Diabetic Retinopathy Classification Using a Hybrid Deep Learning and Machine Learning Model

Barzegari, Motahareh; Zare Mehrjardi, Fatemeh; Sardari Zarchi, Mohsen

doi:10.18502/ijdo.v18i2.21647

Volume 18, Issue 2 (6-2026) IJDO 2026, 18(2): 98-112 | Back to browse issues page

‎ 10.18502/ijdo.v18i2.21647

Mendeley

Zotero

RefWorks

Barzegari M, Zare Mehrjardi F, Sardari Zarchi M. Diabetic Retinopathy Classification Using a Hybrid Deep Learning and Machine Learning Model. IJDO 2026; 18 (2) :98-112
URL: http://ijdo.ssu.ac.ir/article-1-1037-en.html

Diabetic Retinopathy Classification Using a Hybrid Deep Learning and Machine Learning Model

Motahareh Barzegari

, Fatemeh Zare Mehrjardi

, Mohsen Sardari Zarchi ^*

Associate Professor, Faculty of Engineering, Department of Computer Engineering, Meybod University, Meybod, Iran.

Abstract: (214 Views)

Objective: Among diabetic patients, diabetic retinopathy (DR) remains one of the most common causes of preventable blindness and vision loss, making its early detection crucial for preventing irreversible complications. Manual evaluation of fundus photographs is a lengthy process. Additionally, it requires specialized training that is not always available in all clinical settings. Consequently, artificial intelligence‑based automated retinal image analysis systems have emerged as complementary tools to enhance diagnostic accuracy and efficiency. This study proposes an ensemble learning‑based framework to improve the accuracy and robustness of automated DR detection. In the first stage, pretrained convolutional neural network (CNN) models extract high‑level features from fundus images, capturing complex patterns and DR‑related lesions. These features are then fed into several classical machine‑learning classifiers, including Support Vector Machine (SVM), Random Forest, and XGBoost. To further boost discriminative power and reduce classification errors, a stacking ensemble strategy integrates the predictions of the individual classifiers within a meta‑learning framework, enabling the model to learn the optimal combination for DR detection and grading. This hybrid approach effectively combines the strengths of deep learning and classical machine learning, yielding improved performance in DR detection and classification. Experimental results show that the stacking ensemble achieves higher accuracy and F1‑score compared to individual models, underscoring its potential as an auxiliary tool for early diabetic retinopathy detection.

Keywords: Diabetic retinopathy, Ensemble learning, Deep learning, Machine learning

Full-Text [PDF 997 kb] (83 Downloads)

Type of Study: Research | Subject: Special
Received: 2026/01/5 | Accepted: 2026/05/20 | Published: 2026/06/1

References

1. Lee R, Wong TY, Sabanayagam C. Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss. Eye and vision. 2015;2(1):17. [DOI:10.1186/s40662-015-0026-2]

2. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Journal of the American Medical Association. 2016;316(22):2402-10. [DOI:10.1001/jama.2016.17216]

3. Wang Z, Keane PA, Chiang M, Cheung CY, Wong TY, Ting DS. Artificial intelligence and deep learning in ophthalmology. Artificial intelligence in medicine. 2022:1519-52. [DOI:10.1007/978-3-030-64573-1_200]

4. Karsaz A, Mohammadian Roshan S. Deep Convolutional Neural Networks for Diabetic Retinopathy Screening. Advanced Signal Processing. 2020;4(2):225-37.

5. Odeh I, Alkasassbeh M, Alauthman M. Diabetic retinopathy detection using ensemble machine learning. In2021 international conference on information technology (ICIT) 2021:173-178. [DOI:10.1109/ICIT52682.2021.9491645]

6. Bakasa W, Viriri S. Stacked ensemble deep learning for pancreas cancer classification using extreme gradient boosting. Frontiers in Artificial Intelligence. 2023;6:1232640. [DOI:10.3389/frai.2023.1232640]

7. Revathy R, Nithya BS, Reshma JJ, Ragendhu SS, Sumithra MD. Diabetic retinopathy detection using machine learning. International Journal of Engineering. Reearch and Technology. 2020;9(6):122-6. [DOI:10.17577/IJERTV9IS060170]

8. I. Y. Abushawish, E. Abdel-Raheem, S. Modak, S. A. Mahmoud, and A. J. Hussain, "Deep learning in automatic diabetic retinopathy detection and grading systems: A comprehensive survey and comparison of methods," IEEE Access. 2024;12:12345-12367.doi: 10.1109/ACCESS.2024.3415617. [DOI:10.1109/ACCESS.2024.3415617]

9. Bidwai P, Gite S, Pahuja N, Pahuja K, Kotecha K, Jain N, et al. Multimodal image fusion for the detection of diabetic retinopathy using optimized explainable AI-based Light GBM classifier. Information Fusion. 2024;111:102526. [DOI:10.1016/j.inffus.2024.102526]

10. Ren Y, Shao D, Yi S. DR-MAE: Self-supervised learning for diabetic retinopathy grading based on masked autoencoder. Journal of King Saud University Computer and Information Sciences. 2025;37(8):217. [DOI:10.1007/s44443-025-00159-3]

11. Bhoopalan R, Sekar P, Nagaprasad N, Mamo TR, Krishnaraj R. Task optimized vision transformer for diabetic retinopathy detection and classification in resource constrained early diagnosis settings. Scientific Reports. 2025;15(1):39047. [DOI:10.1038/s41598-025-25399-1]

12. Rezaee K, Farnami F. Innovative approach for diabetic retinopathy severity classification: An ai-powered tool using CNN-transformer fusion. Journal of Biomedical Physics & Engineering. 2025;15(2):137. [DOI:10.31661/jbpe.v0i0.2408-1811]

13. Ahmadabadi JZ, Mehrjardi FZ, Ghanbary M, Mirzaei M. Identification of Effective Factors and Prediction of Ischemic Heart Disease Using Machine Learning Methods and Data from the Yazd Health Study (YaHS). Journal of Shahid Sadoughi University of Medical Sciences. 2024, 32(7):8067-8079.(in Persian) [DOI:10.18502/ssu.v32i7.16571]

14. Akbari Podineh M, Zare Mehrjardi F, Sardari Zarchi M. Multimodal analysis of ECG signals for cardiac arrhythmia detection using machine learning and deep learning methods. Applied and basic Machine intelligence research. 2025:17-34.

15. Zare Mehrjardi F, Yazdian-Dehkordi M, Latif A. Evaluating classical machine learning and deep-learning methods in sentiment analysis of Persian telegram message. Soft Computing Journal. 2022;11(1):88-105