OCTess: AN OPTICAL CHARACTER RECOGNITION ALGORITHM FOR AUTOMATED DATA EXTRACTION OF SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHY REPORTS.

PURPOSE: Manual extraction of spectral domain optical coherence tomography (SD-OCT) reports is time and resource intensive. This study aimed to develop an optical character recognition (OCR) algorithm for automated data extraction from Cirrus SD-OCT macular cube reports. METHODS: SD-OCT monocular macular cube reports (n = 675) were randomly selected from a single-center database of patients from 2020 to 2023. Image processing and bounding box operations were performed, and Tesseract (an OCR library) was used to develop the algorithm, OCTess. The algorithm was validated using a separate test data set. RESULTS: The long short-term memory deep learning version of Tesseract achieved the best performance. After reverifying all discrepancies between human and algorithmic data extractions, OCTess achieved accuracies of 100.00% and 99.98% in the training (n = 125) and testing (n = 550) datasets, while the human error rate was 1.11% (98.89% accuracy) and 0.49% (99.51% accuracy) in each, respectively. OCTess extracted data in 3.1 seconds, compared with 94.3 seconds per report for human evaluators. CONCLUSION: We developed an OCR and machine learning algorithm that extracted SD-OCT data with near-perfect accuracy, outperforming humans in both accuracy and efficiency. This algorithm can be used for efficient construction of large-scale SD-OCT data sets for researchers and clinicians.

Visual impairment and the prevalence of ocular pathology in homeless children and adults globally: a systematic review.

BACKGROUND: Homelessness is a global issue in developing and developed countries. This article is the first systematic review to explore its impact on visual health globally. METHODS: A systematic literature search was conducted on OVID MEDLINE, EMBASE, and Cochrane CENTRAL. Peer-reviewed English-language studies with a focus on homeless children or adults that reported on ocular outcomes were included. Primary outcomes and secondary endpoints were reported via weighted averages. Primary outcomes between homeless children and homeless adults were compared using the Fisher exact test. RESULTS: There were 5774 individuals across 23 full-text articles included in the review. For studies reporting primary outcomes, 36.8% of homeless individuals self-reported dissatisfaction with their vision, 26.8% self-reported a previous ocular pathology, 26.3% had uncorrected refractive error, 25.6% were functionally visually impaired, 9.2% had at least one previous eye surgery or procedure, and 4.0% had nonrefractive visual impairment. Upon screening, 25.1% of homeless individuals had some type of ocular pathology, which included cornea and external eye diseases (13.4%), glaucoma (7.4%), cataracts (6.3%), retinal diseases (5.3%), ocular motility disorders (4.7%), trauma (2.3%), neuro-ophthalmological conditions (1.7%), and oculoplastic conditions (0.7%). Homeless adults had significantly more visual impairment (p < 0.001), uncorrected refractive error (p < 0.001), ocular pathology (p < 0.001), cataracts (p < 0.001), retinal pathology (p < 0.001), and neuro-ophthalmological conditions (p < 0.001) relative to children. CONCLUSIONS: Visual impairment in homeless individuals is higher than the general population. Uncorrected refractive error is a leading cause of visual impairment in this population. Additionally, homeless adults have significantly more visual impairment and ocular pathology than homeless children. Future studies should also explore if these differences are consistent in developing countries and investigate ways to increase eye care access for homeless individuals.