Treatment of retinopathy of prematurity (ROP) outside International Classification of ROP (ICROP) guidelines

Insulin-like growth factor-1 and retinopathy of prematurity: A systemic review and meta-analysis

The prevalence of retinopathy of prematurity (ROP) is rapidly increasing worldwide. Many researchers have explored the relationship between insulin-like growth factor-1 (IGF-1) and ROP; however, the results are controversial. This meta-analysis evaluates the correlation between IGF-1 and ROP systematically. We searched for PubMed, Web of Science, Embase, the Cochrane Central Register of Controlled Trials, Ovid MEDLINE, SinoMed, ClinicalTrials.gov, and 3 Chinese databases up to June 2022. Then, the meta-regression and subgroup analysis were carried out. Twelve articles with 912 neonates were included in this meta-analysis. The results revealed that 4 of 7 covariates account for significant heterogeneity: location, measurement method of IGF-1 levels, collection time of blood sample, and the severity of ROP. The pooled analysis showed that low IGF-1 levels could serve as a risk factor associated with the development and severity of ROP. Serum IGF-1 monitoring in preterm infants after birth will be helpful in the diagnosis and treatment of ROP, and the reference value of IGF-1 should be standardized according to the measurement of IGF-1 and the region, as well as the postmenstrual age of prematurity.

Retrospective validation of G-ROP, CO-ROP, Alex-ROP, and ROPscore predictive algorithms in two Chinese medical centers

Purpose

To evaluate the sensitivity and specificity of four predictive algorithms (G-ROP, CO-ROP, Alex-ROP, and ROPscore) for retinopathy of prematurity and compare their performances in the Chinese population.

Methods

A retrospective study was conducted at two medical centers in China of infants born at Women's Hospital School of Medicine Zhejiang University and Yiwu Maternal and Child Health Hospital. A total of 1,634 infants who met the criteria and who were GA < 32 weeks or BW < 2,000 g according to Chinese guidelines for ROP screening were included. The ROP group was further grouped into severe ROP and mild ROP. The sensitivity and specificity of G-ROP, two simplified G-ROPs, CO-ROP, Alex-ROP, and ROPscore were analyzed.

Results

Severe ROP and any ROP were identified in 25 and 399 of 1,634 infants, respectively. According to the criteria of different models, 844, 1,122, 1,122, and 587 infants were eligible in the G-ROP, CO-ROP, Alex-ROP, and ROPscore, respectively. G-ROP had 96.0% sensitivity and 35.0% specificity for severe ROP. For two simplified G-ROPs (180 g and 200 g models), similar sensitivity was showed with original G-ROP and they had specificity of 21.8% and 14.0%, respectively. The sensitivity and specificity of Co-ROP were 96% and 64.3% for severe ROP, while Alex-ROP only had sensitivity of 56.0% and specificity of 61.4% for severe ROP. ROPscore had a sensitivity of 91.3% and a specificity of 62.4% for severe ROP. In 546 infants who met all 4 models' inclusion criteria and included 23 infants with severe ROP, the validation outcomes showed the sensitivity of G-ROP, ROPscore, CO-ROP, and Alex-ROP for severe ROP was 95.6%, 91.3%, 100%, and 56.0%, and their specificity was 38.0%, 60.8%, 39.9%, and 52.9%, respectively.

Conclusion

G-ROP, ROPscore, and CO-ROP had high sensitivity for severe ROP in the Chinese population, but both the sensitivity and specificity of Alex-ROP were low. CO-ROP (not high-grade CO-ROP) provided the best performance for severe ROP in a fair comparison. For further application, ROP screening models need to be adjusted by local populations.

