Machine Learning-Driven Identification of Hematological and Immunological Biomarkers for Predicting Proliferative Diabetic Retinopathy Progression.

Purpose: Proliferative Diabetic Retinopathy (PDR) is a severe complication of diabetes characterized by neovascularization and retinal detachment, leading to significant vision loss. This study investigates the predictive power of hematological and immunological markers in PDR progression.

Methods: Data from 126 patients were analyzed using advanced machine learning techniques, including LASSO regression, elastic net modeling, and backward stepwise regression.

Results: The findings identified age, gender, IL-1, and lymphocyte count (LYM) as significant predictors of PDR, with a high AUC value of 0.839 from the ROC curve analysis. These markers, particularly cytokines in the aqueous humor and peripheral blood, offer a convenient and rapid method for early detection and risk assessment of PDR.

Conclusions: Despite the limitations of being a cross-sectional study with a relatively small sample size, the results highlight the clinical significance of these biomarkers and underscore the need for further validation in larger, more diverse populations. This study contributes to the development of targeted interventions and improved management strategies for diabetic retinopathy, emphasizing the importance of immunological health in disease progression.