Inconsistencies in the Diagnosis of Aggressive Posterior Retinopathy of Prematurity

Purpose: To determine the accuracy and reliability of diagnosing aggressive posterior retinopathy of prematurity (AP-ROP). Methods: A total of 1220 eye examinations from 230 infants were prospectively obtained at 8 major ROP centers. An ophthalmologist at each center provided a clinical diagnosis using indirect ophthalmoscopy. Wide-angle retinal images were then obtained, which were independently read by 2 ROP experts using a web-based system for an image-based diagnosis. Sensitivity and specificity of image-based AP-ROP diagnosis by the ROP experts were calculated using the clinical diagnosis as the reference standard. Agreement of AP-ROP diagnosis through image-based diagnosis and clinical diagnosis was calculated using the unweighted κ statistic. Results: One hundred four (9%) of the 1220 examinations had a clinical diagnosis of AP-ROP. Sensitivity and specificity for the presence of AP-ROP were 35% and 96% for expert 1 and 17% and 99% for expert 2. Using the κ statistic, expert image-based versus clinical diagnostic agreement for the diagnosis of AP-ROP was 0.34 (fair) for expert 1 and 0.24 (fair) for expert 2. Agreement for the diagnosis of AP-ROP between the image-based diagnoses of expert 1 and expert 2 was 0.49 (moderate). Conclusion: There are inconsistencies between the clinical diagnosis of AP-ROP (as determined by indirect ophthalmoscopy) and the image-based diagnosis of AP-ROP. This may have important implications for ROP management and the current international ROP classification system.