Abstract
AbstractBackgroundArtificial intelligence (AI) shows promise in ophthalmology, but its performance in diverse healthcare settings remains understudied. We evaluated retinIA, an AI-powered screening tool developed with Mexican data, against first-year ophthalmology residents in a tertiary care setting in Mexico City.MethodsWe analyzed 435 adult patients undergoing their first ophthalmic evaluation. RetinIA and residents’ assessments were compared against expert annotations for retinal lesions, cup-to-disk ratio (CDR) measurements, and glaucoma suspect detection. We also evaluated a synergistic approach combining AI and resident assessments.ResultsFor glaucoma suspect detection, retinIA outperformed residents in accuracy (88.6% vs 82.9%,p= 0.016), sensitivity (63.0% vs 50.0%,p= 0.116), and specificity (94.5% vs 90.5%,p= 0.062). While, the synergistic approach deemed a higher sensitivity (80.4%) than ophthalmic residents alone or retinIA alone (p <0.001). RetinIA’s CDR estimates showed lower mean absolute error (0.056 vs 0.105,p <0.001) and higher correlation with expert measurements (r= 0.728 vsr= 0.538). In retinal lesion detection, retinIA demonstrated superior sensitivity (90.1% vs 63.0% for medium/high-risk lesions,p <0.001) and specificity (95.8% vs 90.4%,p <0.001). Furthermore, differences between retinIA and residents were statistically significant across all metrics. The synergistic approach achieved the highest sensitivity for retinal lesions (92.6% for medium/high-risk, 100% for high-risk) while maintaining good specificity (87.4%).ConclusionRetinIA outperforms first-year residents in key ophthalmic assessments. The synergistic use of AI and resident assessments shows potential for optimizing diagnostic accuracy, highlighting the value of AI as a supportive tool in ophthalmic practice, especially for earlycareer clinicians.
Publisher
Cold Spring Harbor Laboratory