim, O., & Ahani, A. (2016). Accuracy Improvement for Predicting Parkinson’s Disease Progression. Scientific Reports, 6.

Nilashi, M., Ibrahim, O., Ahmadi, H., Shahmoradi, L., & Farahmand, M. (2018). A hybrid intelligent system for the prediction of Parkinson's Disease progression using machine learning techniques. Biocybernetics and Biomedical Engineering, 38(1), 1-15.

Nilashi, M., Ibrahim, O., Dalvi, M., Ahmadi, H., & Shahmoradi, L. (2017). Accuracy improvement for diabetes disease classification: a case on a public medical dataset. Fuzzy Information and Engineering, 9(3), 345-357.

Nilashi, M., Ibrahim, O., Samad, S., Ahmadi, H., Shahmoradi, L., & Akbari, E. (2019). An Analytical Method for Measuring the Parkinson’s Disease Progression: A Case on a Parkinson’s Telemonitoring Dataset. Measurement.

Nilashi, M., Ibrahim, O., Yadegaridehkordi, E., Samad, S., Akbari, E., & Alizadeh, A. (2018). Travelers decision making using online review in social network sites: A case on TripAdvisor. Journal of computational science, 28, 168-179.

Nilashi, M., Roudbaraki, M. Z., & Farahmand, M. (2017). A Predictive Method for Mesothelioma Disease Classification Using Naïve Bayes Classifier. Journal of Soft Computing and Decision Support Systems, 4(6), 7-14.

Oja, E. (1997). The nonlinear PCA learning rule in independent component analysis. Neurocomputing, 17(1), 25-45.

Pelleg, D., & Moore, A. W. (2000, June). X-means: Extending K-means with Efficient Estimation of the Number of Clusters. In ICML (pp. 727-734).

Spaide, R. F., & Fisher, Y. L. (2006). Intravitreal bevacizumab (Avastin) treatment of proliferative diabetic retinopathy complicated by vitreous hemorrhage. Retina, 26(3), 275-278.

Ulas, M., Orhan, C., Tuzcu, M., Ozercan, I. H., Sahin, N., Gencoglu, H., ... & Sahin, K. (2015). Anti-diabetic potential of chromium histidinate in diabetic retinopathy rats. BMC complementary and alternative medicine, 15(1), 16.

Vesanto, J., & Alhoniemi, E. (2000). Clustering of the self-organizing map. IEEE Transactions on neural networks, 11(3), 586-600.

Wang, L. L., Sun, Y., Huang, K., & Zheng, L. (2013). Curcumin, a potential therapeutic candidate for retinal diseases. Molecular nutrition & food research, 57(9), 1557-1568.

Yadegaridehkordi, E., Hourmand, M., Nilashi, M., Shuib, L., Ahani, A., & Ibrahim, O. (2018). Influence of big data adoption on manufacturing companies' performance: An integrated DEMATEL-ANFIS approach. Technological Forecasting and Social Change, 137, 199-210.

Zadeh, L. A. (1965). Fuzzy sets. Information and control, 8(3), 338-353.

Zhang, L., Krzentowski, G., Albert, A., & Lefebvre, P. J. (2001). Risk of developing retinopathy in Diabetes Control and Complications Trial type 1 diabetic patients with good or poor metabolic control. Diabetes care, 24(7), 1275-1279.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.