Faculty Bibliography

TOPIC/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED: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/UNASSIGNED:Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

PURPOSE/UNASSIGNED:This study was to assess corneal epithelial thickness (CET) in patients with Sjogren's disease (SjD). METHODS/UNASSIGNED:A retrospective chart review was conducted of SjD patients from September 2021 to January 2022. Patient demographics, unanesthetized Schirmer's test, serologic markers, and symptoms as measured by the Ocular Surface Disease Index (OSDI) were reviewed. Epithelial thickness from both eyes was measured using anterior segment OCT at the central 3mm and concentric 5mm, 7mm, and 9mm zones for the superior, temporal, inferior, and nasal corneal quadrants. Associations between corneal epithelial thickness with patient demographics, clinical characteristics, and symptoms were evaluated using regression models. RESULTS/UNASSIGNED:Fifteen SjD patients (100% female) were included with a mean age of 58.4 years. Patients with Sjogren's disease had a significantly thinner superior corneal epithelium compared to the inferior epithelium (mean 47.7mm vs 53.1mm, p = 0.001). The epithelial thickness mean standard deviation (MSD) was significantly inversely correlated with the unanesthetized Schirmer test (r=-0.39, p = 0.005), suggesting that an overall variability of CET correlates with decreased aqueous tear production. SS-A, SS-B, ANA, and RF positivity were not associated with any measures of CET. CONCLUSION/UNASSIGNED:This pilot study suggests that there is significant superior versus inferior thinning of corneal epithelium in Sjogren's patients. There was a significant correlation between variability of corneal epithelial thickness and decreased tear production in Sjogren's patients. Further larger studies are needed to understand the relationship of CET with objective and subjective measurements of ocular surface disease.

PURPOSE/UNASSIGNED:Improvements in best-corrected visual acuity (BCVA) and central subfield thickness (CST) have been well documented after intravitreal injection of anti-VEGF medications in diabetic macular edema (DME); however, their effect on the vasculature of the macula in diabetic retinopathy (DR) remains poorly understood. Our aim was to explore the effect of intravitreal injection of anti-VEGF on parameters of retinal vascular microstructure in DR with OCT angiography (OCTA). DESIGN/UNASSIGNED:Retrospective study of adult patients with DME that were treated with anti-VEGF intravitreal injections at the University of Illinois at Chicago between 2017 and 2022. PARTICIPANTS/UNASSIGNED:Forty-one eyes from 30 patients with nonproliferative or proliferative DR with a mean age of 58.83 ± 11.71 years, mean number of intravitreal injections of 2.8 ± 1.4, and mean follow-up of 6.5 ± 1.7 months. METHODS/UNASSIGNED:tests and analysis of variance were used to determine statistical significance. MAIN OUTCOME MEASURES/UNASSIGNED:A primary analysis was performed comparing the mean of each parameter of all patients as a single group at the beginning and end of the study period. A subgroup analysis was then performed after stratifying patients based on visual improvement, change in CST, prior injection history, and number of injections. RESULTS/UNASSIGNED:Eyes demonstrated statistical improvement in BCVA logarithm of the minimum angle of resolution score and CST after anti-VEGF treatment. Primary analysis showed a reduction in the vessel diameter of the superficial and deep retinal vasculature, as well as an increase in the circularity of the FAZ within the superficial retinal vasculature after anti-VEGF treatment. Subgroup analysis revealed that eyes with improvement in BCVA exhibited reduced vessel diameter in the superficial retinal vasculature and that eyes with the largest decrease in CST displayed increased perfusion density and VLD in the deep retinal vasculature. CONCLUSIONS/UNASSIGNED:Intravitreal injection of anti-VEGF agents to treat DME improved parameters of retinal vascular microstructure on OCTA over a period of 3 to 9 months, and this effect was most pronounced in eyes that experienced improvement in BCVA and CST. FINANCIAL DISCLOSURES/UNASSIGNED:Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.