Figure 1 | Scientific Reports

Figure 1

From: Predicting bleeding risk in a Chinese immune thrombocytopenia (ITP) population: development and assessment of a new predictive nomogram

Figure 1

Results for demographic and clinical feature selection by the LASSO binary logistic regression model. Notes The optimabest parameter (lambda) of the lasso model, which is selected by the minimum criterion for five cross verifications, shown in (A). The binomial deviance curve was plotted depended on log(lambda). According to the minimum criteria and the 1-SE criteria, dotted vertical lines were drawn at the optimal values. (B) Showed LASSO coefficient profiles of the 19 features. A coefficient profile plot was produced based on the log(lambda) sequence. Vertical line was drawn at the value selected using fivefold cross-validation, where optimal lambda resulted in eight features with nonzero coefficients. LASSO least absolute shrinkage and selection operator, SE standard error.

Back to article page