Coronavirus disease 2019 (COVID-19) is an ongoing global public health problem, and most of the COVID-19 research is focused mainly on the respiratory system because of life-threatening results. However, manifestations in other organs should not be ignored since they can also be a mode of transmission. Researchers sought to describe the ocular manifestations of COVID-19, and investigate the association between ocular involvement and clinical presentation and laboratory outcomes. This cross-sectional study was conducted between March 1, 2020, and April 30, 2020. Ninety-three sequentially hospitalized and clinically confirmed COVID-19 patients were included in the study. The systemic and ocular symptoms, clinical findings and laboratory outcomes were recorded.

Of the 93 COVID-19 patients, 54 (58.1%) were male, and 39 (41.9%) were female. Mean age of the patients was 39.4 ± 21.9 (min 7, max 88) years. Twenty patients (n=21.5%) had at least one ocular abnormality. Most common findings included hyperemia (n=20), epiphora (n=9), increased secretion (n=6), chemosis (n=3), follicular conjunctivitis (n=2), and episcleritis (n=2). The most common symptom was photophobia (n=15). Patients with ocular involvement were more likely to have higher neutrophil counts, and increased CRP, PCT and ESR levels. Mean lymphocyte count was statistically lower in patients with ocular manifestations. Mean age and number of patients with fever over 37.3 °C in the ocular involvement group was found to be higher.

Older age, high fever, increased neutrophil/lymphocyte ratio and high levels of acute phase reactants seemed to be risk factors for ocular involvement.

Glaucoma is the most frequent cause of irreversible blindness worldwide. There is no cure, but early detection and treatment can slow the progression and prevent loss of vision. It has been suggested that artificial intelligence (AI) has potential application for detection and management of glaucoma. This literature review was based on articles published in peer-reviewed journals.

There have been significant advances in both AI and imaging techniques that are able to identify the early signs of glaucomatous damage. Machine and deep learning algorithms show capabilities equivalent, if not superior, to human experts. Concerns exist that the increased reliance on AI may lead to deskilling of clinicians. AI has potential to be used in virtual review clinics, telemedicine and as a training tool for junior doctors. Unsupervised AI techniques offer the potential of uncovering currently unrecognized patterns of disease. If this promise is fulfilled, AI may then be of use in challenging cases or where a second opinion is desirable.

There is a need to determine the external validity of deep learning algorithms and to better understand how the 'black box' paradigm reaches results.

Investigators quantitatively assessed anterior chamber angle (ACA) structure by anterior segment optical coherence tomography (AS-OCT) and developed a model to evaluate angle width as defined by gonioscopy. They evaluated the ACAs of each quadrant by gonioscopy, classified by the Scheie grading system, and assigned the angles into one of the three grades: small angle (SA), moderate angle (MA) and large angle (LA). The eyes were imaged by AS-OCT, and ACA structural parameters—including angle opening distance at the scleral spur (AODSS) and at 750 μm anterior to the scleral spur (AOD750), trabecular-iris space area at 750 μm anterior to the scleral spur (TISA750) and a newly defined parameter "light intersection distance" (LID)—were measured. The ACA structural data were used to construct an ordered logistic regression model for assignment of ACAs to one of the three angle grades. The validity of the model was then tested.

A total of 169 quadrants from 53 subjects were included in the analysis, of which 111 quadrants were included in the modeling data and 58 in the testing data. In pairwise comparisons of SA, MA and LA by ANOVA, the measured parameters were as follows: AOD750 (0.174 ± 0.060 vs. 0.249 ± 0.068 vs. 0.376 ± 0.114mm), TISA750 (0.075 ± 0.035 vs. 0.117 ± 0.036 vs. 0.181 ± 0.062mm²), and LID (- 0.300 ± 0.187 vs. -0.085 ± 0.170 vs. 0.122 ± 0.156mm). The ACA grading model based on LID showed a relatively high correction rate of 72.4%, and the model efficiency—calculated using the receiver operating characteristic—showed an area under the curve of 0.740. Weighted kappa statistics showed a good agreement for multiple ACA grades (0.772).

The AS-OCT-based multiple ACA grades model was demonstrated as a non-contact approach for ACA assessment with high speed and high spatial resolution, providing guidance for diagnosis of angle closure.