Keywords
diagnostic task
ethical implication
hybrid models
interpretability
How to Cite
Abstract
Diabetes, if not detected early, can lead to serious complications such as vision loss, known as diabetic retinopathy. Explainable Artificial Intelligence (XAI) can enhance traditional Machine Learning methods, which are not understandable and transparent in diagnostic tasks. This Systematic Literature Review explores data inputs that influence the performance of XAI models in detecting diabetic retinopathy, how XAI techniques can enhance early detection outcomes in diabetic retinopathy, the challenges in implementing these techniques and the ethical implications of using these models in clinical practice. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses approach guided the search in 4 databases, Springer, Science Direct, PubMed and IEEE Xplore. The findings reveal that XAI techniques like Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (GRAD-CAM) offer opportunities like early detection outcomes, integration with existing clinical processes, enhancing trust in AI systems, improving accuracy and personalised treatment. XAI can also facilitate collaboration among clinicians, maintaining fairness in AI systems and supporting adherence to ethical standards. However, research on clinical validation of these models, as well as standardised performance evaluation metrics, is lacking.
References
R. Simó and C. Hernández, “What else can we do to prevent diabetic retinopathy?,” Diabetologia, vol. 66, no. 9, pp. 1614–1621, Sep. 2023, doi: 10.1007/s00125-023-05940-5.
Q. H. Yang, Y. Zhang, X. M. Zhang, and X. R. Li, “Prevalence of diabetic retinopathy, proliferative diabetic retinopathy and non-proliferative diabetic retinopathy in asian t2dm patients: A systematic review and metaanalysis,” Int J Ophthalmol, vol. 12, no. 2, pp. 302–311, Feb. 2019, doi: 10.18240/ijo.2019.02.19.
H. Y. Tsao, P. Y. Chan, and E. C. Y. Su, “Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms,” BMC Bioinformatics, vol. 19, Aug. 2018, doi: 10.1186/s12859-018-2277-0.
E. A. Alfonso-Muñoz, R. Burggraaf-Sánchez de las Matas, J. Mataix Boronat, J. C. Molina Martín, and C. Desco, “Role of oral antioxidant supplementation in the current management of diabetic retinopathy,” Int J Mol Sci, vol. 22, no. 8, Apr. 2021, doi: 10.3390/ijms22084020.
B. Mutunhu, B. Chipangura, and H. Twinomurinzi, “Internet of Things in the Monitoring of Diabetes,” International Journal of Health Systems and Translational Medicine, vol. 2, no. 1, pp. 1–20, 2022, doi: 10.4018/ijhstm.300336.
D. M. Mukona, P. Dzingira, M. Mhlanga, and M. Zvinavashe, “Uptake of Screening for Diabetic Retinopathy and Associated Factors among Adults with Diabetes Mellitus Aged 18-65 Years: A Descriptive Cross Sectional Study,” European Journal of Medical and Health Sciences, vol. 2, no. 4, Jul. 2020, doi: 10.24018/ejmed.2020.2.4.247.
I. Murere, B. Ndlovu, S. Dube, M. Muduva, and F. Jacqueline Kiwa, “Comparative Analysis of Machine Learning Techniques for Predicting Diabetes,” in Proceedings of the International Conference on Industrial Engineering and Operations Management, Michigan, USA: IEOM Society International, Jul. 2024. doi: 10.46254/EU07.20240073.
P. Uppamma and S. Bhattacharya, “A multidomain bio-inspired feature extraction and selection model for diabetic retinopathy severity classification: an ensemble learning approach,” Sci Rep, vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-45886-7.
L. Von Rueden et al., “Informed Machine Learning - A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems,” IEEE Trans Knowl Data Eng, vol. 35, no. 1, pp. 614–633, Jan. 2023, doi: 10.1109/TKDE.2021.3079836.
