Fig. 2From: Establishment and validation of a nomogram predicting the risk of deep vein thrombosis before total knee arthroplastyDemographic and clinical risk factors selection using the LASSO binary logistic regression model. (A) The lasso model was cross-validated using the minimum criterion, with dashed vertical lines plotted at the optimal values (8 factors). (B) The 55 feature LASSO coefficient profiles for logarithmic (lambda) sequences are constructedBack to article page