Key Points Question Can deep learning algorithms achieve a performance comparable with that of ophthalmologists on multidimensional identification of retinopathy of prematurity (ROP) using wide-field retinal images? Findings In this diagnostic study of 14 108 eyes of 8652 preterm infants, a deep learning–based ROP screening platform could identify retinal images using 5 classifiers, including image quality, stages of ROP, intraocular hemorrhage, preplus/plus disease, and posterior retina. The platform achieved an area under the curve of 0.983 to 0.998, and the referral system achieved an area under the curve of 0.9901 to 0.9956; the platform achieved a Cohen κ of 0.86 to 0.98 compared with 0.93 to 0.98 by the ROP experts. Meaning Results suggest that a deep learning platform could identify and classify multidimensional ROP pathological lesions in retinal images with high accuracy and could be suitable for routine ROP screening in general and children’s hospitals.
CH measurement is practical in young children because this is when myopia undergoes its most rapid progression. Prospective follow-up of this cohort at high risk for myopia is under way to determine whether low CH is predictive, or a consequence, of long AL.
Purpose: To evaluate the efficacy of Highly Aspherical Lenslets (HAL) in slowing myopia progression among school children and compare it to Orthokeratology. Methods: This retrospective cohort study included 186 cases of myopic individuals aged between 7 to 15 years, with myopia ranging from -0.75 to -8.00D and astigmatism of ≤ 4.0D. Each group consisted of 62 subjects, and only the right eye was included in the analysis. The study involved six-monthly measurements of both cycloplegic refraction and axial length to track changes over time. Results: The baseline average age, gender, Spherical equivalent refraction (SER), and axial length (AL) in the SV group, HAL group, and Ortho-K group were no statistically significant differences (P>0.05). At six months, average (SER) myopia progression was -0.44±0.34 D in the single vision (SV) lenses group and -0.16±0.32 D in the HAL group. Average axial elongation was 0.22±0.13mm in the SV group, 0.08±0.14mm in the HAL group and 0.04±0.11mm in the orthokeratology group. As compared to the SV group, the HAL group reduced myopia progression (SER) to 65.9% (mean difference 0.29±0.46D, P<0.001). Compared with the SV group, the HAL group axial elongation more slowly(63.6%, mean difference 0.14±0.19mm, P<0.001). Likewise, axial elongation more slowly at 81.8% for orthokeratology group subjects than the SV group (mean difference 0.18±0.20mm, P<0.001). In terms of individual issues, 35 of 62 children wearing HAL had no myopia progression after 6 months, higher than the SV group (15 of 62, 24.2%, P<0 .001). In addition, 30.6% of children with HAL revealed no axial elongation, compared with 3.2% of those with SV lenses (2 of 62, P<0 .001). The axial elongation of HAL and Ortho-K lenses (28 of 62, 45.2%) was similar (P> 0.05). Conclusions: Wearing the HAL daily slows myopia progression in myopic children and significantly reduces axial elongation. Additionally, both the daily employment of HAL and overnight Orthokeratology demonstrate comparable efficacy in slowing axial elongation in myopic children.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.