Transparency in Artificial Intelligence Reporting in Ophthalmology-A Scoping Review.

Topic: This scoping review summarizes artificial intelligence (AI) reporting in ophthalmology literature in respect to model development and validation. We characterize the state of transparency in reporting of studies prospectively validating models for disease classification. Clinical Relevance: Understanding what elements authors currently describe regarding their AI models may aid in the future standardization of reporting. This review highlights the need for transparency to facilitate the critical appraisal of models prior to clinical implementation, to minimize bias and inappropriate use. Transparent reporting can improve effective and equitable use in clinical settings. Methods: Eligible articles (as of January 2022) from PubMed, Embase, Web of Science, and CINAHL were independently screened by 2 reviewers. All observational and clinical trial studies evaluating the performance of an AI model for disease classification of ophthalmic conditions were included. Studies were evaluated for reporting of parameters derived from reporting guidelines (CONSORT-AI, MI-CLAIM) and our previously published editorial on model cards. The reporting of these factors, which included basic model and dataset details (source, demographics), and prospective validation outcomes, were summarized. Results: Thirty-seven prospective validation studies were included in the scoping review. Eleven additional associated training and/or retrospective validation studies were included if this information could not be determined from the primary articles. These 37 studies validated 27 unique AI models; multiple studies evaluated the same algorithms (EyeArt, IDx-DR, and Medios AI). Details of model development were variably reported; 18 of 27 models described training dataset annotation and 10 of 27 studies reported training data distribution. Demographic information of training data was rarely reported; 7 of the 27 unique models reported age and gender and only 2 reported race and/or ethnicity. At the level of prospective clinical validation, age and gender of populations was more consistently reported (29 and 28 of 37 studies, respectively), but only 9 studies reported race and/or ethnicity data. Scope of use was difficult to discern for the majority of models. Fifteen studies did not state or imply primary users. Conclusion: Our scoping review demonstrates variable reporting of information related to both model development and validation. The intention of our study was not to assess the quality of the factors we examined, but to characterize what information is, and is not, regularly reported. Our results suggest the need for greater transparency in the reporting of information necessary to determine the appropriateness and fairness of these tools prior to clinical use. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Environmental influences on ophthalmic conditions: A scoping review.

BACKGROUND: Environmental factors have been implicated in various eye pathologies. The purpose of this review is to synthesise the published research on environmental effects on eye disease. METHODS: Four databases were searched for terms relating to environmental exposures and ophthalmic disease. Titles and abstracts were screened followed by full-text review. Data was extracted from 118 included studies. Quality assessment was conducted for each study. RESULTS: Air pollutants, including nitrogen dioxide, nitrites, sulphur dioxide, particulate matter, carbon monoxide, ozone and hydrocarbons are associated with ocular conditions ranging from corneal damage to various retinopathies, including central retinal artery occlusion. Certain chemicals and metals, such as cadmium, are associated with increased risk of age-related macular degeneration. Climate factors, such as sun exposure, have been associated with the development of cataracts. Living in rural areas was associated with various age-related eye diseases whereas people living in urban settings had higher risk for dry eye disease and uveitis. CONCLUSION: Environmental exposures in every domain are associated with various ophthalmic conditions. These findings underscore the importance of continued research on the interplay between the environment and eye health.

Ophthalmic imaging for the diagnosis and monitoring of glaucoma: A review.

The last three decades have been a turning point for early glaucoma diagnosis and monitoring by newly developed imaging techniques. Improvements in imaging of the anterior segment (AS), retinal nerve fibre layer (RNFL), optic nerve head (ONH), and macular ganglion cell complex (GCC) came into existence and broke new ground for early diagnosis and progression survey. This review will summarise the different ophthalmic imaging techniques, their principles, pros and cons, ongoing development processes, and the future of imaging methods. The aim is to provide the clinician with an understanding of the role of imaging methods and provide insight for appropriate use and evaluation of their outputs in glaucoma diagnosis and treatment.

A comprehensive enhanced depth imaging spectral-domain optical coherence tomography analysis of pseudoexfoliation spectrum from non-glaucomatous to advanced stage glaucoma in the aspect of Bruch's membrane opening-minimum rim width.

