Abstract
Diabetic retinopathy (DR) is vision impairment and a life-threatening condition for diabetic patients. Especially type II diabetic people have higher chances of getting retinal problems. Hence, early prediction of DR is necessary for preventing the diabetic patients from vision impairment. The main aim of this feasibility study is to identify the most critical risk features that could lead to diabetic retinopathy. This study investigated type II diabetic patients’ socio-analytical, diabetes, behavioral, and clinical risk factors. We conducted a self-individual questionnaire session for all participants. Our questionnaire asked about the reliability of results, feeling comfortable during the screening test, willingness to participate in future screenings, overall perspective, and satisfaction with the DR screening test. We proposed a random forest model for predicting the prevalence of DR risk among diabetics. Further explanations of the model were conducted using more robust SHAP eXplainable Artificial Intelligence (XAI) tools. The SHAP method makes it possible to understand how input variables interact with their representative output records, as well as how input variables are ranked. In addition, various descriptive and inferential statistical analyses were performed on the data and evaluated the significant relationship between the factors discussed above via hypothesis testing. This feasibility study involved 172 type II diabetic patients (73 males and 99 females). Therefore, we found that 81 (47.09%) out of 172 participants had referable DR. The average age of the patients was determined as 55.08, with a standard deviation of ± 9.770 (ranging from 40 to 79). Type II patients were affected by mild, moderate, severe, and advanced proliferative diabetic retinopathy (PDR) stages with 23.83%, 13.95%, 5.81%, and 3.48%, respectively, of the total samples. The developed RF model obtained high accuracy of 94.9% using clinical dataset. Our results showed that the formation of tiny microminiature lesions was noticeable in type II diabetic patients with aged people, abnormal blood glucose levels, and prolonged diabetes duration.
Graphical Abstract
Similar content being viewed by others
Data availability
The datasets used and analyzed during the current study are available from the corresponding author upon reasonable request.
Abbreviations
- Anti VEGF:
-
Anti vascular endothelial growth factor
- ANOVA:
-
Analysis of variance
- BMI:
-
Body mass index
- DBP:
-
Diastolic blood pressure
- DR:
-
Diabetic retinopathy
- EOS:
-
Electro optical system
- ETDRS:
-
Early Treatment Diabetic Retinopathy Study
- EURODIB:
-
Epidemiology and prevention of diabetes study
- FOV:
-
Field of view
- HbA1c:
-
Haemoglobin A1c
- HSD:
-
Honestly significant difference
- KMO:
-
Kaiser-Meyer-Olkin method
- KNN:
-
K-nearest neighbour
- LCD:
-
Liquid crystal display
- LR:
-
Logistic Regression
- NB:
-
Naïve Bayes
- NHS:
-
National health service
- NPDR:
-
Non proliferative diabetic retinopathy
- PDR:
-
Proliferative diabetic retinopathy
- RF:
-
Random Forest
- SBP:
-
Systolic blood pressure
- SHAP:
-
Shapley Additive Explanation
- SPSS:
-
Software package for social science
- SVM:
-
Support Vector Machine
- WESDR:
-
Wisconsin epidemiologic study of diabetic retinopathy
References
Egan, A. M., & Dinneen, S. F. (2019). What is diabetes?. Medicine, 47(1), 1-4.
Akhtar, S. N., & Dhillon, P. (2017). Prevalence of diagnosed diabetes and associated risk factors: Evidence from the large-scale surveys in India. Journal of Social Health and Diabetes, 5(01), 028-036.
Narang, R. (2010). Measuring perceived quality of health care services in India. International journal of health care quality assurance, 23(2), 171-186.
Pradeepa, R., Deepa, R., & Mohan, V. (2002). Epidemiology of diabetes in India--current perspective and future projections. Journal of the Indian Medical Association, 100(3), 144-148.
