International Journal of Retina and Vitreous最新文献

Background: The aim of this study is to evaluate near and distance visual acuity (VA) and their correlation with the National Eye Institute Visual Function Questionnaire (NEI VFQ-25) outcomes in patients with diabetic macular edema (DME) and macular edema due to retinal vein occlusion (RVO) treated with aflibercept.

Methods: In this prospective study, we included 87 eyes of patients diagnosed with DME (n = 61) and RVO (n = 26), who received aflibercept treatment and were followed until the 8th injection. Near VA was examined on the 1st, 2nd, 3rd, 4th, 6th, and 8th injection, and patients completed the NEI VFQ-25 on the 1st, 4th, and 8th aflibercept injection.

Results: The mean near VA at baseline in all eyes was 0.89 ± 0.12 logMAR. With every administration, there was a statistically significant improvement; on the 4th (0.70 ± 0.19; p = 0.000) and the 8th application (0.60 ± 0.19; p = 0.000). At baseline, the mean NEI VFQ-25 total score was 71 ± 14%, and improved to 81 ± 13% (p = 0.000) on the 8th injection. The most significant score gain was recorded in the near VA subscale (+ 20 ± 14%, p = 0.000). There was no statistically significant difference between DME and RVO group in the questionnaire or near VA outcomes.

Conclusion: Aflibercept treatment resulted in a remarkable improvement of near vision by 4 lines of logMAR optotype after the 8th application. The near vision questionnaire subscale, initially scoring the lowest, exhibited the greatest gain during the treatment period. This underscores the importance of near vision and reading ability for patients with DME and RVO.

Background: Diabetic retinopathy (DR) is the leading cause of adult blindness in the working age population worldwide, which can be prevented by early detection. Regular eye examinations are recommended and crucial for detecting sight-threatening DR. Use of artificial intelligence (AI) to lessen the burden on the healthcare system is needed.

Purpose: To perform a pilot cost-analysis study for detecting DR in a cohort of minority women with DM in Oslo, Norway, that have the highest prevalence of diabetes mellitus (DM) in the country, using both manual (ophthalmologist) and autonomous (AI) grading. This is the first study in Norway, as far as we know, that uses AI in DR- grading of retinal images.

Methods: On Minority Women's Day, November 1, 2017, in Oslo, Norway, 33 patients (66 eyes) over 18 years of age diagnosed with DM (T1D and T2D) were screened. The Eidon - True Color Confocal Scanner (CenterVue, United States) was used for retinal imaging and graded for DR after screening had been completed, by an ophthalmologist and automatically, using EyeArt Automated DR Detection System, version 2.1.0 (EyeArt, EyeNuk, CA, USA). The gradings were based on the International Clinical Diabetic Retinopathy (ICDR) severity scale [1] detecting the presence or absence of referable DR. Cost-minimization analyses were performed for both grading methods.

Results: 33 women (64 eyes) were eligible for the analysis. A very good inter-rater agreement was found: 0.98 (P < 0.01), between the human and AI-based EyeArt grading system for detecting DR. The prevalence of DR was 18.6% (95% CI: 11.4-25.8%), and the sensitivity and specificity were 100% (95% CI: 100-100% and 95% CI: 100-100%), respectively. The cost difference for AI screening compared to human screening was $143 lower per patient (cost-saving) in favour of AI.

Conclusion: Our results indicate that The EyeArt AI system is both a reliable, cost-saving, and useful tool for DR grading in clinical practice.

Background: This study aims to investigate the factors affecting the vitreous levels of pigment epithelium-derived factor (PEDF) and vascular endothelial growth factor (VGEF) among patients with pars plana vitrectomy (PPV). Also, this study correlates the levels of PEDF with RRD characteristics.

Methods: All patients who were scheduled for PPV for any indication were included in the study. They were divided into a case group which included patients with advanced PDR and a control group which included the remaining diagnoses. During the PPV, an undiluted vitreous sample was taken and the enzyme-linked immunosorbent assay method was utilized to measure the levels of VEGF and PEDF.

Results: Eighty eyes were involved. Patients diagnosed with advanced PDR and endophthalmitis exhibited higher levels of VEGF. PEDF was affected inversely by the age of the patients and PEDF levels were higher in RRD and endophthalmitis cases. In patients with RRD, the level of PEDF was higher if the tear was found inferiorly, if the macula was detached, and with a longer duration of RRD.

Conclusions: This study highlights the clinical importance of those biomarkers. Anti-VEGF-based treatment is the mainstay against PDR. PEDF may show a promising predictive values regarding patients with RRD.

Background: Code-free deep learning (CFDL) is a novel tool in artificial intelligence (AI). This study directly compared the discriminative performance of CFDL models designed by ophthalmologists without coding experience against bespoke models designed by AI experts in detecting retinal pathologies from optical coherence tomography (OCT) videos and fovea-centered images.

Methods: Using the same internal dataset of 1,173 OCT macular videos and fovea-centered images, model development was performed simultaneously but independently by an ophthalmology resident (CFDL models) and a postdoctoral researcher with expertise in AI (bespoke models). We designed a multi-class model to categorize video and fovea-centered images into five labels: normal retina, macular hole, epiretinal membrane, wet age-related macular degeneration and diabetic macular edema. We qualitatively compared point estimates of the performance metrics of the CFDL and bespoke models.

Results: For videos, the CFDL model demonstrated excellent discriminative performance, even outperforming the bespoke models for some metrics: area under the precision-recall curve was 0.984 (vs. 0.901), precision and sensitivity were both 94.1% (vs. 94.2%) and accuracy was 94.1% (vs. 96.7%). The fovea-centered CFDL model overall performed better than video-based model and was as accurate as the best bespoke model.

Conclusion: This comparative study demonstrated that code-free models created by clinicians without coding expertise perform as accurately as expert-designed bespoke models at classifying various retinal pathologies from OCT videos and images. CFDL represents a step forward towards the democratization of AI in medicine, although its numerous limitations must be carefully addressed to ensure its effective application in healthcare.