Fig. 2

2A. Cross-validation plot identified the optimal value at λ = 0.019. 2B. Risk factor selection using the logistic least absolute shrinkage and selection operator (LASSO) regression. The LASSO standardized coefficient profiles of the nonzero variables of the predictors. A coefficient path plot was produced against the ln(lambda) sequence. Reading from left to right, as the penalty factor (λ) increases, the standardized coefficients decrease and finally reach zero, which means exclusion from the model. At the optimal value (λ = 0.019), age, preoperative eGFR, ischemia time, intraoperative blood loss and RNS remained in the model. LASSO: logistic least absolute shrinkage and selection operator. RNS: RENAL Nephrometry Score. 2C. The calibration curve for the predictive nomogram exhibited a high agreement between the actual probability and predicted probability of the AKD transition. 2D. Decision curve analyses demonstrating the net benefit associated with the use of the nomogram-derived probability for the prediction of the transition possibility from AKI to AKD.