RESUMEN
BACKGROUND: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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.
RESUMEN
BACKGROUND: Home delivery is responsible for a high number of maternal and newborn deaths due to the occurrence of obstetric complications during labour and delivery. Little is known about the incidence and predictors of women's place of delivery after utilizing antenatal care services in Ethiopia and the study area. Therefore, the purpose of this study is to fill those gaps in the studies mentioned above by determining the incidence and predictors of women's place of delivery. METHODS: An institutional-based prospective cohort study was conducted among pregnant women in public hospitals of Gedeo zone, Southern Ethiopia between May 1 and October 30, 2021. A total of 390 pregnant women receiving antenatal care at Gedeo zone public hospitals were enrolled using a systematic random sampling technique and followed up to delivery. Data were entered into Epidata version 3.1 and exported to SPSS version 25 for analysis. For both bivariate and multivariable analyses, a poison regression model was used to identify the association between the dependent and independent variables. A statistical significance level was declared at a p-value less than 0.05. RESULTS: In this study, the overall incidence of home delivery and institutional delivery among pregnant women was 37.4% (95% CI: (32.5, 41.9)) and 62.6% (95% CI: 58.1, 67.5)) respectively. Distance from home to nearest health facility(ARR = 1.17:95%:CI (1.01,1.36), poor quality of antenatal care service(ARR = 1.40;95%:CI (1.10,1.79), no formal maternal education(ARR = 1.49;95%:CI (1.21,1.83), previous home delivery history(ARR = 1.38;95%:CI(1.22,1.56), unplanned pregnancy(ARR = 1.23;95%:CI (1.10,1.37) and history of pregnancy-related complication at health facility(ARR = 1.16;95%:CI(1.02,1.33) were predictors of home delivery. CONCLUSIONS: The study indicated a high incidence of home birth after utilizing antenatal care services. As a result, interventions targeting those identified factors during antenatal care services are critical to reducing home births.