Prediction and stratification for the surgical adverse events after minimally invasive esophagectomy: A two-center retrospective study

Figure 1 Work flow of research. MIE: Minimally invasive esophagectomy; SAE: Severe adverse event.

Figure 2 Kaplan-Meier curves of the length of stay for severe adverse event and non-severe adverse event. SAE: Severe adverse event.

Figure 3 LASSO regression curves. A: The curve of the regression coefficient vs log (λ); B: The curve of mean squared error vs log (λ).

Figure 4 Forest plots of risk factors for severe adverse events after minimally invasive esophagectomy. OR: Odds ratio; CI: Confidence interval; COPD: Chronic obstructive pulmonary disease; FEV1: Forced expiratory volume in 1 second; Ca: Calcium.

Figure 5 Nomogram of prediction model. AC: Alcohol consumption; COPD: Chronic obstructive pulmonary disease; FEV1: Forced expiratory volume in the first second; Ca: Calcium; SAE: Severe adverse event.

Figure 6 Receiver operating characteristic curves of prediction model in train set and validation set. A: Receiver operating characteristic curves of train set; the area under the curve of prediction model was 0.889 (95% confidence interval: 0.853-0.926); B: Receiver operating characteristic curves of validation set; the area under the curve of prediction model was 0.793 (95% confidence interval: 0.701-0.884).

Figure 7 Optimal cut-point stratification validation for risk stratification model. A: The best cut-point values are 16.98; B: Validation of risk stratification model in validation set. SAE: Severe adverse event.