BACKGROUND: Applications for artificial intelligence (AI) in ophthalmology are continually evolving. Fundoscopy is one of the oldest ocular imaging techniques but remains a mainstay in posterior segment imaging due to its prevalence, ease of use, and ongoing technological advancement. AI has been leveraged for fundoscopy to accomplish core tasks including segmentation, classification, and prediction.
METHODS: In this article we provide a review of AI in fundoscopy applied to representative chorioretinal pathologies, including diabetic retinopathy and age-related macular degeneration, among others. We conclude with a discussion of future directions and current limitations.
CONCLUSIONS: As AI evolves, it will become increasingly essential for the modern ophthalmologist to understand its applications and limitations to improve patient outcomes and continue to innovate.

UNASSIGNED: Traditional direct ophthalmoscopy (TDO) is the oldest method of fundus examination; however, it has fallen out of use due to its technical difficulty and limitations to clinical utility, amidst the advent of potentially better options. A spectrum of new technologies may help in addressing the shortcomings of TDO: simulation mannequins with non-tracked TDO, simulation models with tracked TDO, and smartphone ophthalmoscopy (SFO).
UNASSIGNED: A systematic search of PubMed, Embase, and Cochrane databases for all studies evaluating usage of simulation mannequins/models and SFO in ophthalmology education was performed, from inception till April 2023 with no language restriction. We ensured that we included all possible relevant articles by performing backward reference searching of included articles and published review articles.
UNASSIGNED: We reviewed studies on non-tracked TDO (n = 5), tracked TDO (n = 3) and SFO (n = 12). Non-tracked TDO and SFO were superior in training competency relative to control (TDO on real eyes). Intriguingly, tracked TDO was non superior to controls. SFO appears to enhance the learning effectiveness of ophthalmoscopy, due to real-time projection of the retina view, permitting instantaneous and targeted feedback. Learners reported improved ergonomics, including a wider field of view and more comfortable viewing distance. Retention of images and recordings permitted the audit of learning and paves the way for storage of such images in patients\' electronic medical record and rapid dissemination for specialist referral.
UNASSIGNED: Smartphone ophthalmoscopy (SFO) permits integration of both the practice and learning of ophthalmoscopy, and the auditing of both. These advantages over traditional methods (with simulation or otherwise) may lead to a paradigm shift in undergraduate ophthalmology education. However, the nascency of SFO necessitates preservation of traditional techniques to tide through this period of transition.

UNASSIGNED: Recent advances in telemedicine have led to increased use of digital ophthalmoscopes (DO) in clinical settings. This review aims to assess commercially available DOs, including smartphone (SP), desktop, and handheld ophthalmoscopes, and evaluate their applications.
UNASSIGNED: A literature review was performed by searching PubMed (pubmed.ncbi.nlm.nih.gov), Web of Science (webofknowledge.com), and Science Direct (sciencedirect.com). All English-language papers that resulted from the search terms \"digital ophthalmoscope\", \"screening tool\", \"glaucoma screening\", \"diabetic retinopathy screening\", \"cataract screening\", and \"papilledema screening\" were reviewed. Studies that contained randomized clinical trials with human participants between January 2010 and December 2020 were included. The Risk of Bias in Systematic Reviews (ROBIS) tool was used to assess the methodological quality of each included paper.
UNASSIGNED: Of the 1307 studies identified, 35 met inclusion and exclusion criteria. The ROBIS tool determined that 29/35 studies (82.8%) had a low risk of bias, 3/35 (8.5%) had a moderate risk of bias, and 3/35 (8.5%) had a high risk of bias.
UNASSIGNED: The continued adoption of DOs remains uncertain because of concerns about the image quality for non-mydriatic eyes and the confidence in data captured from the device. Likewise, there is a lack of guidelines for the use of DOs, which makes it difficult for providers to determine the best device for their practice and to ensure appropriate use. Even so, DOs continue to gain acceptance as technology and practice integration improve, especially in underserved areas with limited access to ophthalmologists.

