FIGURE 6.

NIHL risk model construction through LASSO analysis and their diagnostic power. (A) Tuning parameter lambda (λ) selection using 10-fold cross-validation. (B,C) Five and seven DMs-NIHL with the absolute value of the coefficients >0 were included in the LASSO regression models. The x-axis represented the coefficients of the metabolites, and the y-axis indicated the metabolite variables. (D,E) LASSO regression models could predicate the hearing loss status effectively through ROC curve analysis. NIHL, noise-induced hearing loss; LASSO, least absolute shrinkage and selection operator; ROC, receiver operating characteristics; AUC, area under the curve.