Improving Access to Eye Care Through Community Health Screenings Using Artificial Intelligence.

PURPOSE: To the best of our knowledge, implementation of artificial intelligence (AI)-based vision screening in community health fair settings has not been previously studied. This prospective cohort study explored the incorporation of AI in a community health fair setting to improve access to eyecare. METHODS: Vision screening was implemented during a community health fair event using an AI-based non-mydriatic fundus camera. In addition, a questionnaire was provided to survey the various barriers to eyecare and assess eye health literacy. RESULTS: A total of 53 individuals were screened at this event. Notably, about 88% of participants had follow-up appointments scheduled accordingly with an approximate 62% attendance rate. The most reported barrier to eyecare was lack of health insurance followed by transportation. CONCLUSION: The addition of AI-based vision screening in community health fairs may ultimately help improve access to eye care.

Anterior Chamber Depth and Lens Thickness Measurements in Pediatric Eyes: Ultrasound Biomicroscopy Versus Immersion A-Scan Ultrasonography.

OBJECTIVE: To compare anterior chamber depth (ACD) and lens thickness (LT) measurements by ultrasound biomicroscopy (UBM), A-scan cross vector (CV) overlay with UBM, and immersion A-scan technique in pediatric eyes. METHODS: This prospective comparative cohort study comprised 43 eyes of 25 pediatric participants (mean age: 2.3±2.2 y). UBM and immersion A-scan biometry were performed prior to dilation and intraocular surgery. ACD and LT were measured by UBM image analysis, A-scan CV UBM overlay, and immersion A-scan technique. RESULTS: ACD and LT measurements obtained using immersion A-scan were significantly greater than with UBM image analysis with mean differences of 0.52 mm and 0.62 mm, respectively (p < 0.001). Immersion A-scan and UBM measurements were moderately correlated (r = 0.70 and 0.64, p < 0.001). ACD and LT measurements obtained using CV overlay were not significantly different than UBM measurements and the values were strongly positively correlated (r = 0.95 and 0.93, p < 0.001). CONCLUSION: Immersion A-scan may overestimate ACD and LT compared to UBM in pediatric patients due to oblique placement of the A-scan probe relative to the optical axis. Supplemental use of UBM and/or CV overlay is indicated to improve measurement accuracy in pediatric patients who cannot reliably fixate due to the ability to confirm proper alignment of the probe with the pupil by visualizing the anterior segment.

Comparison of angle-to-angle distance and corneal diameter in pediatric eyes using ultrasound biomicroscopy.

OBJECTIVE: To investigate the relationship between corneal diameter and internal corneal span determined from angle-to-angle distance using ultrasound biomicroscopy (UBM) in an observational cross-sectional patient population comprised of 54 eyes (28 healthy control eyes, ages 0.1 to 11.3 years; 26 eyes with primary congenital glaucoma, ages 0.1 to 3.5 years) from 41 pediatric participants ages 0.1 to 11.3 years (mean age: 3±3 years, median age: 2 years). METHODS: Forty cornea photographs with reference ruler and 110 UBM images were obtained. Three observers measured horizontal and vertical corneal diameter and angle-to-angle distance in each cornea photo and UBM image using ImageJ and the average values were used. Main outcome measures were Pearson correlation coefficient, linear regression, mean difference between corneal diameter and angle-to-angle distance, and intra-class correlation coefficients among measurements from all three observers for each parameter. RESULTS: Corneal diameter and angle-to-angle distance had a strong positive correlation horizontally (Pearson r = 0.89, p<0.001) and vertically (r = 0.93, p<0.001). Correlation was consistent regardless of presence of primary congenital glaucoma and participant age. Regression analysis demonstrated a linear relationship between the parameters for horizontal (CD = 0.99*AA+0.28, R2 = 0.81, p<0.001) and vertical (CD = 0.91 *AA+1.32, R2 = 0.85, p<0.001) dimensions. Overall, reliability was good-excellent, ranging from an ICC of 0.76 for vertical corneal diameter to 0.90 for horizontal angle-to-angle distance. CONCLUSIONS: Based on the strong positive correlation found between corneal diameter and angle-to-angle distance in our study population, UBM image analysis can be used to accurately estimate corneal diameter from angle-to-angle distance in children with healthy eyes and primary congenital glaucoma. UBM may provide a useful intraocular alternative for estimating corneal diameter and monitoring diseases that affect the cornea in infants and children, such as congenital glaucoma.