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

Figure 1

(a) LASSO coefficient profiles of the 82 features. (b) Tuning parameter (λ) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The area under the receiver operating characteristic curve (AUC) was plotted versus . Dotted vertical lines were drawn at the optimal values by using the minimum criteria and the 1SE criteria. 14 features with nonzero coefficients were selected according to the 1SE criterion.

(a)

(b)