Skip to main content
. 2019 May 1;12(5):1690–1701.

Figure 3.

Figure 3

The nomogram of predicting the risk of metastasis and feature selection using the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. A. The construction of a nomogram of predicting metastasis risk in lung ADC, including CaMKII, NSE, CEA, a value of Cyfra 21-1. In the nomogram, each variable value is assigned a score, and the final sum of the scores is projected to the corresponding probability of metastasis. B. The ROC curve of the nomogram, the AUC was 0.800, with a sensitivity value of 0.929 and specificity value of 0.603. C. LASSO coefficient profiles of the 15 features. A vertical line was drawn at the value selected using 10-fold cross-validation, where optimal 1 resulted in 9 nonzero coefficients. D. Tuning parameter (Lambda) selection in the LASSO model used 10-fold cross-validation via minimum criteria. The green circle and dotted line locate the Lambda with the minimum cross-validation mean squared error (MSE).