Non-Invasive Diagnosis of Type II Diabetes Using Iris-Based Machine Learning Models
Non-Invasive Diagnosis of Type II Diabetes Using Iris-Based Machine Learning Models |
||
![]() |
![]() |
|
© 2025 by IJETT Journal | ||
Volume-73 Issue-5 |
||
Year of Publication : 2025 | ||
Author : Alaa Abdulkareem Ahmed, Mohammad Tariq Yaseen |
||
DOI : 10.14445/22315381/IJETT-V73I5P117 |
How to Cite?
Alaa Abdulkareem Ahmed, Mohammad Tariq Yaseen, "Non-Invasive Diagnosis of Type II Diabetes Using Iris-Based Machine Learning Models," International Journal of Engineering Trends and Technology, vol. 73, no. 5, pp.186-198, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I5P117
Abstract
The increasing occurrence of Type II Diabetes Mellitus (T2DM) due to lifestyle changes has required the development of non-invasive diagnostic methods. This study explores the potential of iridology, another diagnostic approach, joined with machine learning (ML) algorithms to detect T2DM based on a precise Region of Interest (ROI) in the right iris. This work introduces two ML-based classification methods. The first method employs multiple ML models with changing K-fold cross-validation (ranging from 2 to 20 folds), achieving a maximum classification accuracy of 78.5% at 5-fold using Support Vector Machine (SVM) and Binary Generalized Linear Model (GLM) Logistic Regression. The second method employs Principal Component Analysis (PCA) to enhance feature selection, improving accuracy to 82.2% by training predictions from two initial classifiers-Coarse Decision Tree (74.8% at 14-fold, PCA variance 97%) and Linear Discriminant Analysis (77.6% at 9-fold, PCA variance 100%)-before refining classification with a Binary GLM Logistic Regression model. The proposed approach offers a promising, non-invasive alternative for early diabetes detection using iris analysis and Artificial Intelligence (AI).
Keywords
Artificial intelligence, Diabetes detection, Iris-based diagnosis, Machine Learning, Non-Invasive.
References
[1] Jai Kumar et al., “A Comparative Analysis of Clinical Features of Diabetes Mellitus Type 2 With Respect to Duration of Diabetes,” Cureus, vol. 16, no. 11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Wantang Li, “Risk Factors and the Treatment of Type 2 Diabetes (T2D),” Proceedings of the 3rd International Conference on Modern Medicine and Global Health, vol. 68, no. 1, pp. 115-120, 2025.
[CrossRef] [Publisher Link]
[3] Dyla Velia, and Adhi Harmoko Saputro, “Retracted: Designing Diabetes Mellitus Detection System Based on Iridology with Convolutional Neural Network Modeling,” 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), Semarang, Indonesia, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Marcello Gallerani et al., “Integrated Design and Prototyping of a Robotic Eye System for Ocular and Craniofacial Trauma Simulators,” International Journal on Interactive Design and Manufacturing (IJIDeM), vol. 17, no. 6, pp. 3103-3116, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Piyush Samant, and Ravinder Agarwal, “Analysis of Computational Techniques for Diabetes Diagnosis using the Combination of Iris-Based Features and Physiological Parameters,” Neural Computing and Applications, vol. 31, no. 12, pp. 8441-8453, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Piyush Samant, and Ravinder Agarwal, “Machine Learning Techniques for Medical Diagnosis of Diabetes using Iris Images,” Computer Methods and Programs in Biomedicine, vol. 157, pp. 121-128, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Ratna Aminah, and Adhi Harmoko Saputro, “Retracted: Application of Machine Learning Techniques for Diagnosis of Diabetes Based on Iridology,” 2019 International Conference on Advanced Computer Science and Information Systems (ICACSIS), Bali, Indonesia, pp. 133-138, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zuraini Othman, and Anton Satria Prabuwono, “Retracted: Preliminary Study on Iris Recognition System: Tissues of Body Organs in Iridology,” 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES), Kuala Lumpur, Malaysia, pp. 115-119, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[9] K. Sivasankar et al., “Retracted: FCM Based Iris Image Analysis for Tissue Imbalance Stage Identification,” 2012 International Conference on Emerging Trends in Science, Engineering and Technology (INCOSET), Tiruchirappalli, India, pp. 210-215, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Sherif E. Hussein, Osama A. Hassan, and Malcolm H. Granat, “Assessment of the Potential Iridology for Diagnosing Kidney Disease Using Wavelet Analysis and Neural Networks,” Biomed Signal Process Control, vol. 8, no. 6, pp. 534-541, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Atul Bansal, Ravinder Agarwal, and R.K. Sharma, “Determining Diabetes Using Iris Recognition System,” International Journal of Diabetes in Developing Countries, vol. 35, no. 4, pp. 