Fig. 3 | Scientific Reports

Fig. 3

From: Constructing a machine learning model for systemic infection after kidney stone surgery based on CT values

Fig. 3

Use of lasso regression analysis for variable selection. (a) Vertical lines were drawn over selected values using 10-fold cross validation, where the best lambda produced 10 non-zero coefficients. (b) Distribution of coefficients for 15 texture features extracted from the log (λ) sequence. Vertical dashed lines are drawn at the minimum mean square error (λ = 0.011) and the standard error of the minimum distance (λ = 0.054). optimal λ When the value is 0.011, our model selects 10variables: Operation time, Urease producing bacteria, Urine turbidity, Urine culture, Urinary protein, Degree of hydronephrosis, HU, BUN, Serum uric acid, Stone burden.

Back to article page