TransFair: Transferring fairness from ocular disease classification to progression prediction.

N6-methyladenosine (m6A), a pivotal RNA modification, has garnered considerable attention in cell biology and disease research. m6A plays a critical role in the regulation of gene expression, cell proliferation, differentiation, and apoptosis, with particular relevance to the onset and progression of ocular diseases. This review examines the current research on m6A in ocular diseases, including keratitis, cataracts, glaucoma, retinopathy, thyroid ophthalmopathy, and ocular tumors, highlighting its functional significance and potential mechanisms in these conditions. Recent studies suggest that m6A modification influences cellular fate and pathophysiological processes by modulating the expression of key genes. However, a deeper understanding of the precise mechanisms underlying m6A action in ocular diseases is still needed. By synthesizing the existing literature, this review seeks to offer novel insights and identify potential therapeutic targets, thereby advancing clinical applications for ocular disease treatment.

An automated system for detecting ocular diseases with computer-aided tools is essential to identify different eye disorders through fundus pictures. This is because diagnosing ocular illnesses manually is a complicated, time-consuming, and error-prone process. In this research, two multi-label embedded architectures based on a deep learning strategy were proposed for ocular disease recognition and classification. The ODIR (Ocular Disease Intelligent Recognition) dataset was adopted for those models. The suggested designs were implemented as parallel systems. The first model was developed as a parallel embedded system that leverages transfer learning to implement its classifiers. The implementation of these classifiers utilized the deep learning network from VGG16, while the second model was introduced with a parallel architecture, and its classifiers were implemented based on newly proposed deep learning networks. These networks were notable for their small size, limited layers, speedy response, and accurate performance. Therefore, the new proposed design has several benefits, like a small classification network size (20 % of VGG16), enhanced speed, and reduced energy consumption, as well as the suitability for IoT applications that support smart systems like Raspberry Pi and Self-powered components, which possess the ability to function as long as a charged battery is available. The highest accuracy of 0.9974 and 0.96 has been obtained in both proposed models for Myopia ocular disease detection and classification. Compared to research that had been presented in the same field, the performance accuracy of each of the two models shown was high. The P3448-0000 Jetson Nano Developer Kit is used to implement both of the proposed embedded models

Bartonella: a new etiological agent of feline ocular disease.

To describe the clinical presentation, treatment, and clinical outcome of horses with ocular disease and evidence of systemic or ocular Lyme disease. Five horses met the inclusion criteria of ocular disease with evidence of Bburgdorferi present in ocular or CNS tissues. The goal of this study was to describe the clinical presentation and progression of ocular disease when associated with ocular or CNS Bburgdorferi infection in horses. A retrospective review of medical records was performed on horses admitted for ocular disease with evidence of Bburgdorferi infection between 1998 and 2015. The diagnosis of Bburgdorferi-associated uveitis was based on histopathologic lesions of lymphohistiocytic and suppurative uveitis/endophthalmitis and intralesional argyrophilic spirochetes in either ocular or CNS tissue consistent with Borrelia. Leptospiral uveitis was ruled out by PCR. All five horses in the current study had intraocular inflammation at the time of presentation. Medical management with anti-inflammatories was successful in controlling uveitis in the two horses in which treatment of uveitis was attempted. Systemic treatment with oral tetracyclines was unsuccessful in a single case in which treatment of Borrelia was attempted. Four horses were euthanized due to progression of neurologic disease. The surviving horse had an enucleation performed and did not show systemic signs. Infection with Borrelia burgdorferi should be considered in endemic areas as a differential for horses with ocular disease, in particular, uveitis. The prognosis for uveitis and neurologic disease associated with Lyme disease was poor in the current study.

