Fig. 1

Model interpretation using Shapley additive explanations (SHAP), calculated with the test dataset. The SHAP value, which represents the average impact on the model’s output for each feature, is shown on the left, and the distribution of the SHAP values is given on the right. The red dots represent greater feature values, while the blue dots represent smaller values. Positive SHAP values indicate positive contributions to the model’s prediction of RNFL thinning, and negative values indicate negative contributions. RNFLT, retinal nerve fiber layer thickness; AST, aspartate aminotransferase; IOP, intraocular pressure; SBP, systolic blood pressure; HDL, high-density lipoprotein cholesterol; ALT, alanine aminotransferase; DBP, diastolic blood pressure; ALP, alkaline phosphatase; LDL, low-density lipoprotein cholesterol; BUN, blood urea nitrogen; BMI, body mass index; TG, triglyceride; Hb, hemoglobin.