Fig. 2.

Variable selection by the LASSO binary logistic regression model. A coefficient profile plot was constructed against the log(λ) sequence. A, Association between coefficient of variables and (λ). Each line corresponded to one distinct variable. Along with the increasing log (λ), the coefficient of variable trended to be close to 0. B, The selection of applicable model. We plotted the misclassification versus Log (λ). Vertical lines were drawn at the optimal values by adopting the minimum criteria (dashed line) and the 1 standard error of the minimum criteria (red dotted line, the 1-SE criteria). In our study, the (λ) value of 0.012832 was chosen according the the 1-SE criteria. Note that 7 variables were selected at last including BMI, Family history of PCAD, Glucose, total cholesterol, Triglyceride, ApoA1, HDL2-C. LASSO, least absolute shrinkage and selection operator; SE, standard error; BMI, body mass index; PCAD, premature coronary artery disease. ApoA1, apolipoprotein 1; HDL2-C, high density lipoprotein 2 cholesterol.