Retinopathy of prematurity (ROP): diagnostic accuracy of AI on retinal imaging for plus disease using wide-field retinal fundus photos
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This study is a systematic review and meta-analysis examining the diagnostic accuracy of artificial intelligence (AI)–based models for detecting plus disease and treatment-requiring retinopathy of prematurity (ROP) in preterm infants. ROP remains one of the leading causes of preventable childhood blindness, and identification of plus disease is central to treatment decisions. However, assessment based on wide-field digital retinal imaging (WFDRI) is subject to inter-observer variability and depends heavily on the availability of experienced ophthalmic graders. AI-driven image analysis has been proposed as a scalable approach to support screening and improve diagnostic consistency. The review will be conducted in accordance with PRISMA guidance. A comprehensive search will be performed in PubMed, Scopus, and Web of Science up to November 2025, with additional screening of reference lists. Eligible studies include original peer-reviewed human investigations evaluating AI algorithms applied to wide-field retinal fundus images, using expert human grading as the reference standard. Outcomes of interest include diagnostic accuracy measures such as sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Study selection, data extraction, and methodological quality assessment will be undertaken independently by multiple reviewers using standardized appraisal tools, including the Joanna Briggs Institute checklist for diagnostic test accuracy studies.
Fields of Study & Subjects
Retinopathy of Prematurity Studies
Retinal Imaging and Analysis
Artificial Intelligence in Healthcare and Education
Publication details
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Preprint