R. Dwivedi et al., “Explainable AI (XAI): Core Ideas, Techniques, and Solutions,” ACM Comput Surv, vol. 55, no. 9, Sep. 2023, doi: 10.1145/3561048.
A. B. Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI,” Oct. 2019, [Online]. Available: http://arxiv.org/abs/1910.10045
L. Longo, R. Goebel, F. Lecue, P. Kieseberg, A. Holzinger, and A. H. Explainable, “Explainable Artificial Intelligence: Concepts, Applications, Research Challenges and Visions,” pp. 1–16, 2020, doi: 10.1007/978-3-030-57321-8_1ï.
Z. Khan et al., “Diabetic Retinopathy Detection Using VGG-NIN a Deep Learning Architecture,” IEEE Access, vol. 9, pp. 61408–61416, 2021, doi: 10.1109/ACCESS.2021.3074422.
T. Shahzad, M. Saleem, M. S. Farooq, S. Abbas, M. A. Khan, and K. Ouahada, “Developing a Transparent Diagnosis Model for Diabetic Retinopathy Using Explainable AI,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3475550.
D. Bhulakshmi and D. S. Rajput, “A systematic review on diabetic retinopathy detection and classification based on deep learning techniques using fundus images,” PeerJ Comput Sci, vol. 10, 2024, doi: 10.7717/PEERJ-CS.1947.
K. Ahnaf Alavee et al., “Enhancing Early Detection of Diabetic Retinopathy Through the Integration of Deep Learning Models and Explainable Artificial Intelligence,” IEEE Access, vol. 12, pp. 73950–73969, 2024, doi: 10.1109/ACCESS.2024.3405570.
B. Ndlovu, K. Maguraushe, and O. Mabikwa, “Machine Learning and Explainable AI for Parkinson’s Disease Prediction: A Systematic Review,” The Indonesian Journal of Computer Science, vol. 14, no. 2, Apr. 2025, doi: 10.33022/ijcs.v14i2.4837.
G. Quellec, H. Al Hajj, M. Lamard, P. H. Conze, P. Massin, and B. Cochener, “ExplAIn: Explanatory artificial intelligence for diabetic retinopathy diagnosis,” Med Image Anal, vol. 72, Aug. 2021, doi: 10.1016/j.media.2021.102118.
A. Ikram and A. Imran, “ResViT FusionNet Model: An explainable AI-driven approach for automated grading of diabetic retinopathy in retinal images,” Comput Biol Med, vol. 186, Mar. 2025, doi: 10.1016/j.compbiomed.2025.109656.
Y. Zou, Y. Wang, X. Kong, T. Chen, J. Chen, and Y. Li, “Deep Learner System Based on Focal Color Retinal Fundus Images to Assist in Diagnosis,” Diagnostics, vol. 13, no. 18, Sep. 2023, doi: 10.3390/diagnostics13182985.
P. Bidwai et al., “Multimodal image fusion for the detection of diabetic retinopathy using optimized explainable AI-based Light GBM classifier,” Information Fusion, vol. 111, Nov. 2024, doi: 10.1016/j.inffus.2024.102526.
R. Raman et al., “Prevalence of Diabetic Retinopathy in India. Sankara Nethralaya Diabetic Retinopathy Epidemiology and Molecular Genetics Study Report 2,” Ophthalmology, vol. 116, no. 2, pp. 311–318, Feb. 2009, doi: 10.1016/j.ophtha.2008.09.010.
Z. Khan, F. Khan, A. Khan, Z. Rehman, … S. S.-I., and undefined 2021, “Diabetic retinopathy detection using VGG-NIN a deep learning architecture,” ieeexplore.ieee.org, Accessed: Nov. 12, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9409084/
I. A. Taifa, D. M. Setu, T. Islam, S. K. Dey, and T. Rahman, “A hybrid approach with customized machine learning classifiers and multiple feature extractors for enhancing diabetic retinopathy detection,” Healthcare Analytics, vol. 5, p. 100346, Jun. 2024, doi: 10.1016/J.HEALTH.2024.100346.