Bonnin, S., Dupas, B., Lavia, C., Erginay, A., Dhundass, M., Couturier, A., ... & Tadayoni, R. (2019). Anti–vascular endothelial growth factor therapy can improve diabetic retinopathy score without change in retinal perfusion. Retina (Philadelphia, Pa.), 39(3), 426. https://doi.org/10.1097/IAE.0000000000002422
Murthy, G. V., Gupta, S. K., Bachani, D., Tewari, H. K., & John, N. (2004). Human resources and infrastructure for eye care in India: current status. National medical journal of India, 17(3), 128-134.
Roy, R., Lobo, A., Pal, B. P., Oliveira, C. M., Raman, R., & Sharma, T. (2014). Automated diabetic retinopathy imaging in Indian eyes: A pilot study. Indian journal of ophthalmology, 62(12), 1121. https://doi.org/10.4103/0301-4738.149129
Lalithadevi, B., & Krishnaveni, S. (2022). Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: A comprehensive review. Concurrency and Computation: Practice and Experience, e7032. https://doi.org/10.1002/cpe.7032
Joseph, L. P., Joseph, E. A., & Prasad, R. (2022). Explainable diabetes classification using hybrid Bayesian-optimized TabNet architecture. Computers in Biology and Medicine, 151, 106178.
Jahmunah, V., Ng, E. Y. K., Tan, R. S., Oh, S. L., & Acharya, U. R. (2022). Explainable detection of myocardial infarction using deep learning models with Grad-CAM technique on ECG signals. Computers in Biology and Medicine, 146, 105550.
Ren, Z., Qian, K., Dong, F., Dai, Z., Nejdl, W., Yamamoto, Y., & Schuller, B. W. (2022). Deep attention-based neural networks for explainable heart sound classification. Machine Learning with Applications, 100322.
Alicioglu, G., & Sun, B. (2022). A survey of visual analytics for Explainable Artificial Intelligence methods. Computers & Graphics, 102, 502-520.
Kumari, S., Kumar, D., & Mittal, M. (2021). An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier. International Journal of Cognitive Computing in Engineering, 2, 40-46.
Meena, J., & Hasija, Y. (2022). Application of explainable artificial intelligence in the identification of Squamous Cell Carcinoma biomarkers. Computers in Biology and Medicine, 146, 105505.
Magesh, P. R., Myloth, R. D., & Tom, R. J. (2020). An explainable machine learning model for early detection of Parkinson's disease using LIME on DaTSCAN imagery. Computers in Biology and Medicine, 126, 104041.
Islam, M. S., Awal, M. A., Laboni, J. N., Pinki, F. T., Karmokar, S., Mumenin, K. M., ... & Mirjalili, S. (2022). HGSORF: Henry Gas Solubility Optimization-based Random Forest for C-Section prediction and XAI-based cause analysis. Computers in Biology and Medicine, 105671.
Hassan, M. R., Islam, M. F., Uddin, M. Z., Ghoshal, G., Hassan, M. M., Huda, S., & Fortino, G. (2022). Prostate cancer classification from ultrasound and MRI images using deep learning based Explainable Artificial Intelligence. Future Generation Computer Systems, 127, 462-472.
Kohoutová, L., Heo, J., Cha, S., Lee, S., Moon, T., Wager, T. D., & Woo, C. W. (2020). Toward a unified framework for interpreting machine-learning models in neuroimaging. Nature protocols, 15(4), 1399-1435.
Amparore, E., Perotti, A., & Bajardi, P. (2021). To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods. PeerJ Computer Science, 7, e479.
Dikshit, A., & Pradhan, B. (2021). Interpretable and explainable AI (XAI) model for spatial drought prediction. Science of the Total Environment, 801, 149797.
Kollias, A. N., & Ulbig, M. W. (2010). Diabetic retinopathy: early diagnosis and effective treatment. Deutsches Arzteblatt International, 107(5), 75.
Attiku, Y., He, Y., Nittala, M. G., & Sadda, S. R. (2021). Current status and future possibilities of retinal imaging in diabetic retinopathy care applicable to low-and medium-income countries. Indian Journal of Ophthalmology, 69(11), 2968.
