Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population

Frontiers in Pediatrics

Pediatrics

Joshua Zhi En Tan¹  Brian Pei-En Fung¹  Chiran Mandula Bopitiya¹  Florian M. Savoy¹  Divya Parthasarathy Rao²  Anand Sivaraman³  Anand Vinekar⁴ 

[1] Artificial Intelligence Research and Development, Medios Technologies Pvt. Ltd., Singapore, Singapore;Artificial Intelligence Research and Development, Remidio Innovative Solutions Inc., United States;Artificial Intelligence Research and Development, Remidio Innovative Solutions Pvt. Ltd., India;Department of Pediatric Retina, Narayana Nethralaya Eye Institute, Bangalore, India;

关键词: retinopathy of prematurity;    artificial intelligence;    screening;    deep learning;    accessibility;    ROP;    infant blindness;    AI;   

DOI  :  10.3389/fped.2023.1197237

 received in 2023-03-30, accepted in 2023-08-29,  发布年份 2023

来源: Frontiers

【 摘 要 】

PurposeThe primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP).ParticipantsImages were collected from infants enrolled in the KIDROP tele-ROP screening program.MethodsWe developed a deep learning (DL) algorithm with 227,326 wide-field images from multiple camera systems obtained from the KIDROP tele-ROP screening program in India over an 11-year period. 37,477 temporal retina images were utilized with the dataset split into train (n = 25,982, 69.33%), validation (n = 4,006, 10.69%), and an independent test set (n = 7,489, 19.98%). The algorithm consists of a binary classifier that distinguishes between the presence of ROP (Stages 1–3) and the absence of ROP. The image labels were retrieved from the daily registers of the tele-ROP program. They consist of per-eye diagnoses provided by trained ROP graders based on all images captured during the screening session. Infants requiring treatment and a proportion of those not requiring urgent referral had an additional confirmatory diagnosis from an ROP specialist.ResultsOf the 7,489 temporal images analyzed in the test set, 2,249 (30.0%) images showed the presence of ROP. The sensitivity and specificity to detect ROP was 91.46% (95% CI: 90.23%–92.59%) and 91.22% (95% CI: 90.42%–91.97%), respectively, while the positive predictive value (PPV) was 81.72% (95% CI: 80.37%–83.00%), negative predictive value (NPV) was 96.14% (95% CI: 95.60%–96.61%) and the AUROC was 0.970.ConclusionThe novel ROP screening algorithm demonstrated high sensitivity and specificity in detecting the presence of ROP. A prospective clinical validation in a real-world tele-ROP platform is under consideration. It has the potential to lower the number of screening sessions required to be conducted by a specialist for a high-risk preterm infant thus significantly improving workflow efficiency.

【 授权许可】

Unknown   
© 2023 Rao, Savoy, Tan, Fung, Bopitiya, Sivaraman and Vinekar.