The early prediction of ocular disease is certainly an obligatory concern in the domain of ophthalmic medicine. Although modern scientific discoveries have shown the potential to treat eye diseases by using artificial intelligence (AI) and machine learning, explainable AI remains a crucial challenge confronting this area of research. Although some traditional methods put in significant effort, they cannot accurately predict the proper ocular diseases. However, incorporating AI into diagnosing eye diseases in healthcare complicates the situation as the decision-making process of AI demonstrates complexity, which is a significant concern, especially in major sectors like ocular disease prediction. The lack of transparency in the AI models may hinder the confidence and trust of the doctors and the patients, as well as their perception of the AI and its abilities. Accordingly, explainable AI is significant in ensuring trust in the technology, enhancing clinical decision-making ability, and deploying ocular disease detection. This research proposed an efficient transfer learning model for eye disease prediction to transform smart vision potential in the healthcare sector and meet conventional approaches’ challenges while integrating explainable artificial intelligence (XAI). The integration of XAI in the proposed model ensures the transparency of the decision-making process through the comprehensive provision of rationale. This proposed model provides promising results with 95.74% accuracy and explains the transformative potential of XAI in advancing ocular healthcare. This significant milestone underscores the effectiveness of the proposed model in accurately determining various types of ocular disease. It is clearly shown that the proposed model is performing better than the previously published methods.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) viruses is mainly transmitted through respiratory droplets. Notably, some coronavirus disease 2019 (COVID-19) patients have ocular manifestations, including conjunctival hyperaemia, chemosis, epiphora, and increased secretions. However, the association between SARS-CoV-2 and ocular surface diseases is poorly described. Between May 2020 and March 2021, a total of 2, 0157 participants from six districts of China were enrolled. Serum samples were tested for immunoglobulin G and M (IgG and IgM) antibodies against the SARS-CoV-2 spike protein and nucleoprotein using magnetic chemiluminescence enzyme immunoassays. Throat swabs were tested for SARS-CoV-2 RNA using RT-PCR assays in a designated virology laboratory. Fisher exact, χ2 test, and logistic regression analysis were performed. Of 2, 0157 serum samples tested, 1, 755 (8.71%) were from ocular surface diseases, 1, 2550 (62.26%) from no-ocular surface diseases (ocular diseases except ocular surface diseases), 5, 852 (29.03%) from no-ocular diseases. SARS-CoV-2 prevalence for the combined measure was 0.90% (182/2, 0157). Seroprevalence of SARS-CoV-2 was significantly (p<0.05) higher in the population with ocular surface diseases (2.28%, 40/1755) compared with no-ocular surface diseases (0.70%, 88/1, 2550), and no-ocular diseases (0.92%, 54/5, 852). Similar results were also observed with respect to sex, age, time, and districts. Logistic regression analyses revealed that ocular surface diseases [ocular surface diseases vs. no-ocular diseases (p=0.001, OR =1.467, 95% CI=1.174-1.834); ocular surface diseases vs. no-ocular surface diseases (p<0.001, OR =2.170, 95% CI=1.434-3.284)] were associated with increased risk of susceptible to SARS-CoV-2 infection. In a word, there was a significant association between ocular surface disease and SARS-CoV-2 infection. Therefore, increasing awareness of eye protection during the pandemic is necessary, especially for individuals with ocular surface diseases.

Most genomic prediction models are linear regression models that assume continuous and normally distributed phenotypes, but responses to diseases such as stripe rust (caused by Puccinia striiformis f. sp. tritici) are commonly recorded in ordinal scales and percentages. Disease severity (SEV) and infection type (IT) data in germplasm screening nurseries generally do not follow these assumptions. On this regard, researchers may ignore the lack of normality, transform the phenotypes, use generalized linear models, or use supervised learning algorithms and classification models with no restriction on the distribution of response variables, which are less sensitive when modeling ordinal scores. The goal of this research was to compare classification and regression genomic selection models for skewed phenotypes using stripe rust SEV and IT in winter wheat. We extensively compared both regression and classification prediction models using two training populations composed of breeding lines phenotyped in 4 years (2016–2018 and 2020) and a diversity panel phenotyped in 4 years (2013–2016). The prediction models used 19,861 genotyping-by-sequencing single-nucleotide polymorphism markers. Overall, square root transformed phenotypes using ridge regression best linear unbiased prediction and support vector machine regression models displayed the highest combination of accuracy and relative efficiency across the regression and classification models. Furthermore, a classification system based on support vector machine and ordinal Bayesian models with a 2-Class scale for SEV reached the highest class accuracy of 0.99. This study showed that breeders can use linear and non-parametric regression models within their own breeding lines over combined years to accurately predict skewed phenotypes.

Ocular Neovascularization: Clarifying Complex Interactions

Interpretable diagnostic system for multiocular diseases based on hybrid meta-heuristic feature selection

Eye disease has evolved into a global health issue and has become widespread. Nowadays, ocular diseases spread all over the world and cause dangerous effects in humans. A wide range of eye diseases can significantly affect visual clarity, which can lead to permanent vision loss. Among these, glaucoma affects the optic nerve due to the increased eye pressure, often leading to vision loss. Thus, it requires an effective strategy that includes healthcare providers, public health officials and community education to prevent these diseases. One of the most effective measures for reducing the consequences of ocular disease among the population is periodic check-ups and early recognition of particular diseases. By extracting enriched features in the fundus and ocular computed tomography images, the multiple layers in the deep learning architectures help in accurate image classification and segmentation of specific areas in images. In this research, ocular disease detection with a severity classification model is proposed to prevent early vision loss. The process is started by gathering input images needed for the detection task. Then, the segmentation process is done on the input images using the developed Trans-EfficientUnet[Formula: see text] (TEUNet[Formula: see text] model. This segmentation process is helpful for faster analysis of the affected regions. Then, the ocular disease classification into the normal case and abnormal case will be performed via Adaptive and Region Attention-based Pyramid Dilated EfficientNetB7 (ARA-PDEB7). Here, an Enhanced Magnificent Frigatebird Optimization with Random Number Amendment (EMFO-RNA) was introduced for optimizing the performance of the classification model to obtain accurate outcomes. If the disease is detected, then severity assessments are done to take appropriate treatments. The features in segmented images are retrieved using the Pyramid Dilated EfficientNetB7 (PDEB7). The ocular disease classification performance of the presented model was analyzed among existing models to verify its efficiency.