Whitley, E., & Ball, J. (2002). Statistics review 4: sample size calculations. Critical care, 6, 1-7
Aldington, S. J., Kohner, E. M., Meuer, S., Klein, R., & Sjølie, A. K. (1995). Methodology for retinal photography and assessment of diabetic retinopathy: the EURODIAB IDDM complications study. Diabetologia, 38(4), 437–444. https://doi.org/10.1007/BF00410281
Solomon, S. D., & Goldberg, M. F. (2019). ETDRS grading of diabetic retinopathy: still the gold standard?. Ophthalmic research, 62(4), 190-195.
Lechner, J., O'Leary, O. E., & Stitt, A. W. (2017). The pathology associated with diabetic retinopathy. Vision research, 139, 7-14.
Eszes, D. J., Szabó, D. J., Russell, G., Kirby, P., Paulik, E., Nagymajtényi, L., ... & Petrovski, B. É. (2016). Diabetic retinopathy screening using telemedicine tools: pilot study in Hungary. Journal of Diabetes Research, 2016. https://doi.org/10.1155/2016/4529824
Obasanmi, G., Lois, N., Armstrong, D., Lavery, N. J., Hombrebueno, J. R., Lynch, A., ... & Xu, H. (2020). Circulating leukocyte alterations and the development/progression of diabetic retinopathy in type 1 diabetic patients-a pilot study. Current Eye Research, 45(9), 1144–1154. https://doi.org/10.1080/02713683.2020.1718165
Wang, J., Li, W., Wang, C., Wang, L., He, T., Hu, H., ... & Chen, L. (2020). Enterotype bacteroides is associated with a high risk in patients with diabetes: a pilot study. Journal of Diabetes Research, 2020. https://doi.org/10.1155/2020/6047145
Sen, S., & Yildirim, I. (2022). A tutorial on how to conduct meta-analysis with IBM SPSS statistics. Psych, 4(4), 640-667.
Allen, P., Bennett, K., & Heritage, B. (2014). SPSS statistics version 22: A practical guide. Cengage Learning Australia.
Sulaiman, A. S. M., & Shabri, A. (2021). Forecasting carbon dioxide emissions for Malaysia using grey model with Cramer’s rule. Malaysian J. Fundam. Appl. Sci, 17, 437-445.
Cook, G. B., & Watson, F. R. (1968). Events in the natural history of prostate cancer: using salvage curves, mean age distributions and contingency coefficients. The Journal of Urology, 99(1), 87-96.
Sivaprasad, S., Sahasranamam, V. I., George, S., Sadanandan, R., Gopal, B., Premnazir, L., ... & Netuveli, G. (2021). Burden of Diabetic Retinopathy amongst People with Diabetes Attending Primary Care in Kerala: Nayanamritham Project. Journal of Clinical Medicine, 10(24), 5903. https://doi.org/10.3390/jcm10245903
Lund, S. H., Aspelund, T., Kirby, P., Russell, G., Einarsson, S., Palsson, O., & Stefánsson, E. (2016). Individualised risk assessment for diabetic retinopathy and optimisation of screening intervals: a scientific approach to reducing healthcare costs. British Journal of Ophthalmology, 100(5), 683-687.
Chen, Y. W., Wang, Y. Y., Zhao, D., Yu, C. G., Xin, Z., Cao, X., ... & Yang, J. K. (2015). High prevalence of lower extremity peripheral artery disease in type 2 diabetes patients with proliferative diabetic retinopathy. PloS One, 10(3), e0122022. https://doi.org/10.1371/journal.pone.0122022
Gilbert, C., Gordon, I., Mukherjee, C. R., & Govindhari, V. (2020). Guidelines for the prevention and management of diabetic retinopathy and diabetic eye disease in India: a synopsis. Indian journal of ophthalmology, 68(Suppl 1), S63.
Schiel, R., Bambauer, R., & Steveling, A. (2018). Technology in Diabetes Treatment: update and future. Artificial organs, 42(11), 1017-1027.
