Explore the vast range of titles available.

This study aims to investigate the prevalence of visual impairments, such as myopia, hyperopia, and astigmatism, among school-age children (7–9 years) in Lubelskie Voivodeship (Republic of Poland) and apply artificial intelligence (AI) in the detection of severe ocular diseases. A total of 1049 participants (1.7% of the total child population in the region) were examined through a combination of standardized visual acuity tests, autorefraction, and assessment of fundus images by a convolutional neural network (CNN) model. The results from this artificial intelligence (AI) model were juxtaposed with assessments conducted by two experienced ophthalmologists to gauge the model's accuracy. The results demonstrated myopia, hyperopia, and astigmatism prevalences of 3.7%, 16.9%, and 7.8%, respectively, with myopia showing a significant age-related increase and hyperopia decreasing with age. The AI model performance was evaluated using the Dice coefficient, reaching 93.3%, indicating that the CNN model was highly accurate. The study underscores the utility of AI in the early detection and diagnosis of severe ocular diseases, providing a foundation for future research to improve paediatric ophthalmic screening and treatment outcomes.

Keratoconus is a progressive eye disease characterized by the thinning and bulging of the cornea, leading to visual impairment. Early and accurate diagnosis is crucial for effective management and treatment. This study investigates the application of machine learning models to identify keratoconus based on corneal topography and biomechanical data. We collected a dataset comprising 144 corneal scans from adults aged 18–35, including an equal proportion of keratoconus and normal cases. Various machine learning algorithms were trained and evaluated on datasets containing different parameters obtained using the Pentacam device. The Random Forest algorithm demonstrated the highest reliability, achieving an accuracy of 98% during training and 96% on the test set, while also identifying the most diagnostically relevant measurements. Unlike prior studies, our approach enables detailed comparison between model-selected features and clinically recognized diagnostic parameters. This interpretability provides a clinically meaningful bridge between AI-driven predictions and expert-based decision-making. The results suggest that machine learning models, particularly Random Forest, can effectively aid in the early detection of keratoconus in young individuals, potentially improving patient outcomes through timely intervention.

Teleophthalmology uses technology to provide remote eye care services, tackling obstacles in accessing specialized care. Optical coherence tomography (OCT) represents a technical advancement, enabling high-resolution ocular imaging. The aim of this study is to evaluate the diagnostic accuracy, feasibility, safety, and clinical utility of home monitoring OCT devices and remote OCT technology compared to standard in-office OCT in teleophthalmology settings across various eye conditions. A systematic literature search was conducted in PubMed, Cochrane Library, ScienceDirect and Google Scholar for studies on home-monitoring/remote OCT published from January 2004 to February 2024. Studies utilizing home monitoring/remote OCT in teleophthalmology for patients with eye disorders and reporting on diagnostic accuracy, safety, disease monitoring (clinical utility) or treatment response were included and synthesized narratively. A total of 12 research studies involving 3,539 participants were incorporated in the analysis. The majority of home or remote OCT scans exhibited satisfactory diagnostic image quality. There was high agreement between home/remote and in-office OCT for detecting pathologies and measuring retinal thickness. Compared to in-person evaluations, home/remote OCT demonstrated excellent sensitivity and specificity, though some variability was seen across conditions and interpreters. Home OCT devices provided feasible and safe self-operation with high patient acceptability. Scan times were faster when conducted at home compared to those in the office. Home/remote OCT devices can effectively provide diagnostic-grade retinal imaging outside traditional settings. High diagnostic accuracy was demonstrated compared to in-office OCT. Feasibility and patient acceptability data support home OCT for remote monitoring.

