Explainable Machine Learning-Based Prediction Model for Diabetic Nephropathy

Figure 3

(a) LASSO coefficient profiles of 119 features; (b) the value of with the smallest mean error is selected by 10-fold cross-validation. (a) Each line represents a feature, and each estimated parameter decreases as increases until it compresses to 0. (b) The relationship between the mean square error and is plotted. Vertical dashed lines are plotted at the best value using the minimum criterion and the 1SE principle. Based on 10-fold cross-validation, the value of 0.017 was selected and the optimal number of features was obtained as 38.

(a)

(b)