Fig. 2 | Scientific Reports

Fig. 2

From: Development and validation of a machine learning model for critical progression risk in pediatric severe community-acquired pneumonia

Fig. 2

LASSO regression results. This figure illustrates the results of the Least Absolute Shrinkage and Selection Operator (LASSO) regression used for variable selection. The left panel shows the mean-squared error (MSE) as a function of the regularization parameter (lambda) in a 10-fold cross-validation process. The vertical dashed lines indicate the optimal lambda values: the left line corresponds to the lambda that minimizes MSE, and the right line corresponds to the lambda chosen using the “one standard error rule” for more conservative variable selection. The right panel shows the coefficient paths for all candidate variables as lambda increases (moving from left to right). Based on the LASSO regression results, four key variables—RDW-CV, PCT, BUN and LDH—were identified as important predictors of cSCAP.

Back to article page