Purpose: This study describes the initial development of a deep learning algorithm, ROP.AI, to automatically diagnose retinopathy of prematurity (ROP) plus disease in fundal images. Methods: ROP.AI was trained using 6974 fundal images from Australasian image databases. Each image was given a diagnosis as part of real-world routine ROP screening and classified as normal or plus disease. The algorithm was trained using 80% of the images and validated against the remaining 20% within a hold-out test set. Performance in diagnosing plus disease was evaluated against an external set of 90 images. Performance in detecting pre-plus disease was also tested. As a screening tool, the algorithm's operating point was optimized for sensitivity and negative predictive value, and its performance reevaluated. Results: For plus disease diagnosis within the 20% hold-out test set, the algorithm achieved a 96.6% sensitivity, 98.0% specificity, and 97.3% ± 0.7% accuracy. Area under the receiver operating characteristic curve was 0.993. Within the independent test set, the algorithm achieved a 93.9% sensitivity, 80.7% specificity, and 95.8% negative predictive value. For detection of pre-plus and plus disease, the algorithm achieved 81.4% sensitivity, 80.7% specificity, and 80.7% negative predictive value. Following the identification of an optimized operating point, the algorithm diagnosed plus disease with a 97.0% sensitivity and 97.8% negative predictive value. Conclusions: ROP.AI is a deep learning algorithm able to automatically diagnose ROP plus disease with high sensitivity and negative predictive value. Translational Relevance: In the context of increasing global disease burden, future development may improve access to ROP diagnosis and care.

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.

Objective Early detection of ocular abnormalities in newborn infants is essential for timely diagnosis and treatment. This study aimed to assess wide-field digital imaging for universal newborn eye screening (UNES) to determine the prevalence of ocular abnormalities, including retinal haemorrhages, in newborn infants in New Zealand. Design Prospective ocular screening study of infants. Setting A public hospital maternity ward and a community birth centre in Auckland, New Zealand. Patients A total of 350 infants were enrolled in UNES, those with birth weight <1250 g or gestational age <30 weeks were excluded. Methods Wide-field digital images of the external eye and retina were captured by RetCam (Natus Medical, San Carlos, California, USA) and reviewed by an ophthalmologist via an established telemedicine methodology. Main outcome measures Detection of ocular abnormalities, including retinal haemorrhages. Correlation between haemorrhages and maternal, obstetric and neonatal factors. Results A total of 346 infants completed screening (median age 2 days). Retinal haemorrhages were present in 50 cases (14.5%), two cases exhibited persistent retinal haemorrhages at 6-week follow-up. A significant increase in the odds of retinal haemorrhages was present for vaginal delivery compared with caesarean section. Other ocular abnormalities, including congenital cataract and optic nerve hypoplasia, were present in 1.4% of infants. Conclusions Ocular abnormalities were detected by UNES including congenital cataract and optic nerve hypoplasia. However, retinal haemorrhages, significantly associated with delivery modality, were the most common abnormality detected. The majority of retinal haemorrhages resolved spontaneously.