PURPOSE: To compare the correlations between lamina cribrosa (LC) and related structures with Bruch's membrane opening-minimum rim width (BMO-MRW) and retinal nerve fiber layer (RNFL) thickness in pseudoexfoliation syndrome (PXS) and different stages of pseudoexfoliation glaucoma (PXG). METHODS: This prospective cross-sectional study included 32 PXS eyes of 24 patients and 94 PXG eyes (early-stage (n: 55) and advanced-stage glaucoma (n: 39) of 78 patients. Global and six sectors of RNFL thicknesses and BMO-MRW parameters were measured with enhanced depth imaging (EDI) mode of SD-OCT. Structural parameters; lamina cribrosa thickness (LCT), lamina cribrosa depth (LCD), prelaminar tissue thickness (PLTT), four quadrants of peripapillary choroidal thicknesses (PPCT), and subfoveal choroidal thickness (SFCT) were measured and statistical relationships between the structural parameters have been laid out. We apply the generalized estimating equations method to take into account dependency of right and left eyes. RESULTS: From PXS to mild and advanced PXG groups LCT and PLTT decrease from 147.29 ± 33.10, 145.62 ± 30.64, 126.30 ± 29.14 and 260.93 ± 185.07, 247.27 ± 142.58, 159.89 ± 86.84, respectively, and LCD varies as 159.89 ± 86.84, 420.88 ± 117.80, and 505.64 ± 183.25. The correlations between LCD, LCT, and PLTT and the stage of the disease are significant. BMO-MRW shows slightly stronger correlations than the RNFL with LC related parameters. SFCT does not exhibit any significant relationship with the stage of the disease. However, PPCT in only the interior quadrant does. The significant correlations between LCD and all quadrants of PPCT is the sign of important anatomic relationship. CONCLUSION: These findings show that the BMO-MRW parameter may be more sensitive than RNFL and can safely be used in the diagnosis and follow-up in PXS and PXG, but this result should be supported with longer and larger series.

Real-Time Mobile Teleophthalmology for the Detection of Eye Disease in Minorities and Low Socioeconomics At-Risk Populations.

PURPOSE: To examine the benefits and feasibility of a mobile, real-time, community-based, teleophthalmology program for detecting eye diseases in the New York metro area. DESIGN: Single site, nonrandomized, cross-sectional, teleophthalmologic study. METHODS: Participants underwent a comprehensive evaluation in a Wi-Fi-equipped teleophthalmology mobile unit. The evaluation consisted of a basic anamnesis with a questionnaire form, brief systemic evaluations and an ophthalmologic evaluation that included visual field, intraocular pressure, pachymetry, anterior segment optical coherence tomography, posterior segment optical coherence tomography, and nonmydriatic fundus photography. The results were evaluated in real-time and follow-up calls were scheduled to complete a secondary questionnaire form. Risk factors were calculated for different types of ophthalmological referrals. RESULTS: A total of 957 participants were screened. Out of 458 (48%) participants that have been referred, 305 (32%) had glaucoma, 136 (14%) had narrow-angle, 124 (13%) had cataract, 29 had (3%) diabetic retinopathy, 9 (1%) had macular degeneration, and 97 (10%) had other eye disease findings. Significant risk factors for ophthalmological referral consisted of older age, history of high blood pressure, diabetes mellitus, Hemoglobin A1c measurement of ≥6.5, and stage 2 hypertension. As for the ocular parameters, all but central corneal thickness were found to be significant, including having an intraocular pressure >21 mm Hg, vertical cup-to-disc ratio ≥0.5, visual field abnormalities, and retinal nerve fiber layer thinning. CONCLUSIONS: Mobile, real-time teleophthalmology is both workable and effective in increasing access to care and identifying the most common causes of blindness and their risk factors.

Detecting Common Eye Diseases Using the First Teleophthalmology GlobeChek Kiosk in the United States: A Pilot Study.

