A Metabolism-Based Interpretable Machine Learning Prediction Model for Diabetic Retinopathy Risk: A Cross-Sectional Study in Chinese Patients with Type 2 Diabetes

Figure 3

The calibration curve of predictive models. Red line means XGBoost model with LASSO selection features (Brier score = 0.090), green line means Logistic Regression model with LASSO selection features (Brier score = 0.099), blue line means XGBoost model with conventional features (Brier score = 0.120), yellow line means Logistic Regression model with conventional features (Brier score = 0.103), grey dotted line means perfectly calibrated.