Figure 2

PLT-based score models selection using the LASSO binary logistic regression model. (A) The Optimum parameter (lambda) selection in the LASSO model performed fivefold cross-validation through minimum criteria. The partial likelihood deviance (binomial deviance) curve was presented versus log (lambda). Dotted vertical lines were showed at the optimum values by performing the minimum criteria and the 1 SE of the minimum criteria (the 1-SE criteria). (B) The LASSO coefficient profiles of the 9 features. The coefficient profile plot was evaluated against the log (lambda) sequence. Vertical line was shown at the value selected using cross-validation, where the optimum lambda gave rise to four features with nonzero coefficients.