Fig. 2 | Scientific Reports

Fig. 2

From: Preoperative prediction of major adverse outcomes after total arch replacement in acute type A aortic dissection based on machine learning ensemble

Fig. 2

Construction of prediction model. (A) Error curve of RSF. (B) GBM reaches the minimum residual value at 8640 iterations. (C) Variables are ranked from large to small according to the average SHAP value in SHAP analysis. A SHAP value greater than 0 indicates that the result is more likely to occur due to the predicted value. Only the top-ranked variables are shown in the figure. CK-MB, Creatine kinase-MB; eGFR, estimated glomerular filtration rate; APTT, activated partial thromboplastin time; INR, International Normalized Ratio.

Back to article page