Chronic kidney disease (CKD) and ocular disease share several cardiovascular risk factors as well as pathogenetic mechanisms having Renin-Angiotensin-Aldosterone System (RAAS) as main actor. Moreover, kidney and eyes have common genetic and embryonic origin. In this literature review, we present main evidence supporting this association for early identifying diseases affecting both systems and evaluating potential multi-target therapeutic strategies. We performed a literature review of the current peer-reviewed English-language randomized controlled studies (RCTs), reference lists of nephrology or ophthalmology textbooks, review articles and relevant studies with ocular or eye and kidney or renal diseases as keywords until March 2020. Prospective and retrospective studies as well as meta-analyses and latest systematic reviews were included. We evaluated a total of 683 records, finally selecting 119 articles related to ocular and renal diseases. Records were divided into two areas: chronic and acute kidney disease and ocular or eye diseases. Some of the examined studies were discarded for population biases/intervention or deemed unfit. Based on our results, we conclude that there is evidence of a clear association between kidney and eye diseases, being this cross-link mainly based on RAAS dysregulation. Our review suggests that it may be useful to screen CKD patients for associated ocular diseases, such as cataract, glaucoma, diabetic retinopathy and age-related macular degeneration. A comprehensive study of CKD and proteinuric patients should include careful eye examination. Renal impairment in young patients should prompt a search for ocular disease, such as TUNA syndrome or oculo-renal syndrome, in particular if family history of concurrent ocular and renal disease is present. Anti-RAAS agents are mostly recommended in patients with renal and ocular impairment.

Vision is our most precious sense, and numerous ocular diseases, including age‐related macular degeneration, glaucoma and diabetic retinopthay, are responsible for visual impairment and blindness in hundreds of millions of individuals worldwide. In the past several years, a number of advances have been made to better understand ocular biology and diseases. Research in ocular proteomics of ocular tissues and cells such as the trabecular meshwork, retina, optic nerve head, retinal pigment epithelium, cornea, lens, sclera, tears, aqueous humour and vitreous humour, has allowed the identification of eye proteins and protein modifications that are involved in ocular development, ageing and disease. This provides an important foundation for better understanding ocular biology and disease pathogenesis. Key Concepts: The eye is a unique sensory organ. A wide variety of proteomics techniques are being used to identify proteins and protein modifications that are involved in ocular development, ageing and a wide variety of ocular diseases. Eye proteomics can be very challenging due to the very limited quantity of ocular tissues and fluids available for analysis. Posttranslational protein modifications are commonly associated with a variety of ocular diseases, including glaucoma, macular degeneration and cataracts. Serum proteomics is being used to examine systemic effects of specific ocular diseases.

Multi-label ocular disease classification with a dense correlation deep neural network

Artificial intelligence (AI) classification holds promise as a novel and affordable screening tool for clinical management of ocular diseases. Rural and underserved areas, which suffer from lack of access to experienced ophthalmologists may particularly benefit from this technology. Quantitative optical coherence tomography angiography (OCTA) imaging provides excellent capability to identify subtle vascular distortions, which are useful for classifying retinovascular diseases. However, application of AI for differentiation and classification of multiple eye diseases is not yet established. In this study, we demonstrate supervised machine learning based multi-task OCTA classification. We sought (1) to differentiate normal from diseased ocular conditions, (2) to differentiate different ocular disease conditions from each other, and (3) to stage the severity of each ocular condition. Quantitative OCTA features, including blood vessel tortuosity (BVT), blood vascular caliber (BVC), vessel perimeter index (VPI), blood vessel density (BVD), foveal avascular zone (FAZ) area (FAZ-A), and FAZ contour irregularity (FAZ-CI) were fully automatically extracted from the OCTA images. A stepwise backward elimination approach was employed to identify sensitive OCTA features and optimal-feature-combinations for the multi-task classification. For proof-of-concept demonstration, diabetic retinopathy (DR) and sickle cell retinopathy (SCR) were used to validate the supervised machine leaning classifier. The presented AI classification methodology is applicable and can be readily extended to other ocular diseases, holding promise to enable a mass-screening platform for clinical deployment and telemedicine.