T. Shahzad, M. Saleem, M. Farooq, … S. A.-I., and undefined 2024, “Developing a Transparent Diagnosis Model for Diabetic Retinopathy Using Explainable AI,” ieeexplore.ieee.org, Accessed: Nov. 12, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10706847/
W. X. Lim, Z. Y. Chen, and A. Ahmed, “The adoption of deep learning interpretability techniques on diabetic retinopathy analysis: a review,” Med Biol Eng Comput, vol. 60, no. 3, pp. 633–642, Mar. 2022, doi: 10.1007/S11517-021-02487-8.
U. Parmar, P. Surico, R. Singh, F. Romano, C. S.- Medicina, and undefined 2024, “Artificial intelligence (AI) for early diagnosis of retinal diseases,” mdpi.com, Accessed: Nov. 11, 2024. [Online]. Available: https://www.mdpi.com/1648-9144/60/4/527
R. Romero-Oraá, M. Herrero-Tudela, M. I. López, R. Hornero, and M. García, “Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy grading,” Comput Methods Programs Biomed, vol. 249, Jun. 2024, doi: 10.1016/j.cmpb.2024.108160.
F. H. Yagin, C. Colak, A. Algarni, Y. Gormez, E. Guldogan, and L. P. Ardigò, “Hybrid Explainable Artificial Intelligence Models for Targeted Metabolomics Analysis of Diabetic Retinopathy,” Diagnostics, vol. 14, no. 13, Jul. 2024, doi: 10.3390/diagnostics14131364.
F. H. Yagin et al., “Explainable Artificial Intelligence Paves the Way in Precision Diagnostics and Biomarker Discovery for the Subclass of Diabetic Retinopathy in Type 2 Diabetics,” Metabolites, vol. 13, no. 12, Dec. 2023, doi: 10.3390/metabo13121204.
X. Wang, W. Wang, H. Ren, X. Li, and Y. Wen, “Prediction and analysis of risk factors for diabetic retinopathy based on machine learning and interpretable models,” Heliyon, vol. 10, no. 9, p. e29497, May 2024, doi: 10.1016/J.HELIYON.2024.E29497.
G. Quellec, H. Al Hajj, M. Lamard, P. H. Conze, P. Massin, and B. Cochener, “ExplAIn: Explanatory artificial intelligence for diabetic retinopathy diagnosis,” Med Image Anal, vol. 72, p. 102118, Aug. 2021, doi: 10.1016/J.MEDIA.2021.102118.
P. Bidwai, S. Gite, K. Pahuja, and K. Kotecha, “A Systematic Literature Review on Diabetic Retinopathy Using an Artificial Intelligence Approach,” Dec. 01, 2022, MDPI. doi: 10.3390/bdcc6040152.
G. Chondrozoumakis et al., “Retinal Biomarkers in Diabetic Retinopathy: From Early Detection to Personalized Treatment,” J Clin Med, vol. 14, no. 4, p. 1343, Feb. 2025, doi: 10.3390/jcm14041343.
K. Vinogradova, A. Dibrov, and G. Myers, “Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract).” [Online]. Available: www.aaai.org
J. Li et al., “Interpretable machine learning-derived nomogram model for early detection of diabetic retinopathy in type 2 diabetes mellitus: a widely targeted metabolomics study,” Nutr Diabetes, vol. 12, no. 1, Dec. 2022, doi: 10.1038/s41387-022-00216-0.
S. O’Sullivan et al., “Explainable artificial intelligence (XAI): closing the gap between image analysis and navigation in complex invasive diagnostic procedures,” May 01, 2022, Springer Science and Business Media Deutschland GmbH. doi: 10.1007/s00345-022-03930-7.
A. K. Smilde et al., “Dynamic metabolomic data analysis: A tutorial review,” Metabolomics, vol. 6, no. 1, pp. 3–17, Mar. 2010, doi: 10.1007/s11306-009-0191-1.
