INTELIGENCIA ARTIFICIAL PARA EL CRIBADO DE RETINOPATÍA DIABÉTICA: PRECISIÓN DIAGNÓSTICA, IMPLEMENTACIÓN EN ENTORNOS REALES Y DESAFÍOS ÉTICOS
Open Access
- 16 September 2026
- journal article
- Published by InvestiGO in VitalyScience Revista Científica Multidisciplinaria
- Vol. 4 (11) , 57-70
Abstract
Diabetic retinopathy (DR) is the leading cause of preventable blindness among working-age adults, and its prevalence is increasing in line with the global spread of diabetes mellitus. Objective: To analyze the scientific evidence published from 2016 to 2026 regarding the diagnostic accuracy of artificial intelligence (AI) for DR screening, its application in real-world clinical practice, and the ethics of its use. A systematic narrative literature review was conducted according to the PRISMA 2020 guidelines, involving a search of indexed databases (PubMed/MEDLINE, Scopus, Web of Science, and the Cochrane Library) for primary studies, systematic reviews, and meta-analyses published in high-impact journals. Deep learning algorithms achieve sensitivities and specificities exceeding 90% in the detection of referable PR under rigorous laboratory conditions; however, these algorithms face limitations in their diagnostic performance in external populations, particularly in low- and middle-income countries. Studies on the implementation of AI within national screening programs document increases in coverage and reductions in costs, although gaps in generalizability still persist due to issues with the representativeness of training datasets. From an ethical perspective, we identify risks of algorithmic bias, equity gaps, issues of clinical accountability, and informed consent. AI is viewed as a tool with the potential to increase access to RD screening, although its use requires rigorous external studies to validate its performance, the creation of clear regulatory frameworks, and the implementation of strategies to mitigate bias.Keywords
This publication has 23 references indexed in Scilit:
- Diagnostic Accuracy of IDX-DR for Detecting Diabetic Retinopathy: A Systematic Review and Meta-AnalysisAmerican Journal of Ophthalmology, 2025
- Artificial intelligence and digital health in global eye health: opportunities and challengesThe Lancet Global Health, 2023
- Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to DeploymentOphthalmology and Therapy, 2023
- IDF Diabetes Atlas: Global, regional and country-level diabetes prevalence estimates for 2021 and projections for 2045Diabetes Research and Clinical Practice, 2022
- Global Prevalence of Diabetic Retinopathy and Projection of Burden through 2045Ophthalmology, 2021
- Deep learning in ophthalmology: The technical and clinical considerationsProgress in Retinal and Eye Research, 2019
- Artificial intelligence using deep learning to screen for referable and vision-threatening diabetic retinopathy in Africa: a clinical validation studyThe Lancet Digital Health, 2019
- Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With DiabetesJAMA, 2017
- Automated Diabetic Retinopathy Image Assessment SoftwareOphthalmology, 2017
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJAMA, 2016