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

Abstract

Background: Minimally invasive esophagectomy (MIE) is a widely accepted treatment for esophageal cancer, yet it is associated with a significant risk of surgical adverse events (SAEs), which can compromise patient recovery and long-term survival. Accurate preoperative identification of high-risk patients is critical for improving outcomes.

Aim: To establish and validate a risk prediction and stratification model for the risk of SAEs in patients with MIE.

Methods: This retrospective study included 747 patients who underwent MIE at two centers from January 2019 to February 2024. Patients were separated into a train set (n = 549) and a validation set (n = 198). After screening by least absolute shrinkage and selection operator regression, multivariate logistic regression analyzed clinical and intraoperative variables to identify independent risk factors for SAEs. A risk stratification model was constructed and validated to predict the probability of SAEs.

Results: SAEs occurred in 10.2% of patients in train set and 13.6% in the validation set. Patients with SAE had significantly higher complication rate and a longer hospital stay after surgery. The key independent risk factors identified included chronic obstructive pulmonary disease, a history of alcohol consumption, low forced expiratory volume in the first second, and low albumin levels. The stratification model has excellent prediction accuracy, with an area under the curve of 0.889 for the training set and an area under the curve of 0.793 for the validation set.

Conclusion: The developed risk stratification model effectively predicts the risk of SAEs in patients undergoing MIE, facilitating targeted preoperative interventions and improving perioperative management.

Keywords: Esophageal cancer; Minimally invasive esophagectomy; Perioperative management; Stratification model; Surgical adverse events.

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.