Fong, D. S., Aiello, L., Gardner, T. W., King, G. L., Blankenship, G., Cavallerano, J. D., ... & American Diabetes Association. (2004). Retinopathy in diabetes. Diabetes Care, 27(suppl_1), s84–s87. https://doi.org/10.2337/diacare.26.2007.S99
Bain, S. C., Klufas, M. A., Ho, A., & Matthews, D. R. (2019). Worsening of diabetic retinopathy with rapid improvement in systemic glucose control: a review. Diabetes, Obesity and Metabolism, 21(3), 454–466. https://doi.org/10.1111/dom.13538
Tapp, R. J., Shaw, J. E., Harper, C. A., De Courten, M. P., Balkau, B., McCarty, D. J., ... & AusDiab Study Group. (2003). The prevalence of and factors associated with diabetic retinopathy in the Australian population. Diabetes Care, 26(6), 1731–1737. https://doi.org/10.2337/diacare.26.6.1731
Jingi, A. M., Tankeu, A. T., Ateba, N. A., & Noubiap, J. J. (2017). Mechanism of worsening diabetic retinopathy with rapid lowering of blood glucose: the synergistic hypothesis. BMC Endocrine Disorders, 17(1), 1–4. https://doi.org/10.1186/s12902-017-0213-3
Zhao, C., Wang, W., Xu, D., Li, H., Li, M., & Wang, F. (2014). Insulin and risk of diabetic retinopathy in patients with type 2 diabetes mellitus: data from a meta-analysis of seven cohort studies. Diagnostic Pathology, 9(1), 1–7. https://doi.org/10.1186/1746-1596-9-130
Gupta, A., Delhiwala, K. S., Raman, R. P., Sharma, T., Srinivasan, S., & Kulothungan, V. (2016). Failure to initiate early insulin therapy–A risk factor for diabetic retinopathy in insulin users with Type 2 diabetes mellitus: sankara Nethralaya-Diabetic Retinopathy Epidemiology and Molecular Genetics Study (SN-DREAMS, Report number 35). Indian Journal of Ophthalmology, 64(6), 440. https://doi.org/10.4103/0301-4738.187668
Preti, R. C., Iovino, C., Abalem, M. F., Garcia, R., Dos Santos, H. N. V., Sakuno, G., ... & Sarraf, D. (2021). Prevalence of focal inner, middle, and combined retinal thinning in diabetic patients and its relationship with systemic and ocular parameters. Translational Vision Science & Technology, 10(2), 26–26. https://doi.org/10.1167/tvst.10.2.26
Shrestha, N. (2021). Factor analysis as a tool for survey analysis. American Journal of Applied Mathematics and Statistics, 9(1), 4-11.
Peng, J., Zou, K., Zhou, M., Teng, Y., Zhu, X., Zhang, F., & Xu, J. (2021). An explainable artificial intelligence framework for the deterioration risk prediction of hepatitis patients. Journal of Medical Systems, 45(5), 1-9.
Adak, A., Pradhan, B., Shukla, N., & Alamri, A. (2022). Unboxing deep learning model of food delivery service reviews using explainable artificial intelligence (XAI) technique. Foods, 11(14), 2019.
Acknowledgements
The authors would like to thank all participants and our institution SRMIST in this study. And we thank the doctors and clinical supporting faculties for their support in fundus image acquisition and disease severity detection.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. B.Lalithadevi performed data collection, statistical analysis, preparation of manuscript, model development with shap analysis and interpretation of the results. S.Krishnaveni involved in study design, reviewing, editing the manuscript and participated in the result interpretation. Fundus images acquisition and disease severity grading were done by J.Samuel Cornelius Gnanadurai. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics approval
The procedures used in this study adhere to the tenets of the Declaration of Helsinki. This study was approved by the Institutional Ethics Committee (IEC) and was conducted at SRM Medical College Hospital and Research Centre, Kattankulathur according to the guidelines(Approval no/8377).
Informed consent
Informed consent was obtained from all individual participants included in the study.
Consent to publish
Patients signed informed consent regarding publishing their data and photographs.
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lalithadevi, B., Krishnaveni, S. & Gnanadurai, J.S.C. A Feasibility Study of Diabetic Retinopathy Detection in Type II Diabetic Patients Based on Explainable Artificial Intelligence. J Med Syst 47, 85 (2023). https://doi.org/10.1007/s10916-023-01976-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-023-01976-7