PURPOSE: The aim of this study was to assess the benefit and feasibility of the teleophthalmology GlobeChek kiosk in a community-based program. DESIGN: Single-site, nonrandomized, cross-sectional, teleophthalmologic study. METHODS: Participants underwent comprehensive evaluation that consists of a questionnaire form, brief systemic evaluation, screening visual field (VF), and GlobeChek kiosk screening, which included but not limited to intraocular pressure, pachymetry, anterior segment optical coherence tomography, posterior segment optical coherence tomography, and nonmydriatic fundus photography. The results were evaluated by a store-and-forward mechanism and follow-up questionnaires were obtained through phone calls. RESULTS: A total of 326 participatents were screened over 4 months. One hundred thirty-three (40.79%) participants had 1 condition in either eye, and 47 (14.41%) had >1 disease. Seventy (21.47%) had glaucoma, 37 (11.34%) narrow-angles, 6 (1.84%) diabetic retinopathy, 4 (1.22%) macular degeneration, and 43 (13.10%) had other eye disease findings. Age >65, history of high blood pressure, diabetes mellitus, not having a dental examination >5 years, hemoglobn A1c measurement of ≥5.6, predibates risk score of ≥9, stage 2 hypertension, and low blood pressure were found to be significant risk factors. As for the ocular parameters, all but central corneal thickness, including an intraocular pressure >21 mm Hg, vertical cup to disc ratio >0.7, visual field abnormalities, and retinal nerve fiber layer thinning were found to be significant. CONCLUSIONS: GlobeChek kiosk is both workable and effective in increasing access to care and identifying the most common causes of blindness and their risk factors.

Effects of the rigid gas permeable contact lense use on tear and ocular surface among keratoconus patients.

PURPOSE: To investigate changes in tear and ocular surface of patients with keratoconus using rigid gas permeable contact lenses (RGPCL) and compare them against keratoconus patients who were not using lenses as well as a control group of healthy subjects. METHODS: 24 keratoconus patients using RGPCL (Group 1) 22 patients who were not using lenses (Group 3) and 21 healthy subjects (Group 3) were included in the study. Subjective complaints about the subjects' eyes have been investigated using the ocular-surface disease index (OSDI). After the control of best-corrected visual acuity, anterior chamber and fundus examinations were performed. RESULTS: Schirmer (p-value=0.01) and tear break up mean comparison tests (p-value=0.002) revealed significant differences across different groups but tear osmolarity analysis did not (p-value >0.05). Oxford and OSDI scores were compatible with Schirmer and tear break up test comparisons. (for both p-value=0.001) Moreover, no statistical differences were seen in impression cytology measures between groups. (p-value >0.05) CONCLUSIONS: The erosion in the tear film stability is in line with the erosion in the ocular surface epithelium. Taking into account the statistical indifference between the impression cytology measures across groups, the break up time differences may be attributed to the collagen destruction in tear.

Intraocular pressure elevation after intravitreal triamcinolone acetonide injection: a Meta-analysis.

AIM: To report on intraocular pressure (IOP) after intravitreal injections of triamcinolone acetonide. METHODS: Systematic literature review of studies that investigated the effects of an injection of triamcinolone intravitreal triamcinolone acetonide on IOP was conducted according to the Cochrane Collaboration methodology and the reported effects have been analyzed with Meta-analysis. RESULTS: We found that the IOP follows an inverted-U shape pattern over time starting with an average value of 14.81±1.22 mm Hg before the injection, rising to a maximum of 19.48±2.15 mm Hg after one month of injection and falling down to 16.16±1.92 mm Hg after 6mo. Moreover, country of study, age, previous history of glaucoma and gender compositions matter for cross-study were different in reported IOP changes. CONCLUSION: Our findings may be helpful in determining pressure elevation risk of intravitreal triamcinolone acetonide therapy as well as comparing it with those of more recent therapies such as the anti-vascular endothelial growth factor agents.

Comparative Analysis of Tear Film Levels of Inflammatory Mediators in Contact Lens Users.

