Prediction of diabetic retinopathy among type 2 diabetic patients in University of Gondar Comprehensive Specialized Hospital, 2006–2021: A prognostic model

• Published in: International journal of medical informatics (Shannon, Ireland) Vol. 190; p. 105536
• Main Authors: Mulat Tebeje, Tsion, Kindie Yenit, Melaku, Gedlu Nigatu, Solomon, Bizuneh Mengistu, Segenet, Kidie Tesfie, Tigabu, Byadgie Gelaw, Negalgn, Moges Chekol, Yazachew
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.10.2024
• Subjects: Adult; Aged; Algorithms; Bayes Theorem; Diabetes Mellitus, Type 2 - complications; Diabetes Mellitus, Type 2 - diagnosis; Diabetic retinopathy; Diabetic Retinopathy - diagnosis; Diabetic Retinopathy - epidemiology; Ethiopia; Ethiopia - epidemiology; Female; Follow-Up Studies; Hospitals, Special; Humans; Logistic Models; Machine learning; Male; Middle Aged; Nomogram; Nomograms; Prognosis; Retrospective Studies; Risk Factors; Risk prediction; Type 2 diabetes; Ethiopia; Type 2 diabetes; Diabetic retinopathy; T2DM; Risk prediction; AUROC; DM; DR; AUC; SD; DBP; PBG; LASSO; BUN; HbA1c; BMI; PDR; SBP; UoGCSH; Nomogram; ROC; HDL cholesterol; NPDR; Machine learning; FPG; Ethiopia
• ISSN: 1386-5056; 1872-8243; 1872-8243
• DOI: 10.1016/j.ijmedinf.2024.105536

•Naïve Bayes, K-nearest neighbor, decision tree, and logistic regression (LR) were employed to predict diabetic retinopathy among type 2 diabetic patients.•The LR model performed best, and significant predictors were used to develop a nomogram.•To make the nomogram accessible, a web-based application was developed. The URL is https://tsion.shinyapps.io/DynNomapp/.•Patients were classified as low-risk or high-risk for developing DR if their cutoff points were < 0.22 and ≥ 0.22, respectively.•The net benefit of using the nomogram was better than treating all or none of thepatients. There has been a paucity of evidence for the development of a prediction model for diabetic retinopathy (DR) in Ethiopia. Predicting the risk of developing DR based on the patient’s demographic, clinical, and behavioral data is helpful in resource-limited areas where regular screening for DR is not available and to guide practitioners estimate the future risk of their patients. A retrospective follow-up study was conducted at the University of Gondar (UoG) Comprehensive Specialized Hospital from January 2006 to May 2021 among 856 patients with type 2 diabetes (T2DM). Variables were selected using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. The data were validated by 10-fold cross-validation. Four ML techniques (naïve Bayes, K-nearest neighbor, decision tree, and logistic regression) were employed. The performance of each algorithm was measured, and logistic regression was a well-performing algorithm. After multivariable logistic regression and model reduction, a nomogram was developed to predict the individual risk of DR. Logistic regression was the best algorithm for predicting DR with an area under the curve of 92%, sensitivity of 87%, specificity of 83%, precision of 84%, F1-score of 85%, and accuracy of 85%. The logistic regression model selected seven predictors: total cholesterol, duration of diabetes, glycemic control, adherence to anti-diabetic medications, other microvascular complications of diabetes, sex, and hypertension. A nomogram was developed and deployed as a web-based application. A decision curve analysis showed that the model was useful in clinical practice and was better than treating all or none of the patients. The model has excellent performance and a better net benefit to be utilized in clinical practice to show the future probability of having DR. Identifying those with a higher risk of DR helps in the early identification and intervention of DR.