R. Younisse, A. Ahmad, and Q. Abu Al-Haija, “Explaining Intrusion Detection-Based Convolutional Neural Networks Using Shapley Additive Explanations (SHAP),” Big Data and Cognitive Computing, vol. 6, no. 4, Dec. 2022, doi: 10.3390/bdcc6040126.
M. Rehman Zafar and N. Khan, “machine learning & knowledge extraction Deterministic Local Interpretable Model-Agnostic Explanations for Stable Explainability,” 2021, doi: 10.3390/make.
R. O. Alabi, M. Elmusrati, I. Leivo, A. Almangush, and A. A. Mäkitie, “Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP,” Sci Rep, pp. 1–14, 2023, doi: 10.1038/s41598-023-35795-0.
Y. Nohara, K. Matsumoto, H. Soejima, and N. Nakashima, “Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital,” Dec. 2021, doi: 10.1016/j.cmpb.2021.106584.
W. E. Marcilio-jr, D. M. Eler, and P. Brazil, “From explanations to feature selection : assessing SHAP values as feature selection mechanism”.
A. E. Maxwell, M. Sharma, and K. A. Donaldson, “Explainable boosting machines for slope failure spatial predictive modeling,” Remote Sens (Basel), vol. 13, no. 24, Dec. 2021, doi: 10.3390/rs13244991.
E. Guldogan, F. H. Yagin, A. Pinar, C. Colak, S. Kadry, and J. Kim, “OPEN A proposed tree based explainable artificial intelligence approach for the prediction of angina pectoris,” Sci Rep, pp. 1–12, 2023, doi: 10.1038/s41598-023-49673-2.
J. C. Chien, J. Der Lee, C. S. Hu, and C. T. Wu, “The Usefulness of Gradient-Weighted CAM in Assisting Medical Diagnoses,” Applied Sciences (Switzerland), vol. 12, no. 15, Aug. 2022, doi: 10.3390/app12157748.
A. Chattopadhyay, A. Sarkar, and P. Howlader, “Grad-CAM ++ : Improved Visual Explanations for Deep Convolutional Networks”.
B. Mutunhu, B. Chipangura, and S. Singh, “An Exploration of Opportunities for Quantified-Self Technology in Diabetes Self-Care: A Systematic Literature Review,” J Health Inform Afr, vol. 11, no. 2, pp. 17–30, 2024, doi: 10.12856/JHIA-2024-v11-i2-481.
C. Fuyana, B. Ndlovu, S. Dube, K. Maguraushe, and L. Malungana, “Optimizing HIV Care Through Machine Learning-Assisted Prediction and Personalized Treatment,” 2025, pp. 149–161. doi: 10.1007/978-981-96-2124-8_11.
T. Shahzad, M. Saleem, M. S. Farooq, S. Abbas, M. A. Khan, and K. Ouahada, “Developing a Transparent Diagnosis Model for Diabetic Retinopathy Using Explainable AI,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3475550.
X. Wang, W. Wang, H. Ren, X. Li, and Y. Wen, “Prediction and analysis of risk factors for diabetic retinopathy based on machine learning and interpretable models,” Heliyon, vol. 10, no. 9, p. e29497, May 2024, doi: 10.1016/J.HELIYON.2024.E29497.
U. Parmar, P. Surico, R. Singh, F. Romano, C. S.- Medicina, and undefined 2024, “Artificial intelligence (AI) for early diagnosis of retinal diseases,” mdpi.com, Accessed: Nov. 11, 2024. [Online]. Available: https://www.mdpi.com/1648-9144/60/4/527
B. Mutunhu, B. Chipangura, and H. Twinomurinzi, “A Systematized Literature Review: Internet of Things (IoT) in the Remote Monitoring of Diabetes,” in Lecture Notes in Networks and Systems, Springer Science and Business Media Deutschland GmbH, 2023, pp. 649–660. doi: 10.1007/978-981-19-1610-6_57.
