Prediction of retinopathy through machine learning in diabetes mellitus

Abstract

Aims: Development of a machine learning model on an electronic health record (EHR) dataset for predicting retinopathy in people with diabetes mellitus (DM), analysis of its explainability. Methods: A public dataset based on EHR records of patients diagnosed with DM located in İstanbul, Turkiye (n=77724) was used. The categorical variable indicating a retinopathy-positive diagnosis was chosen as the target variable. Variables were preprocessed and split into training and test sets with the same ratio of class distribution for model training and evaluation respectively. Four machine learning models were developed for comparison: logistic regression, decision tree, random forest and eXtreme Gradient Boosting (XGBoost). Each algorithm’s optimal hyperparameters were obtained using randomized search cross validation with 10-folds followed by the training of the models based on the results. The receiver operating characteristic (ROC) area under curve (AUC) score was used as the primary evaluation metric. SHapley Additive exPlanations (SHAP) analysis was done to provide explainability of the trained models. Results: The XGBoost model showed the best results on retinopathy classification on the test set with a low amount of overfitting (AUC: 0.813, 95% CI: 0.808-0.819). 15 variables that had the highest impact on the prediction were obtained for explainability, which include eye-ear drugs, other eye diseases, Disorders of refraction, Insulin aspart and hemoglobin A1c (HbA1c). Conclusion: Early detection of retinopathy based on EHR data can be successfully detected in people with diabetes using machine learning. Our study reports that the XGBoost algorithm performed best in this research, with the presence of other eye diseases, insulin dependence and high HbA1c being observed as important predictors of retinopathy.

Keywords

• Diabetic retinopathy
• diabetes mellitus
• machine learning
• electronic health records

References

1. World Health Organization (WHO). Diabetes. World Health Organization. Published May 4, 2023. Accessed February 29, 2024. https://www.who.int/news-room/fact-sheets/detail/diabetes
2. Ogurtsova K, Da Rocha Fernandes JD, Huang Y, et al. IDF diabetes atlas: global estimates for the prevalence of diabetes for 2015 and 2040. Diabetes Res Clin Pract. 2017;128:40-50.
3. Early treatment diabetic retinopathy study research group. Grading diabetic retinopathy from stereoscopic color fundus photographs-an extension of the modified airlie house classification. ETDRS report number 10. Early treatment diabetic retinopathy study research group. Ophthalmology. 1991;98(5 Suppl):786-806.
4. Steinmetz JD, Bourne RRA, Briant PS, et al. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the right to Sight: an analysis for the global burden of disease study. Lancet Glob Health. 2021;9(2):144-160.
5. Aiello LP, Gardner TW, King GL, et al. Diabetic retinopathy. Diabetes Care. 1998;21(1):143-156.
6. Wong TY, Sabanayagam C. Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence. Ophthalmologica. 2020;243(1):9-20.
7. Sloan FA, Grossman DS, Lee PP. Effects of receipt of guideline-recommended care on onset of diabetic retinopathy and its progression. Ophthalmology. 2009;116(8):1515-1521.
8. The diabetic retinopathy study research group. Indications for photocoagulation treatment of diabetic retinopathy: diabetic retinopathy study report no. 14. Int Ophthalmol Clin. 1987;27(4): 239-253.

9. Teo ZL, Tham YC, Yu M, Cheng CY, Wong TY, Sabanayagam C. Do we have enough ophthalmologists to manage vision-threatening diabetic retinopathy? A global perspective. Eye (Lond). 2020;34(7):1255-1261.
10. Liu L, Wang M, Li G, Wang Q. Construction of predictive model for type 2 diabetic retinopathy based on extreme learning machine. Diabetes Metab Syndr Obes. 2022;15:2607-2617.
11. Ogunyemi OI, Gandhi M, Lee M, et al. Detecting diabetic retinopathy through machine learning on electronic health record data from an urban, safety net healthcare system. JAMIA Open. 2021;4(3):1-10.
12. Saleh E, Błaszczyński J, Moreno A, et al. Learning ensemble classifiers for diabetic retinopathy assessment. Artif Intell Med. 2018;85:50-63.
13. Gülkesen KH, Ülgü MM, Mutlu B, et al. Machine learning for prediction of glycemic control in diabetes mellitus. Mendeley Data; 2022. doi: 10.17632/rr4rzzrjfc.2
14. The pandas development team. pandas-dev/pandas: pandas (v2.0.2). Zenodo; 2023. doi: 10.5281/zenodo.7979740
15. McKinney W. Data structures for statistical computing in python. In: Van Der Walt S, Millman J, eds. Proceedings of the 9th Python in Science Conference; 2010:56-61.
16. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12(85):2825-2830.
17. Lundberg SM, Lee SI. A Unified approach to interpreting model predictions. In: Guyon I, Luxburg U Von, Bengio S, et al., eds. Advances in neural information processing systems 30. Curran Associates, Inc.;2017.
18. Hunter JD. Matplotlib: a 2D graphics environment. Comput Sci Eng. 2007;9(3):90-95.
19. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316(22):2402-2410.
20. Alabdulwahhab KM. Senile cataract in patients with diabetes with and without diabetic retinopathy: a community-based comparative study. J Epidemiol Glob Health. 2022;12(1):56-63.