The purpose of this multi-center study is to evaluate the extent to which AI-assisted fundus image interpretation improves the diagnostic performance of ophthalmologists. Rather than assessing the standalone algorithm performance, this study aims to determine the clinical value of using AI as a decision-support tool within actual clinical workflows. At each participating institution, five ophthalmologists within three years of board certification and five ophthalmology residents will participate as readers. All readers will interpret fundus images both with and without the AI-based assistance software. The study will quantitatively compare diagnostic accuracy and reading time across the two conditions for four posterior segment diseases: diabetic retinopathy, age-related macular degeneration, retinal vein occlusion, and glaucoma.
Study Type
INTERVENTIONAL
Allocation
NON_RANDOMIZED
Purpose
DIAGNOSTIC
Masking
NONE
Enrollment
10
The intervention consists of an AI-based fundus image interpretation software that provides automated outputs for 12 retinal and optic nerve findings (e.g., hemorrhage, exudates, drusen, optic disc change). The system does not generate a direct disease diagnosis. Instead, the AI displays the presence or absence of 12 predefined findings along with their lesion locations. Readers may use this finding-level information as decision-support when determining the presence of the four target diseases (diabetic retinopathy, age-related macular degeneration, retinal vein occlusion, and glaucoma).
Inje University Busan Paik Hospital
Busan, South Korea
Dong-A University Hospital
Busan, South Korea
Pusan National University Hospital
Busan, South Korea
Kosin University Gospel Hospital
Busan, South Korea
Pusan National University Yangsan Hospital
Yangsan, South Korea
Performance of readers with and without AI assistance: Sensitivity
Sensitivity of reader diagnoses for each of the four target diseases (DR, AMD, RVO, glaucoma) will be assessed with and without AI assistance, using the image-level reference standard as the comparator, through two reading sessions in which all 10 readers review all cases-randomised for each reader-with a washout period implemented to mitigate recall bias.
Time frame: Through study completion, approximately 2 months
Performance of readers with and without AI assistance: Specificity
Specificity of reader diagnoses for each of the four target diseases (DR, AMD, RVO, glaucoma) will be assessed with and without AI assistance, using the image-level reference standard as the comparator, through two reading sessions in which all 10 readers review all cases-randomised for each reader-with a washout period implemented to mitigate recall bias.
Time frame: Through study completion, approximately 2 months
Reading time per image
Reading time per image will be measured during both unassisted and AI-assisted interpretation sessions. For each case, the total time from the moment the image is displayed to the moment the reader submits the final disease classification will be recorded automatically by the reading platform. Mean reading time per image will be calculated for each reader and compared between the two conditions to evaluate whether AI assistance reduces interpretation time.
Time frame: Through study completion, approximately 2 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.