Skip to main content
Fig. 2 | Lipids in Health and Disease

Fig. 2

From: Development and validation of a new nomogram to screen for MAFLD

Fig. 2

Variables selection using the LASSO regression. A Selection of the tuning parameter lambda in the LASSO model via tenfold cross-validation based on minimum criteria. Mean-squared error (MSE) from the LASSO regression cross-validation procedure was plotted as a function of log lambda. The y-axis indicates the MSE. The x-axis indicates the log lambda. Numbers along the upper x-axis represent the average number of predictors. Red dots indicate average MSE values for each model with a given lambda, and vertical bars through the red dots show the upper and lower values of the MSE. The vertical black lines define the optimal values of lambda, where the model provides its best fit to the data based on 1 standard error criteria. The optimal lambda value of 0.014 with log lambda = -4.269 was selected. B The LASSO coefficient profiles of clinical features. The dotted vertical line was plotted at the value selected using tenfold cross-validation in A. The nine resulting variables with non-zero coefficients are indicated in the plot

Back to article page