K. Maguraushe and B. M. Ndlovu, “The use of smart technologies for enhancing palliative care: A systematic review,” Digit Health, vol. 10, Jan. 2024, doi: 10.1177/20552076241271835.
B. Mutunhu Ndlovu, B. Chipangura, and S. Singh, “Towards a quantified-self technology conceptual framework for monitoring diabetes,” 2024, doi: 10.36303/SATNT.2024.43.1.970E.
B. M. Ndlovu, B. Chipangura, and S. Singh, “Factors Influencing Quantified SelfTechnology Adoption in Monitoring Diabetes,” in Proceedings of Ninth International Congress on Information and Communication Technology, X.-S. Yang, S. Sherratt, N. Dey, and A. Joshi, Eds., Singapore: Springer Nature Singapore, 2024, pp. 469–479.
A. M. Antoniadi et al., “Current challenges and future opportunities for xai in machine learning-based clinical decision support systems: A systematic review,” Applied Sciences (Switzerland), vol. 11, no. 11, Jun. 2021, doi: 10.3390/app11115088.
A. Das and P. Rad, “Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey,” Jun. 2020, [Online]. Available: http://arxiv.org/abs/2006.11371
K. Reel, “The benefits of practice standards and other practice-defining texts: And why healthcare ethicists ought to explore them,” HEC Forum, vol. 24, no. 3, pp. 203–217, Sep. 2012, doi: 10.1007/s10730-012-9186-9.
I. A. Taifa, D. M. Setu, T. Islam, S. K. Dey, and T. Rahman, “A hybrid approach with customized machine learning classifiers and multiple feature extractors for enhancing diabetic retinopathy detection,” Healthcare Analytics, vol. 5, Jun. 2024, doi: 10.1016/j.health.2024.100346.
M. T. Hagos and S. Kant, “Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset,” 2019.
S. Chokuwa and M. H. Khan, “Divergent Domains, Convergent Grading: Enhancing Generalization in Diabetic Retinopathy Grading,” Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025, pp. 3667–3677, 2025, doi: 10.1109/WACV61041.2025.00361.
C. The- and T. H. Tower, “Chapter 34 ( I ) Computational Complexity Play with Hanoi ( 3 ) and beyond ...,” vol. 34, no. I, pp. 1–13.
C. Jean-quartier, K. Bein, L. Hejny, E. Hofer, A. Holzinger, and F. Jeanquartier, “The Cost of Understanding — XAI Algorithms towards Sustainable ML in the View of Computational Cost,” pp. 1–14, 2023.
P. Sengupta and F. Eliassen, “Balancing Explainability-Accuracy of Complex Models,” no. Ml, pp. 1–18.
Y. Luo, H.-H. Tseng, S. Cui, L. Wei, and R. K. Ten Haken, “Review article Balancing accuracy and interpretability of machine learning approaches for radiation treatment outcomes modeling,” no. April 2019, pp. 1–12, 2022.
A. I. Ml et al., “FDA-Approved Artificial Intelligence and Machine Learning,” 2024.
A. Don, “Regulatory Perspectives of AI as Medical Device – a scoping review,” no. November, 2024.
H. Bleher and M. Braun, “Diffused responsibility: attributions of responsibility in the use of AI-driven clinical decision support systems,” AI and Ethics, vol. 2, no. 4, pp. 747–761, Nov. 2022, doi: 10.1007/s43681-022-00135-x.
B. Pickering, “Trust , but Verify : Informed Consent , AI Technologies , and Public Health Emergencies,” 2021.
C. Bascaran, M. Zondervan, C. Walker, N. J. Astbury, and A. Foster, “Diabetic retinopathy in Africa,” May 01, 2022, Springer Nature. doi: 10.1038/s41433-022-01999-3.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.