Fig. 1

Use of the LASSO regression to select the variables in the training set. a We use the method of 10 times cross-validation to select the optimal value of λ. The value of parameter λ is determined by the mean square error. We chose the λ value with the lowest mean square error. The λ value was 0.004. b Twenty-two variables were screened by LASSO regression, among which the optimal λ resulted in 17 nonzero coefficients