Português 
Español 
English 
MAGAZINE
Telemed J E Health
Diagnostic Performance of an Artificial Intelligence Model for Retinal Abnormalities in Primary Health Care: A Real-World Teleophthalmology Study
AUTHORS & DATE
Alan Cristian Marinho Ferreira, Mariana Abreu Caporali de Freitas, Rosangela Durso Perillo, Carlos Eduardo Menezes Amaral, Alaneir de Fátima Santos
22/05/2026
Abstract
Background
Timely access to ophthalmological care is a challenge in primary health care (PHC) Teleophthalmology and artificial intelligence (AI) are tools to expand access, but real-world evidence remains limited. This study evaluates the diagnostic performance of an AI model for detecting retinal abnormalities in PHC, analyzing variability across clinical and demographic subgroups.
Methods
This cross-sectional study analyzed 2,158 initial retinal exams, resulting in a final paire sample of 824 retinographies for accuracy analysis. The exams were conducted within a teleophthalmology workflow in the PHC of six municipalities in Minas Gerais, Brazil. A commercia AI model based on a convolutional neural network (Eyer Maps ) evaluated the images and was compared with classifications performed by an ophthalmologist, considered the reference standard. Cluster analysis was performed, and sensitivity, specificity, positive and negative predictive values, Cohen's Kappa coefficient, and area under the receiver operating characteristic curve (AUC) were calculated.
Results
This cross-sectional study analyzed 2,158 initial retinal exams, resulting in a final paire sample of 824 retinographies for accuracy analysis. The exams were conducted within a teleophthalmology workflow in the PHC of six municipalities in Minas Gerais, Brazil. A commercia AI model based on a convolutional neural network (Eyer Maps ) evaluated the images and was compared with classifications performed by an ophthalmologist, considered the reference standard. Cluster analysis was performed, and sensitivity, specificity, positive and negative predictive values, Cohen's Kappa coefficient, and area under the receiver operating characteristic curve (AUC) were calculated.
Conclusion
In a real-world teleophthalmology context within PHC, AI showed robust diagnostic performance and a high capacity for confirming retinal abnormalities, minimizing unnecessary referrals. The findings reinforce its potential as a supportive tool for organizing ophthalmological care and optimizing assistance workflows in PHC.
