Search

Abstract This study aims to evaluate the macular and the optic nerve head thickness and vascular profiles in KC patients and compare them with two groups of healthy emmetrope and subjects with myopic-astigmatism. This cross-sectional study was conducted at Khatam-Al-Anbia Eye Hospital between 2022 and 2023. Subjects aged 18 to 40 were prone to be included in the study. The participants in this study were grouped into three categories: emmetrope (E), myopic-astigmatic (MA), and keratoconus (KC). All participants underwent a comprehensive ocular examination, as well as macular and optic nerve head (ONH) optical coherence tomography angiography (OCTA). In this study, 143 subjects, 50 cases in the KCN group, 46 cases in the E group, and 47 cases in the MA group, enrolled. There was no difference between the three groups regarding age (p = 0.123) and gender (p = 0.632). The superficial and deep capillary densities at the fovea, parafovea, and perifovea were significantly lower in KC patients than in the control groups (p

Purpose: To investigate peripapillary retinal nerve fiber layer (pRNFL) thickness changes in preterm children with or without retinopathy of prematurity (ROP) history compared to full-term children. Methods: A retrospective comparative cohort study assessing pRNFL thickness was completed in children aged 4–8 years. Four groups of children were included (n = 30 each group): children with a history of ROP who were treated with intravitreal bevacizumab, children with ROP who received no treatment, and preterm children without ROP compared to age- and gender-matched full-term children. Results: A total of 120 eyes from 120 children were enrolled in this study. Both treated and regressed ROP children showed a significantly thinner pRNFL in the nasal quadrant compared to full-term children (P = 0.017 and P = 0.008, respectively). The pRNFL in the superior quadrant of treated ROP children was thinner than the preterm and control groups (P = 0.015 and P = 0.023, respectively), whereas the inferior quadrant of treated ROP children was thinner than the preterm group alone (P = 0.008). The pRNFL thickness in the temporal quadrant was comparable between groups (P = 0.129). The average spatial distribution profile of pRNFL thickness in treated ROP children was significantly thinner than in the preterm group (P = 0.041). Conclusion: pRNFL thickness is significantly altered in children with a prior history of treated ROP with thinning of the nasal and superior quadrants compared to full-term children.

Abstract Introduction Open globe injuries (OGI) represent a main preventable reason for blindness and visual impairment, particularly in developing countries. The goal of this study is evaluating key variables affecting the prognosis of open globe injuries and validating internally and comparing different machine learning models to estimate final visual acuity. Materials and methods We reviewed three hundred patients with open globe injuries receiving treatment at Khatam-Al-Anbia Hospital in Iran from 2020 to 2022. Age, sex, type of trauma, initial VA grade, relative afferent pupillary defect (RAPD), zone of trauma, traumatic cataract, traumatic optic neuropathy (TON), intraocular foreign body (IOFB), retinal detachment (RD), endophthalmitis, and ocular trauma score (OTS) grade were the input features. We calculated univariate and multivariate regression models to assess the association of different features with visual acuity (VA) outcomes. We predicted visual acuity using ten supervised machine learning algorithms including multinomial logistic regression (MLR), support vector machines (SVM), K-nearest neighbors (KNN), naïve bayes (NB), decision tree (DT), random forest (RF), bagging (BG), adaptive boosting (ADA), artificial neural networks (ANN), and extreme gradient boosting (XGB). Accuracy, positive predictive value (PPV), recall, F-score, brier score (BS), Matthew correlation coefficient (MCC), receiver operating characteristic (AUC-ROC), and calibration plot were used to assess how well machine learning algorithms performed in predicting the final VA. Results The artificial neural network (ANN) model had the best accuracy to predict the final VA. The sensitivity, F1 score, PPV, accuracy, and MCC of the ANN model were 0.81, 0.85, 0.89, 0.93, and 0.81, respectively. In addition, the estimated AUC-ROC and AUR-PRC of the ANN model for OGI patients were 0.96 and 0.91, respectively. The brier score and calibration log-loss for the ANN model was 0.201 and 0.232, respectively. Conclusion As classic and ensemble ML models were compared, results shows that the ANN model was the best. As a result, the framework that has been presented may be regarded as a good substitute for predicting the final VA in OGI patients. Excellent predictive accuracy was shown by the open globe injury model developed in this study, which should be helpful to provide clinical advice to patients and making clinical decisions concerning the management of open globe injuries.

Purpose. To compare biometric and optical coherence tomography parameters as well as refractive status in preterm children aged 4–8 years with or without retinopathy of prematurity (ROP), and evaluate their correlations with age and gender-matched full-term children. Methods. Retrospective comparative cohort study of four groups of children. Children with a history of preterm birth, including ROP who received intravitreal bevacizumab (IVB) treatment, children with a history of ROP that regressed without treatment and those with no history of ROP were compared to age and gender-matched full-term children as a control group. Best corrected visual acuity (BCVA), spherical equivalent of refraction (SE), macular and choroidal thickness, as well as biometric parameters was measured. Results. A total of 120 eyes of 120 children (30 children in each group) were included. There was no significant difference in BCVA, SE, and subjective cylinder between groups (p=0.05, p=0.3, p=0.6, respectively). Axial length was significantly shorter, and the cornea was steeper in both ROP groups than in other groups (p=0.001, p