Risk factors of prolonged mechanical ventilation after acute type A aortic dissection surgery: a single-center retrospective study

Figures

• 

  Figure 1. Flow diagram of patient inclusion and exclusion according to STROBE guidelines.

• 

  Figure 2. Demographic and clinical feature selection using lasso binary logistic regression model. (A) Tuning parameters λ were obtained through 10 times crossvalidation with the minimum standard, the partial likelihood deviance curve was drawn through Log (λ), and the minimum standard and 1-SE standard were used to draw the vertical dotted line, after 10 times cross-validation, the Log (λ) was determined to be 0.027 (1-SE standard) at the optimal value. (B) Lasso coefficient profiles of the 9 features. A coefficient profile plot was produced against the log (λ) sequence. The vertical line was drawn at the value selected using 10fold cross-validation, where optimal resulted in 6 features with non-zero coefficients.

• 

  Figure 3. ROC analysis, calibration curves and DCA for delayed extubation. Plots (A) shows the nomogram analysis of delayed extubation. Plots (B) shows the ROC analysis of delayed extubation. Plots (C) Calibration curves of the prediction model. Calibration curves depicted the calibration of the model. The 45◦ line represents a perfect prediction, and the red line and green line represent the actual prediction and bootstrap adjusted curve respectively. Plots (D) show DCA of Model for delayed extubation. Plots (E) show clinical impact curve of Model for delayed extubation. AUC, area under the receiver operating characteristic curve; CI, confidence interval; DCA, decision curve analysis; ROC, receiver operating characteristic.