Retinal immaturity at first screening and retinopathy of prematurity: Image-based validation of 1202 eyes of premature infants to predict disease progression

Abstract

Purpose: To use the extent of retinal immaturity at the first visit to predict progression to any stage and treatment-requiring retinopathy of prematurity (ROP). Methods: Retrospective, multicenter, nonrandomized, observational, clinical, validation study. In all, 601 Asian Indian preterm infants born < 2000 g and/or < 34 weeks of gestation completing ROP screening with RetCam images taken during each visit were included. A total of 1202 eyes of these infants were classified into three groups based on the retinal immaturity at the first screening visit into “mild” (Group 1), vessels reaching the posterior boundary of zone 3; “moderate” (Group 2), vessels entering zone 2 anterior; and “severe” (Group 3), vessels in zone 1 or zone 2 posterior. RetCam images at each subsequent visit were evaluated and the proportion of eyes that progressed to Type 1 or Type 2 ROP was correlated with the degree of retinal immaturity. Results: Of the 958 eyes in Group 1, 200 eyes in Group 2, and 44 eyes in Group 3, any stage ROP developed in 15% of eyes in Group 1, 46.5% of eyes in Group 2, and 100% of eyes in Group 3 ( P < 0.001). Sixteen of 128 eyes (12.5%), 12 of 72 (16.6%), and 28 of 44 of eyes (63.6%) in Groups 1, 2, and 3, respectively, required treatment ( P < 0.001). Conclusion: Retinal immaturity at first screening visit predicts Type 1 and Type 2 ROP. “Severe” immaturity is more likely to progress to “treatment-requiring” disease. This could be a useful tool for prognostication, counseling, and scheduling follow-up.

Risk Calculator for Retinopathy of Prematurity Requiring Treatment

“…Meanwhile, Jayadev classifies the temporal avascular area of the retina into three degrees: (a) mild: vessels reach posterior zone III; (b) moderate: vessels enter anterior zone II; (c) severe: vessels in posterior zone I or zone II. Thus, type 1 and type 2 ROP are predicted during the first screening visit (27). Jayadev and we have determined that the avascular area of the retina is the main risk factor for ROP requiring treatment.…”

“…Once the optic disc diameter is known, extension of any retinal territory can be quantified in DDs. This measurement unit has been used by several authors to quantify the territory of retinal immaturity (26,27).…”

Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity

“…However, retinal status is also important for ROP prediction. Previous studies have shown that minor vascular dilation, vascular tortuosity insufficiency in plus disease, the extent of temporal vascularization, and retinal immaturity at the first screening have prognostic significance in the early course of ROP . Thus, our DL system was developed to predict occurrence and severity of ROP using retinal photographs from the first screening along with clinical characteristics.…”

“…16,[20][21][22][23][24] However, some of these prediction models are flawed because of they neglect retinal status, which is also important for ROP prediction. [25][26][27] Deep learning (DL) has been recently used for the automated diagnosis of many ocular diseases. [28][29][30][31] Several DL systems have been developed for automated diagnosis of the plus disease of ROP with high accuracy (>89.6%) based on RetCam images.…”

“…Previous studies have used traditional regression analysis to predict ROP based on BW, GA, gender, and/or postnatal weight gain, among other factors . However, some of these prediction models are flawed because of they neglect retinal status, which is also important for ROP prediction …”