This study investigated the potential of using automated Optical Coherence Tomography (OCT) analysis, specifically retinal layer smoothness index (SI) and area (S), as biomarkers for diabetic retinopathy (DR). The researchers found significant differences in the area of the inner nuclear layer (INL) and outer nuclear layer (ONL) in the central vision area (foveal zone) across healthy eyes, non-proliferative DR (NPDR), and proliferative DR (PDR). Additionally, the smoothness of the inner plexiform layer (IPL) and outer plexiform layer (OPL) borders in the sides of the retina (nasal and temporal regions) differed significantly between the groups. The INL area in the fovea showed the best accuracy (87.6%) in distinguishing DR from normal eyes, while the IPL smoothness in the nasal region was most accurate (97.2%) in differentiating PDR from NPDR. The study suggests that analyzing retinal layer smoothness and area using OCT could be a valuable tool for detecting and classifying DR, with the nasal and temporal regions potentially being key for distinguishing between NPDR and PDR. Further research in larger populations is needed to validate these findings and explore their use in improving DR detection and management.