Treatment for Nontype 1 Retinopathy of Prematurity by Intravitreal Injection of Antivascular Endothelial Growth Factor Drugs

Background. To explore clinical characteristics and treatment reasons for intravitreal injection of antivascular endothelial growth factor (anti-VEGF) drugs in the treatment of nontype 1 retinopathy of prematurity (ROP). Methods. A retrospective study was conducted to screen the nontype 1 ROP from the collected ROP patients who received intravitreal injections of anti-VEGF drugs in Henan Eye Hospital from September 2018 to June 2021. Results. A total of 138 ROP cases (262 eyes) were included in this study, including 39 cases (28.3%), 65 eyes (24.8%) that were the nontype 1 ROP. Compared with the type 1 ROP group, the nontype 1 ROP group had slightly later treatment time (39.8 ± 2.7 weeks vs 38.1 ± 2.6 weeks, $P<0.05$ ) and a higher proportion of fusion protein drugs (87.2% vs 54.5%, $P<0.05$ ). After intravitreal injection of anti-VEGF drugs, 27 eyes (41.5%) were cured and 38 eyes (58.5%) improved in the nontype 1 ROP group, without recurrence and aggravation cases. There were more lesions in zone II (63 eyes, 96.9%), with stage 2 (40 eyes, 61.5%) and stage 3 (23 eyes, 35.4%), and 58 eyes (89.2%) showed preplus in the nontype 1 ROP group. Treatment reasons included preplus in 58 eyes (89.2%), ridge aggravation in 22 eyes (33.8%), simultaneous treatment of the contralateral eye in 9 eyes (13.8%), no regression of lesions in the persistent stage 2 or 3 over PMA 44 weeks of follow-up in 8 eyes (12.3%), and logistical considerations in 4 eyes (6.2%). Conclusions. Considering some peculiar clinical characteristics, treatment by intravitreal injection of anti-VEGF drugs may be considered carefully for some nontype 1 ROP in critical conditions.

Artificial Intelligence for Retinopathy of Prematurity: Validation of a Vascular Severity Scale against International Expert Diagnosis

PURPOSE

To validate a vascular severity score as an appropriate output for artificial intelligence (AI) Software as a Medical Device (SaMD) for retinopathy of prematurity (ROP) through comparison with ordinal disease severity labels for stage and plus disease assigned by the International Classification of Retinopathy of Prematurity, Third Edition (ICROP3), committee.

DESIGN

Validation study of an AI-based ROP vascular severity score.

PARTICIPANTS

A total of 34 ROP experts from the ICROP3 committee.

METHODS

Two separate datasets of 30 fundus photographs each for stage (0-5) and plus disease (plus, preplus, neither) were labeled by members of the ICROP3 committee using an open-source platform. Averaging these results produced a continuous label for plus (1-9) and stage (1-3) for each image. Experts were also asked to compare each image to each other in terms of relative severity for plus disease. Each image was also labeled with a vascular severity score from the Imaging and Informatics in ROP deep learning system, which was compared with each grader's diagnostic labels for correlation, as well as the ophthalmoscopic diagnosis of stage.

MAIN OUTCOME MEASURES

Weighted kappa and Pearson correlation coefficients (CCs) were calculated between each pair of grader classification labels for stage and plus disease. The Elo algorithm was also used to convert pairwise comparisons for each expert into an ordered set of images from least to most severe.

RESULTS

The mean weighted kappa and CC for all interobserver pairs for plus disease image comparison were 0.67 and 0.88, respectively. The vascular severity score was found to be highly correlated with both the average plus disease classification (CC = 0.90, P < 0.001) and the ophthalmoscopic diagnosis of stage (P < 0.001 by analysis of variance) among all experts.

CONCLUSIONS

The ROP vascular severity score correlates well with the International Classification of Retinopathy of Prematurity committee member's labels for plus disease and stage, which had significant intergrader variability. Generation of a consensus for a validated scoring system for ROP SaMD can facilitate global innovation and regulatory authorization of these technologies.

