AI Prediction of Treatment Response in DME

Diabetic macular edema (DME) is a leading cause of vision loss among individuals with diabetes mellitus. Although intravitreal anti-vascular endothelial growth factor (anti-VEGF) therapy is the standard treatment for center-involved DME, treatment response varies considerably between patients. Recent advances in artificial intelligence (AI), including machine learning (ML) and deep learning (DL), have enabled automated analysis of retinal imaging biomarkers to predict anatomical and functional treatment outcomes. This study aims to systematically evaluate published evidence regarding AI-based prediction models and imaging biomarkers used to predict treatment response in patients with DME. The review will assess the predictive performance of AI models, identify the most important imaging biomarkers, compare different AI approaches and imaging modalities, and summarize methodological strengths, limitations, and research gaps to support future development of precision ophthalmology.

Inclusion Criteria: * Adults aged 18 years or older. * Diagnosis of diabetic macular edema (DME) confirmed by clinical examination and optical coherence tomography (OCT). * Treatment with intravitreal anti-vascular endothelial growth factor (anti-VEGF), intravitreal corticosteroids, focal/grid laser photocoagulation, or combination therapy. * Availability of baseline retinal imaging, including OCT, OCT angiography (OCTA), fundus photography, or multimodal imaging suitable for artificial intelligence analysis. * Availability of baseline and follow-up best-corrected visual acuity (BCVA) and central retinal thickness (CRT) measurements. * Complete demographic and clinical data required for model development or validation. * Minimum follow-up of 3 months after initiation of treatment. Exclusion Criteria: * Macular edema due to causes other than diabetes. * Previous vitreoretinal surgery in the study eye. * Coexisting retinal diseases that may affect visual or anatomical outcomes (e.g., retinal vein occlusion, age-related macular degeneration, uveitis, inherited retinal disorders). * Significant media opacity resulting in poor-quality retinal imaging. * Incomplete clinical records or missing imaging data. * Follow-up duration less than 3 months. * Images that fail quality-control criteria for artificial intelligence analysis.