The eyes are our windows to the world. Major ocular diseases, including cataracts, glaucoma, age-related macular degeneration (AMD), diabetic retinopathy (DR), dry eye syndrome and allergic conjunctivitis, can cause vision impairment and even blindness, which not only affect our daily life, but also have a significant socio-economic and psychological impact on our society. The prevalence of vision impairment was estimated to be 147 million people in 2010, and is projected to reach 191 million in the word in 2020 due to an increase in aging populations. The market for ophthalmic disease therapeutics is expected to reach $18.7 billion this year, and is predicted to grow steadily. Ophthalmic drug development has been in the forefront of therapeutic research partly because the eye is an accessible and immunologically isolated organ, which has the advantage of avoiding the complications of systemic drug delivery. With the recent advances in genetics, genomics and stem cell biology, the mechanisms of many ophthalmic diseases are being increasingly revealed. Accordingly, the field of ophthalmic therapeutics is facing unprecedented challenges and opportunities. Looking back in history, ophthalmic drug development has been driven by the scientific breakthroughs. For example, the discovery that vascular endothelial growth factor (VEGF) is a driving force of choroidal neovascularization in AMD has led to the successful development of anti-VEGF antibodies for wet AMD therapy. The discovery that prostaglandin mediates reduction in intraocular pressure (IOP) has led to the treatment of ocular hypertension in glaucoma using prostaglandin analogues. Research over the past decade has uncovered novel mechanisms for many ocular diseases, which will likely spawn new therapeutic solutions. But this field is not without challenges: (A) currently there is no cure for many ocular diseases, including dry AMD, DR and glaucoma; (B) current ophthalmic drug development is not based on the unique characteristics of ocular diseases, but mainly applies agents developed for non-ocular diseases to the eye; (C) most of the ocular diseases are multi-factorial diseases with both genetic and environmental (nutritional) risk factors, therefore many drugs only work for a subset of patients. For example, cyclosporine, acting as an immune-modulator for dry-eye disease, is only effective in about 15% of all patients; (D) ophthalmic drug delivery, especially to the posterior eye, remains a considerable challenge. These challenges present unique opportunities for researchers in the field of ophthalmology to further elucidate the mechanisms of and develop innovative therapeutics and delivery approaches for ocular diseases. Despite the challenges, significant progress has recently been made towards understanding the mechanisms of several ocular diseases, which may translate into future therapeutics. Dry AMD accounts for up to 90% of the AMD cases and is currently without cure. Polymorphisms in members of the complement system, especially complement factor H (CFH), have been associated with AMD. Moreover, CFH was recently shown to protect against oxidative stress-induced inflammation in animal model. Inhibitors of the complement system and the recombinant form of CFH are being tested preclinically for AMD treatment. Aβ amyloid, originally implicated in Alzheimer’s disease, was recently associated with pathogenesis of AMD. Anti-Aβ amyloid antibody has shown promise in animal models of AMD. Autophagy is currently being investigated for AMD involvement, and may represent a potential therapeutics for AMD (See review in this issue). Diabetic retinopathy is one of the leading causes of blindness in the working class. Besides laser photocoagulation and vitrectomy surgery, several therapeutic options, including protein kinase inhibitors, cyclooxygenase inhibitors, anti-VEGF and slow release steroid, are on clinical trials. Some of them may enter the market in the near future. As reviewed in this issue, pericytes and the angiopoietin (Ang)-Tie-2 signaling also play an important role in the development of DR, and may be potential therapeutic targets for DR. For glaucoma, the current mainstay for treatment is to lower IOP, therefore preventing further damage to the optic nerve. β-blocker, prostaglandin, carbonic anhydrase inhibitor, miotics, α-adrenergic agonist, or their combinations are routinely used for lowering IOP. Rho kinase inhibitors and actin depolymerization agents are currently tested in clinical trials for safely reducing IOP. Dominant mutations in the olfactomedin (OLF) domain of myocilin have been associated with several populations of familial glaucoma, and molecular studies suggest that the OLF domain of myocilin may be a bona fide target for future glaucoma therapeutics (reviewed in this issue). Looking into future, the explosion in basic research in ocular biology and disease will lead to revolutionarily innovative ophthalmic therapeutics. Numerous opportunities also present themselves to researchers working on medicinal chemistry, new biomaterials, and new delivery system (see reviews for these subjects in the issue). With the coordinated effort of all these groups, the future of ophthalmic therapeutics is bright.