Retinopathy of prematurity in preterm infants born following assisted conception versus spontaneously conceived pregnancies – A 2-year retrospective observational study from an urban tertiary eye care referral center in South India

Purpose: The aim of this study is to determine if in vitro fertilization (IVF) is associated with an increase in the incidence of retinopathy of prematurity (ROP) among preterm infants. Methods: This retrospective, comparative study included all the preterm babies who were screened under an urban multicentric outreach project between April 2019 and August 2022. Infant details including gender, birth weight, mode of conception, single or multiple gestation, gestational age and post?menstrual age in weeks, age at presentation, and any presence of risk factors were recorded and analyzed. Results: Among 444 preterm babies included in the study, 373 (84%) were conceived normally and 71 (16%) were conceived by IVF. ROP was found in 99 (22.29%) babies in total. There was no significant difference in the incidence of any stage of ROP between the two groups; however, higher stages of ROP were found to be relatively more frequent in the spontaneous conception group in our study. We also found a statistically significant difference in the presence of ROP among singletons, twins, and triplets. Conclusion: IVF was found not to independently increase the risk of ROP in preterm infants. More prospective studies and randomized controlled trials are needed to establish the relationship between the mode of conception and development of severe ROP in preterm infants

Development and validation of an offline deep learning algorithm to detect vitreoretinal abnormalities on ocular ultrasound

Purpose: We describe our offline deep learning algorithm (DLA) and validation of its diagnostic ability to identify vitreoretinal abnormalities (VRA) on ocular ultrasound (OUS). Methods: Enrolled participants underwent OUS. All images were classified as normal or abnormal by two masked vitreoretinal specialists (AS, AM). A data set of 4902 OUS images was collected, and 4740 images of satisfactory quality were used. Of this, 4319 were processed for further training and development of DLA, and 421 images were graded by vitreoretinal specialists (AS and AM) to obtain ground truth. The main outcome measures were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and area under receiver operating characteristic (AUROC). Results: Our algorithm demonstrated high sensitivity and specificity in identifying VRA on OUS ([90.8%; 95% confidence interval (CI): 86.1�.3%] and [97.1% (95% CI: 93.7�.9%], respectively). PPV and NPV of the algorithm were also high ([97.0%; 95% CI: 93.7�.9%] and [90.8%; 95% CI: 86.2�.3%], respectively). The AUROC was high at 0.939, and the intergrader agreement was nearly perfect with Cohen抯 kappa of 0.938. The model demonstrated high sensitivity in predicting vitreous hemorrhage (100%), retinal detachment (97.4%), and choroidal detachment (100%). Conclusion: Our offline DLA software demonstrated reliable performance (high sensitivity, specificity, AUROC, PPV, NPV, and intergrader agreement) for predicting VRA on OUS. This might serve as an important tool for the ophthalmic technicians who are involved in community eye screening at rural settings where trained ophthalmologists are not available