432-438, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jamal Firmat Banzi, and Zhaojun Xue, “An Automated Tool for Non-contact, Real Time Early Detection of Diabetes by Computer Vision,” International Journal of Machine Learning and Computing, vol. 5, no. 3, pp. 225-229, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Piyush Samant, and Ravinder Agarwal, “Diagnosis of Diabetes Using Computer Methods: Soft Computing Methods for Diabetes Detection Using Iris,” International Journal of Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering, vol. 11, no. 2, pp. 63-68, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Dyah Ceni Adelina et al., “Retracted: Identification of Diabetes in Pancreatic Organs using Iridology,” 2017 International Electronics Symposium on Knowledge Creation and Intelligent Computing (IES-KCIC), Surabaya, Indonesia, pp. 114-119, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Parsa Moradi et al., “Retracted: Discovering Informative Regions in Iris Images to Predict Diabetes,” 2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME), Qom, Iran, pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] The GitHub Website, 2018. [Online]. Available: https://github.com/NaghmeNazer/diabetes-iridology?tab=readme-ov-file
[17] Sandeep Panwar Jogi, and Bharat Bhushan Sharma, “Retracted: Methodology of Iris Image Analysis for Clinical Diagnosis,” 2014 International Conference on Medical Imaging, m-Health and Emerging Communication Systems (MedCom), Greater Noida, India, pp. 235-240, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[18] K. Entin Martiana, “Retracted: Application for Heart Abnormalities Detection through Iris,” 2016 International Electronics Symposium (IES), Denpasar, Indonesia, pp. 315-322, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] P.A. Reshma, and K.V. Divya, and T.B. Subair, “Detection of Heart Abnormalities and High-Level Cholesterol Through Iris,” Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB), Palladam, India, vol. 30, pp. 339-346, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[20] David Habsara Hareva, Samuel Lukas, and Natanael Oktavian Suharta, “Retracted: The Smart Device for Healthcare Service: Iris Diagnosis Application,” 2013 Eleventh International Conference on ICT and Knowledge Engineering, Bangkok, Thailand, pp. 1-6, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sare Amerifar, Alireza Tavakoli Targhi, and Mohammad Mahdi Dehshibi, “Retracted: Iris the Picture of Health: Towards Medical Diagnosis of Diseases Based on Iris Pattern,” 2015 Tenth International Conference on Digital Information Management (ICDIM), Jeju, Korea (South), pp. 120-123, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[22] R.A. Ramlee, and S. Ranjit, “Retracted: Using Iris Recognition Algorithm, Detecting Cholesterol Presence,” 2009 International Conference on Information Management and Engineering, Kuala Lumpur, Malaysia, pp. 714-717, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[23] L.B. Rachman, and Basari, “Detection of Cholesterol Levels by Analyzing Iris Patterns using Backpropagation Neural Network,” The 2nd Tarumanagara International Conference on the Applications of Technology and Engineering (TICATE), Jakarta, Indonesia, vol. 852, no. 1, pp. 1-8, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Ferdi Özbilgin, Çetin Kurnaz, and Ertan Aydın, “Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis,” Diagnostics, vol. 13, no. 6, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Melvin Daniel, Jangkung Raharjo, and Koredianto Usman, “Iris-based Image Processing for Cholesterol Level Detection using Gray Level Co-Occurrence Matrix and Support Vector Machine,” Engineering Journal, vol. 24, no. 5, pp. 135-144, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Kumar Mohit, Rajeev Gupta, and Basant Kumar, “A Survey on the Machine Learning Techniques for Automated Diagnosis from Ultrasound Images,” Current Medical Imaging Formerly Current Medical Imaging Reviews, vol. 20, no. 1, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Isaac Kofi Nti, Owusu Nyarko-Boateng, and Justice Aning, “Performance of Machine Learning Algorithms with Different K Values in K-fold CrossValidation,” International Journal of Information Technology and Computer Science, vol. 13, no. 6, pp. 61-71, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Carlos Fernandez-Grandon, Ismael Soto, and David Zabala-Blanco, “Extreme Learning Machine for Iris-Based Diabetes Detection,” 2023 IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON), Valdivia, Chile, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] C. Yohannes, I. Nurtanio, and K.C. Halim, “Potential of Heart Disease Detection Based on Iridology,” The 3rd EPI International Conference on Science and Engineering 2019 (EICSE2019), South Sulawesi, Indonesia, vol. 875, no. 1, pp. 1-9, 2020.
[CrossRef] [Google Scholar] [Publisher Link]