Analysis of trends in retinopathy of prematurity over 5 years in a tertiary neonatal intensive care unit.

AIM: The aim of the study was to look at the incidence and trend of retinopathy of prematurity (ROP) between 2017 and 2021 in a tertiary neonatal intensive care unit (NICU) in Australia and to compare potential modifiable risk factors of ROP between preterm infants who required treatment for ROP and who did not need treatment. METHODS: This retrospective study used the data of newborn infants who were <31 weeks gestational age (GA) or birth weight (BW) of <1250 g born between 2017 and 2021 at a tertiary NICU in Australia (n = 261). Univariate analysis using t test for continuous data, Fischer exact test for categorical data and multiple logistic regression analysis were undertaken to identify any significant differences between two groups. RESULTS: A total number of 261 infants were studied. 55.9% of infants developed any type of ROP (146 infants out of 261 infants), type 1 ROP was 5.4% (14 out of 261) and aggressive ROP (AROP) was 3% (8 out of 261). Out of 146 infants who were diagnosed with ROP, 22 (15%) of them required treatment. Mean GA for those who underwent ROP treatment was 25.6 (±1.47) weeks and for those who did not require treatment was 27.6 (±1.95) weeks. The mean BWs for those who needed treatment was 764 (±189.32) g and for those who did not need treatment was 1039 (±306.06) g. The mean duration of invasive ventilation for infants with ROP requiring treatment and those who did not require treatment were 23.95 (±22.41) days and 9.89 (±17.2) days. The total duration of oxygen requirement was 235.54 (±160.5) days and 121.11 (±117.34) days for those who needed treatment and those who did not need treatment respectively. Among infants who required treatment for ROP, 68.18% required blood transfusion whereas among those who did not need treatment, 24.19% required blood transfusion. CONCLUSION: Lower GA, lower BW, longer duration of invasive ventilation, longer total duration of oxygen requirement and blood transfusion in first 2 weeks of life were significant in preterm infants who required treatment for ROP compared with those who did not.

Multicenter Validation of Deep Learning Algorithm ROP.AI for the Automated Diagnosis of Plus Disease in ROP.

Purpose: Retinopathy of prematurity (ROP) is a sight-threatening vasoproliferative retinal disease affecting premature infants. The detection of plus disease, a severe form of ROP requiring treatment, remains challenging owing to subjectivity, frequency, and time intensity of retinal examinations. Recent artificial intelligence (AI) algorithms developed to detect plus disease aims to alleviate these challenges; however, they have not been tested against a diverse neonatal population. Our study aims to validate ROP.AI, an AI algorithm developed from a single cohort, against a multicenter Australian cohort to determine its performance in detecting plus disease. Methods: Retinal images captured during routine ROP screening from May 2021 to February 2022 across five major tertiary centers throughout Australia were collected and uploaded to ROP.AI. AI diagnostic output was compared with one of five ROP experts. Sensitivity, specificity, negative predictive value, and area under the receiver operator curve were determined. Results: We collected 8052 images. The area under the receiver operator curve for the diagnosis of plus disease was 0.75. ROP.AI achieved 84% sensitivity, 43% specificity, and 96% negative predictive value for the detection of plus disease after operating point optimization. Conclusions: ROP.AI was able to detect plus disease in an external, multicenter cohort despite being trained from a single center. Algorithm performance was demonstrated without preprocessing or augmentation, simulating real-world clinical applicability. Further training may improve generalizability for clinical implementation. Translational Relevance: These results demonstrate ROP.AI's potential as a screening tool for the detection of plus disease in future clinical practice and provides a solution to overcome current diagnostic challenges.