Though several procedures of IOL implantation have been described (sutured scleral fixation, intra-scleral fixation, angle-supported anterior chamber, and anterior chamber or retropupillary iris-claw IOLs), there are no randomized trials which are comparing different techniques. Hence, the surgical treatment of aphakia still remains controversial and challenging. The purpose of this study was to compare the long-term efficacy and the rate of complications of anterior versus posterior Iris-claw intraocular lenses (IOL) implantation to correct for the treatment of aphakia without sufficient capsule support. Consecutive eyes having secondary implantation of aphakic iris-fixated IOLs with a follow-up of at least 5 years were considered. Mean correct distance visual acuity (CDVA) changes, percentage of eyes with CDVA improvement, mean corneal endothelial cell density (CECD) loss and the rate of other complications were used for statistical analysis. The study evaluated a total of 180 eyes (Group A: 87 anterior chamber iris-claw fixation, Group B: 93 retropupillary iris-claw implantation) of 180 consecutive different patients, with aphakia of various reasons. CDVA improved significantly in both groups after surgery (P<0.001, ANOVA), and was remarkably higher than baseline in both groups from first week and during the entire follow-up (P<0.001, Tukey's Honest Significant Difference). There was no statistically significant difference in CDVA between the two groups during each follow-up visits (P = NS, unpaired t-test) and in the CDVA improvement percentage between the two groups (P = 0.882, Chi-square test). No significant changes in CECD were noted after surgery in both groups (ANOVA Group A: P = 0.067, Group B: P = 0.330P). No intra-operative complications occurred in both groups. There was no statistically significant difference in the rate of complications between the two groups (P = NS, Chi-square test), except for pigment precipitates which were higher in Group A (P<0.05, Chi-square test). Five-year follow-up shows that secondary implantation of aphakic IOLs is effective and safe for the correction treatment of aphakia in eyes without capsule support.

Retinal diseases recognition is still a challenging task. Many deep learning classification methods and their modifications have been developed for medical imaging. Recently, Vision Transformers (ViT) have been applied for classification of retinal diseases with great success. Therefore, in this study a novel method was proposed, the Residual Self-Attention Vision Transformer (RS-A ViT), for automatic detection of acquired vitelliform lesions (AVL), macular drusen as well as distinguishing them from healthy cases. The Residual Self-Attention module instead of Self-Attention was applied in order to improve model’s performance. The new tool outperforms the classical deep learning methods, like EfficientNet, InceptionV3, ResNet50 and VGG16. The RS-A ViT method also exceeds the ViT algorithm, reaching 96.62%. For the purpose of this research a new dataset was created that combines AVL data gathered from two research centers and drusen as well as normal cases from the OCT dataset. The augmentation methods were applied in order to enlarge the samples. The Grad-CAM interpretability method indicated that this model analyses the appropriate areas in optical coherence tomography images in order to detect retinal diseases. The results proved that the presented RS-A ViT model has a great potential in classification retinal disorders with high accuracy and thus may be applied as a supportive tool for ophthalmologists.

Purpose To evaluate and compare the visual outcomes of an enhanced monofocal intraocular lens (IOL) with two different monofocal IOLs. Setting Eye Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, Trieste, Italy. Design Prospective, single-center, single-masked, randomized controlled clinical study. Methods The study included patients undergoing phacoemulsification and IOL implantation. Patients were consecutively randomized by block randomization and assigned in a 1:1:1 allocation ratio to three study arms to bilaterally receive Tecnis Eyhance™ (model ICB00) or Tecnis ® monofocal 1-piece (model PCB00) or Clareon ® monofocal (model CNA0T0), respectively. Monocular and binocular (both corrected and uncorrected) visual acuities for far, intermediate and near were registered and compared among groups at 3 months. To track changes in patient quality of life, the Catquest-9SF questionnaire was administered to each patient before and after cataract extraction. Results Ninety patients (30 for each group) were enrolled. At 3 months follow-up, statistically significant differences for intermediate visual acuities were found between the three groups. Nonstatistically significant differences were observed for distance visual acuities and the changes in Catquest-9SF scores. Conclusion Tecnis Eyhance™ provided better results in intermediate visual outcomes without adverse effects on patients’ quality of life.

The main aim of this study is to evaluate the effects of painful muscle form of temporomandibular disorders and myopia on the connections between the visual organ, the bioelectrical activity and sensitivity of the masticatory and cervical muscles, and sleep quality. Subjects were divided into 4 groups (Myopia & TMDs, Myopia (Without TMDs), Emmetropic & TMDs and Emmetropic (Without TMDs)). The study was conducted in the following order of assessment: examination for temporomandibular disorders, assessment of the muscle activity by electromyograph, pressure pain thresholds examination, ophthalmic examination and completion of the Pittsburgh Sleep Quality Index. It was observed that the Myopia & TMDs group had higher muscle tenderness, higher resting and lower functional muscle bioelectrical activity. The visual organ is clinical related to the masticatory and cervical muscles. TMDs and myopia alter masticatory and cervical muscle activity. The thickness of the choroid in people with myopia is related to muscle tenderness. TMDs and myopia impair sleep quality. It is recommended to determine the number of people with refractive error and its magnitude in the sEMG study in order to be able to replicate the research methodology.

