Comparison of AI-Based Retinal Fluid Monitoring in Neovascular Age-Related Macular Degeneration with Manual Assessment by Different Eye Care Professionals Under Optimized Conditions

AI Generated Summary*

Seventeen eye care professionals, from retinologists and residents to general ophthalmologists, orthoptists and reading centre graders, judged intraretinal and subretinal fluid presence and change on routine OCT scans, without time limits, across 124 visit pairs in 59 eyes treated with anti-VEGF for neovascular AMD. Group majority votes were benchmarked against an MDR-approved deep learning quantification tool using a 5 nL presence threshold. Sensitivity ran 0.81 to 0.95 for IRF and 0.89 to 0.98 for SRF, specificities 0.74 to 0.91; kappa against the algorithm was 0.69 to 0.82 and 0.73 to 0.79 respectively, and AUCs separating increase from decrease reached 0.89 or higher. Accuracy appeared similar irrespective of experience, though manual grading fell short of automated measurement in this retrospective sample.

*This summary was generated by AI and is published unedited. Oku does not alter these summaries. It may contain errors or omissions and is provided for general informational purposes only. Oku does not guarantee its accuracy, completeness, or reliability. For authoritative information, please refer to the original, peer-reviewed article.