Treatment outside the Recommended Guidelines for Retinopathy of Prematurity (ROP): Prevalence, Characteristics, and Issues

This study aims to assess the prevalence and characteristics of preterm infants with retinopathy of prematurity (ROP) treated outside the recommended guidelines. In this retrospective monocentric cohort, we included all premature children treated in our department for ROP by laser photoablation or anti-VEGF intravitreal injection. The main outcome was treatment of both eyes for ROP less severe than pre-threshold type 1, treated outside ETROP guidelines. A total of 114 children received treatment for ROP in our department, among whom 32 (28.1%) children received treatment for indications outside the ETROP guidelines for both eyes. The indications outside the guidelines were persistent stage 2 or 3 ROP that showed no evidence of regression after 41 weeks of corrected gestational age (11 children; 34.4%), pre-plus stage (11; 34.4%), difficulties in disease staging (7; 21.9%), type 2 ROP with plus disease (2; 6.2%), and treatment due to logistical difficulties (1; 3.1%; hospitalized in neonatal units hundreds of miles away from our department, with no fundus examination possible in the neonatal unit). To resume, in our cohort, 28.1% of children received treatment for ROP less severe than pre-threshold type 1 both eyes. The main indications for off-label treatment were the persistence of active ROP during follow-up and the presence of pre-plus-stage disease. Our data suggest the need to update ROP treatment criteria to reflect real-life practices. Additional studies are required in order to evaluate the long-term benefits and side effects of treatments outside the recommended indications, and to establish revised treatment guidelines.

Severe Retinopathy of Prematurity Is Not Independently Associated With Worse Neurodevelopmental Outcomes in Preterm Neonates

Purpose: To evaluate the relationship between retinopathy of prematurity (ROP) severity and neurodevelopmental outcomes in premature neonates at 0-36 months corrected age. Methods: A retrospective chart review was performed on 228 neonates screened for ROP at the UCLA Mattel Children's Hospital between 2011 and 2018. Demographic information, clinical outcomes, ROP severity (no ROP, type 1 ROP, type 2 ROP), and Bayley-III neurodevelopmental scores were collected. Infants were grouped into corrected age cohorts (0-12, 12-24, and 24-36 months) to assess neurodevelopmental outcomes with increasing age. Within each age cohort, ANOVA and Chi-Square testing were used to detect differences in birth characteristics and neurodevelopmental scores between infants with type 1 ROP, type 2 ROP, or no ROP. Univariable analyses assessed the relationship between ROP severity and neurodevelopmental outcomes within each age cohort. A multivariable analysis was then performed to determine if ROP severity remained significantly associated with worse neurodevelopmental scores after controlling for birth weight (BW), intraventricular hemorrhage grade (IVH), health insurance type, male sex, and age at Bayley testing. Results: Without controlling for factors associated with prematurity, neonates with type 1 ROP had poorer cognition (p = 0.001) and motor (p = 0.006) scores at ages 0-12 months and poorer cognition (p = 0.01), language (p = 0.04) and motor (p = 0.04) scores at ages 12-24 months than infants without ROP, but no significant differences were detected at ages 24-36 months. After adjusting for BW, IVH, insurance type, male sex, and age at Bayley testing, ROP severity was no longer associated with worse neurodevelopmental scores in any domain. Conclusion: This study emphasizes that poorer neurodevelopmental outcomes in preterm neonates are most likely related to lower birthweight, associated co-morbidities of prematurity, and socioeconomic factors such as health insurance, not severity of ROP itself.

Deep Learning Models for Automated Diagnosis of Retinopathy of Prematurity in Preterm Infants

Retinopathy of prematurity (ROP) is a disease that can cause blindness in premature infants. It is characterized by immature vascular growth of the retinal blood vessels. However, early detection and treatment of ROP can significantly improve the visual acuity of high-risk patients. Thus, early diagnosis of ROP is crucial in preventing visual impairment. However, several patients refrain from treatment owing to the lack of medical expertise in diagnosing the disease; this is especially problematic considering that the number of ROP cases is on the rise. To this end, we applied transfer learning to five deep neural network architectures for identifying ROP in preterm infants. Our results showed that the VGG19 model outperformed the other models in determining whether a preterm infant has ROP, with 96% accuracy, 96.6% sensitivity, and 95.2% specificity. We also classified the severity of the disease; the VGG19 model showed 98.82% accuracy in predicting the severity of the disease with a sensitivity and specificity of 100% and 98.41%, respectively. We performed 5-fold cross-validation on the datasets to validate the reliability of the VGG19 model and found that the VGG19 model exhibited high accuracy in predicting ROP. These findings could help promote the development of computer-aided diagnosis.