Background This study aimed to evaluate the impact of introducing faricimab into a publicly funded drug programme for retinal diseases, focusing particularly on reducing treatment frequency and optimising resources. Faricimab, a bispecific antibody targeting angiopoietin-2 and VEGF-A, offers a dual mechanism for managing nAMD and DME, both leading causes of vision loss. Methods The analysis included forecasting patient treatment trends, estimating the potential market share of faricimab, and simulating drug administration frequencies. A Monte Carlo simulation was conducted to model the impact of faricimab on reducing injection frequency. Scenarios with variable patient numbers and administration rates were explored, covering the years 2025, 2030, and 2035, to assess potential efficiencies in healthcare resources use and the capacity to treat additional patients. Results Results indicated that faricimab could reduce injection frequency by approximately 15%, freeing up resources within the healthcare system. Under the primary scenario, faricimab introduction could enable an additional 2,115 patients to be treated in 2025, rising to 7,662 by 2035 without additional resources. In the minimum scenario, the capacity increased by 4,415 patients by 2035, while the maximum scenario saw an increase of 12,003 patients. Conclusions The introduction of faricimab is expected to improve access to ophthalmic treatments, especially within the drug programme for retinal diseases, by decreasing injection frequency and enhancing resource efficiency. Given Poland’s ageing population and the rising prevalence of nAMD and DME, faricimab adoption could alleviate pressures on healthcare infrastructure, ultimately supporting better patient outcomes and overcoming current limitations in access to ophthalmic services.

Background: Active vitreous seeds in eyes with retinoblastoma (Rb) adversely affects the treatment outcome. This study aimed to investigate the safety and efficacy of intravitreal melphalan chemotherapy (IViC) as a treatment for recurrent and refractory vitreous seeds in patients with Rb. Methods: We used a retrospective non-comparative study of patients with intraocular Rb who had vitreous seeds and were treated by IViC (20–30 μg of melphalan) using the safety-enhanced anti-reflux technique. Tumor response, ocular toxicity, demographics, clinical features, and survival were analyzed. Results: In total, 27 eyes were treated with 108 injections for recurrent (16 eyes) or refractory (11 eyes) vitreous seeds after failed systemic chemotherapy. A total of 15 (56%) were males, and 20 (74%) had bilateral disease. At diagnosis, the majority ( n = 21) of the injected eyes were group D, and n = 6 were group C. Vitreous seeds showed complete regression in 21 (78%) eyes; 100% ( n = 10) for eyes with focal seeds; 65% ( n = 11/17 eyes) for eyes with diffuse seeds ( p = 0.04); 7 (64%) eyes with refractory seeds; and 14 (87%) eyes with recurrent seeds showed complete response ( p = 0.37). In total, 16 (59%) eyes developed side effects: retinal toxicity (48%), pupillary synechiae (15%), cataracts (30%), iris atrophy (7%), and retinal and optic atrophy (4%). Only one child was lost to follow-up whose family refused enucleation and none developed orbital tumor recurrence or distant metastasis. Conclusion: IViC with melphalan is effective (more for focal than diffuse seeding) and a relatively safe treatment modality for Rb that can improve the outcomes of eye salvage procedures. However, unexpected toxicity can occur even with the standard dose of 20–30 μg.

Retinitis Pigmentosa (RP) is a rare genetic retinal disorder characterized by the progressive degeneration of rod and cone photoreceptors, leading to vision impairment and eventual blindness. This study investigates the application of state-of-the-art convolutional neural networks (CNNs) and aggregation methods related to Ordered Weighted Averaging Operators (OWA) to classify RP with enhanced accuracy. Using pre-trained CNN architectures such as EfficientNet, ResNet, and DenseNet, individual classifiers were evaluated, among which EfficientNet achieved the highest performance. To improve these results, aggregation methods, including classic Ordered Weighted Averaging (OWA) operators and the novel Smooth OWA operators, were employed. The aggregation process significantly boosted classification accuracy, with the OWA operator variants achieving approximately 25 percentage point improvement over the best-performing individual classifier. The best results were obtained using Smooth OWA operators inspired by Newton-Cotes quadratures, achieving a consistent additional improvement over the base OWA operator. This study demonstrates the effectiveness of combining advanced CNN models with aggregation techniques for improving classification accuracy on small and imbalanced datasets. The results highlight the potential of Smooth OWA operators in enhancing the robustness and performance of machine learning models in medical diagnosis tasks.