Background: Age-related macular degeneration (AMD) is a complex eye disorder with an environmental and genetic origin, affecting millions worldwide. The study aims to explore the association between retinal morphology and the polygenic risk score (PRS) for AMD using fundus images and deep learning techniques. Methods: The study used and pre-processed 23,654 fundus images from 332 subjects (235 patients with AMD and 97 controls), ultimately selecting 558 high-quality images for analysis. The fine-tuned DenseNet121 deep learning model was employed to estimate PRS from single fundus images. After training, deep features were extracted, fused, and used in machine learning regression models to estimate PRS for each subject. The Grad-CAM technique was applied to examine the relationship between areas of increased model activity and the retina’s morphological features specific to AMD. Results: Using the hybrid approach improved the results obtained by DenseNet121 in 5-fold cross-validation. The final evaluation metrics for all predictions from the best model from each fold are MAE = 0.74, MSE = 0.85, RMSE = 0.92, R² = 0.18, MAPE = 2.41. Grad-CAM heatmap evaluation showed that the model decisions rely on lesion area, focusing mostly on the presence of drusen. The proposed approach was also shown to be sensitive to artifacts present in the image. Conclusions: The findings indicate an association between fundus images and AMD PRS, suggesting that deep learning models may effectively estimate genetic risk for AMD from retinal images, potentially aiding in early detection and personalized treatment strategies.

Background/Objectives: Real-world registries of neovascular age-related macular degeneration (nAMD) treatments provide critical insights for optimizing patient care and resource allocation. This study evaluates one-year outcomes of anti-VEGF therapy with aflibercept, ranibizumab, and brolucizumab in the Polish Therapeutic Program Monitoring System between 1 January 2016 and 31 October 2023. Methods: We analyzed data from 51,902 treatment-naïve patients with nAMD, comparing baseline characteristics and outcomes across drugs, as well as between those who discontinued therapy early and those treated for at least one year. Results: No significant baseline differences were found between drug groups. One-year follow-up was available for 40,396 eyes; 3184 were lost to follow-up, and 8322 discontinued treatment: 14.4% for those receiving aflibercept, 24.1% for those receiving brolucizumab, and 20.1% for those receiving ranibizumab. Early discontinuers were older and had higher baseline visual acuity (aflibercept, ranibizumab). Twelve-month treatment outcomes, particularly visual acuity gains and injection frequency (~6–7/year), were similar across agents. Only ~22% achieved at least 0.3 logMAR improvement, underscoring real-world treatment challenges. Conclusions: System-level support, appropriate treatment intensification, and strategic use of newer, durable agents like brolucizumab are crucial to narrowing the gap between clinical trial efficacy and real-world effectiveness, ultimately improving long-term outcomes in nAMD care.

Background: Age-related macular degeneration (AMD) is a multifactorial disease encompassing a complex interaction between aging, environmental risk factors, and genetic susceptibility. The study aimed to determine whether there is a relationship between the polygenic risk score (PRS) in patients with AMD and the characteristics of the retinal vascular network visualized by optical coherence tomography angiography (OCTA). Methods: 235 patients with AMD and 97 healthy controls were included. We used data from a previous AMD PRS study with the same group. The vascular features from different retina layers were compared between the control group and the patients with AMD. The association between features and PRS was then analyzed using univariate and multivariate approaches. Results: Significant differences between the control group and AMD patients were found in the vessel diameter distribution (variance: p = 0.0193, skewness: p = 0.0457) and fractal dimension distribution (mean: p = 0.0024, variance: p = 0.0123). Both univariate and multivariate analyses showed no direct and significant association between the characteristics of the vascular network and AMD PRS. Conclusions: The vascular features of the retina do not constitute a biomarker of the risk of AMD. We have not identified a genotype–phenotype relationship, and the expression of AMD-related genes is perhaps not associated with the characteristics of the retinal vascular network.

Purpose: To evaluate long‐term outcomes of anti‐VEGF therapy for nAMD using the Polish Retinal Therapeutic Program Monitoring Registry. Methods: The cohort consisted of 63 840 eyes with nAMD qualified for treatment from 2016 to 2022, with follow‐up through 31 October 2023. Long‐term follow‐up (>5 years) was conducted for 7631 eyes. Statistical comparisons and multivariate logistic regression analysed differences between treatment failure and long‐term treatment, treatment effectiveness, drug efficacy and predictive factors. Results: The relative risk of nAMD in females was 1.45. By the last follow‐up, 17 518 (48.6%) patients discontinued treatment due to patient‐related factors, 7202 (20.0%) due to treatment failure, 6285 (17.4%) for other reasons and 5065 (14.0%) due to death or clinical complications. Long‐term patients were significantly younger, more of them were previously treated, received fewer injections per year and had better baseline BCVA and lower CRT than the failure group. Females and previously treated patients had a higher likelihood of long‐term therapy, while older age and initial ranibizumab treatment increased the risk of failure. Patients with an initial BCVA >0.4 logMAR had significantly worse BCVA outcomes, while CRT and treatment strategy showed no significant differences. Introduction of programme exclusion if treatment gap >4 months reduced long breaks, increased injection numbers, slightly lowered BCVA and had no significant effect on CRT. Conclusion: Early visual acuity response, drug choice (aflibercept), and healthcare system modifications influence long‐term success and adherence in nAMD management. While systemic changes improved continuity and injection frequency, they did not enhance visual outcomes, highlighting the need for individualized treatment strategies.