Fig. 2From: Machine learning model identifies aggressive acute pancreatitis within 48 h of admission: a large retrospective studyFeatures selection by Lasso regression. The figure shows the relationship between the log (λ), the number of features in the model, and the mean square error (MSE). λ is the optional user-supplied lambda sequence. Dashed vertical lines were drawn at the optimal values by using the minimum criteria and the 1 standard error of the minimum criteria (the 1-SE criteria). The left dashed line represents the model achieved the minimum MSE with corresponding log(λ) and number of features. The right dashed line represents log(λ) of 1 standard error from MSE with corresponding number of featuresBack to article page