PURPOSE: To compare tear films levels of various inflammatory cytokines in asymptomatic contact lens (CL) users. CL users of rigid gas-permeable CLs (RGPCL) (group 1) or silicone hydrogel CLs (SiHCL) (group 2) were compared with non-CL-using healthy subjects (group 3). MATERIALS AND METHODS: Tear samples were collected from subjects in each group after ensuring that there were no complications secondary to CL wear in the CL-wearing participants. Tear-film levels of interleukins (ILs)-1ß, -6, and -8; granulocyte-macrophage colony-stimulating factor (GM-CSF) (using the Luminex method); and leukotriene B4 (LTB4) (using the ELISA method) were determined. Cytokine levels were compared among the three groups using analysis-of-variance (ANOVA) and Kruskall-Wallis tests. RESULTS: There were significant differences in concentrations of IL-1ß, GM-CSF and LTB4 among the three groups (p = 0.002, p = 0.021 and p = 0.009, respectively), as shown by the Kruskall-Wallis test comparing all three groups for the three cytokines. There were no significant differences for IL-6 and IL-8 (p = 0.079 and 0.094, respectively) when all three groups were compared. CONCLUSIONS: There were substantial statistically significant differences between RGPCL users, SiHCL users and control subjects in levels of tear film cytokines. Although CL users were asymptomatic, changes in tear-film levels of several important inflammatory mediators revealed that a chronic inflammatory process occurs during CL wear.

Effect of Fasting on Corneal Biomechanical and Structural Parameters.

PURPOSE: To evaluate the effects of hunger and thirst on corneal biomechanical and structural parameters during Ramadan fasting. MATERIALS AND METHODS: Corneal biomechanical properties and intraocular pressures of 29 eyes of 29 healthy subjects were evaluated by Reichert ocular response analyzer; and structural and anatomical properties of cornea and anterior eye chamber of same eyes were scanned with Oculus Pentacam anterior segment analyzer. Each eye has been evaluated at 8 am and 4 pm both during and 1 month after Ramadan. Changes of subjects' weight were calculated and their relationship with corneal biomechanical and structural parameters was assessed. RESULTS: Intraday changes in horizontal corneal astigmatism (p = 0.02), anterior chamber volume (p = 0.01), intraocular pressure associated with the Goldmann IOPg (p = 0.02) and corneal resistance factor (CRF) (p = 0.04) were significantly different when measured during the fasting period in Ramadan and 1 month thereafter. Moreover, when we compared 8 am measurements taken during and after Ramadan, we observed significant differences for anterior chamber volume (p = 0.04) and anterior chamber angle values (p = 0.03). Similarly, for 4 pm measurements, there were significant differences for IOPg (p = 0.01) and CRF values (p = 0.00). CONCLUSIONS: Fasting lasting for more than 12 h during Ramadan creates an important window of opportunity to investigate the response of anterior chamber of eye to hunger and thirst. The current study contributes to the existing literature on the effects of dietary habits and water intake on corneal and anterior chamber properties.

Retinal nerve fiber layer structure abnormalities in patients with Neuro-Behcet's disease.

PURPOSE: Our aim was the evaluation of retinal nerve fiber layer (RNFL) and central macular thickness (CMT) in patients with Neuro-Behcet's disease (NBD) and to compare the results with healthy control subjects. METHODS: We recruited 50 eyes of 25 patients with NBD and 42 eyes of 21 age-matched healthy control subjects. Patients and control subjects underwent a thorough ophthalmic examination, including retinal nerve fiber layer and macular thickness measurements by optical coherence tomography. RESULTS: No significant difference was found between groups for age, sex, intra-ocular pressure and central corneal thickness measurements. The average RNFL in patients with NBD was significantly lower than that of healthy controls (86.92 ± 18.36 µm vs. 99.74 ± 8.73 µm; p = 0.00). There was significant thinning of the RNFL in three of four quadrants of the peripapillary area, superior (107.22 ± 30.91 µm vs. 125.57 ± 20.97 µm; p = 0.00), inferior (110.36 ± 25.57 µm vs. 132.19 ± 12.71 µm; p = 0.00) and nasal (68.84 ± 18.47 µm vs. 74.98 ± 11.42 µm; p = 0.05), in patients with NBD. Average CMT was significantly lower in NBD patients than in control subjects (244.06 ± 26.25 µm vs. 261.69 ± 25.71 µm; p = 0.00). CONCLUSIONS: There are significant differences in average RNFL and CMT between the two groups. RNFL and CMT thicknesses are reduced in patients with NBD compared with the healthy controls.