This review will provide a better understanding of a set of signs known as malarial retinopathy. The discovery of this retinopathy in association with cerebral malaria is important because it best distinguishes patients with true cerebral malaria from those with coma due to other causes and incidental Plasmodium falciparum parasitemia. Identifying a comatose patient with malarial retinopathy increases the likelihood of an accurate severe or cerebral malaria diagnosis. As the World Health Organization does not specify that malarial retinopathy is one of the factors included in determining a cerebral malaria diagnosis, there are significant false-positive diagnoses of cerebral malaria. Once a cerebral malaria diagnosis is assigned, other possibilities and treatments are often excluded making an incorrect diagnosis of cerebral malaria potentially fatal. However, Plasmodium falciparum may also contribute to coma in some children with retinopathy-negative cerebral malaria, as this group is still not clinically well characterized, so all children with the WHO definition of cerebral malaria should be treated for severe malaria. Nevertheless, by raising awareness about malarial retinopathy, there could be a greater potential to accurately diagnose cerebral malaria and thus achieve more positive patient outcomes in the future. This literary review aims to raise awareness of the retinopathy by defining what it is to non-experts, explaining its pathology, clarifying the techniques needed to accurately diagnose malarial retinopathy, as well as the barriers that prevent clinicians from providing a proper diagnosis in malaria-endemic regions; and finally, discuss future directions to continue the study of malarial retinopathy.

Objectives: To present the clinical features of and diagnostic methods used for macular coloboma (MC), and to analyze the factors associated with best-corrected visual acuity (BCVA) in patients with MC.Methods: A systematic review using the MEDLINE (PubMed), EMBASE, LILACS, and Cochrane databases was performed. The factors associated with BCVA were analyzed.Results: A total of 21 patients (mean age at diagnosis, 18.1 ± 14.6 years) with 36 eyes affected by MC (5 unilateral, 16 bilateral) were included in the study. All 21 patients (100%) had undergone a good-quality fundus examination. The size of the MC lesions ranged from 1.0 × 1.2 to 4.0 × 4.0 disc diameters (DD). Twenty-seven (73%) eyes had pigmented MC, seven (19%) had non-pigmented MC, and one (3%) had an unspecific type. The diagnosis was confirmed using spectral-domain optical coherence tomography (SD-OCT) in 16 (43.2%) eyes. A positive correlation was found between BCVA and the type of MC (β = 0.876, p = .006) and abnormal eye movement (β = 0.087, p = .018), and a negative correlation was found between BCVA and a contributory medical history of ventricular septal defect (β = -0.327, p = .001).Conclusions: Pigmented MC was the most common type and had the highest possibility of causing impaired vision in the affected eyes. Additionally, joint examinations should be applied for diagnostic confirmation of MC. Furthermore, fundoscopy, electroretinogram, electrooculography, fundus fluorescein angiography, and SD-OCT are all critical for differential diagnosis of MC-like lesions.

Background and objective Coronavirus disease 2019 (COVID-19) is a viral infection that has grown to be a global pandemic, and it is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The ocular involvement in COVID-19, both in the anterior and posterior segments, is increasingly being recognized by ophthalmologists. We report the fundus photographic and systemic findings in 25 patients without recent-onset visual symptoms who were hospitalized with COVID-19. Methods Patients with COVID-19 infection who were admitted to an isolation ward/ICU in Mumbai, India during June-August 2020 underwent a comprehensive clinical and systemic evaluation. We performed a fundus evaluation using a handheld fundus camera during their admission period. We conducted a retrospective case record review and extracted demographic characteristics, laboratory findings, and fundus photographs from each case record. Results We screened 25 non-consecutive patients, and they included 20 (80%) men and five (20%) women, with ages ranging from 31 to 79 years (mean: 56.3 years). Systemically, the spectrum of severity on admission varied from mild to moderate to severely ill. The majority of the patients had no complaints of recent visual loss. An analysis of fundus photographs of 50 eyes of 25 patients revealed no evidence of fundus lesions in as many as 48 photographs. Two photographs of two eyes of patients showed incidental lesions. Conclusions We found no evidence of vascular, inflammatory, or thromboembolic disease that could be linked to COVID-19 infection in any of the images we studied; however, fundus examination may be utilized in patients with co-infection.

UNASSIGNED: Smartphone fundoscopy is a new option for visualizing the ocular fundus but must be validated before being included in population-based examinations. Our aim was to evaluate the quality of fundoscopic images obtained via smartphone and to compare their agreement with retinal camera images or clinical examination.
UNASSIGNED: The database for this study included all observational studies with smartphone fundoscopy that have comparative analyses with the gold standard methods.
UNASSIGNED: Out of 121 potentially relevant studies, nine were included in this analysis, comprising a total of 4,219 eyes. Mean age was 56.6 years (SD±8.5). Combined kappa (κ) agreement statistics were equal to 77.77% (95% CI: 70.34%, 83.70%). No heterogeneity was measured by random effects (I 2=zero).
UNASSIGNED: Fundoscopic images obtained by using smartphones have substantial agreement with gold standards for clinical or photographic exams.