Objective:

To develop and validate a predictive model for assessing the risk of anastomotic leakage (AL) in esophageal cancer patients undergoing esophagectomy.

Approach:

• Study Design: Retrospective cohort study including 650 esophageal cancer patients who underwent esophagectomy, divided into a training set (n = 455) and a validation set (n = 195).
• Data Collection: Collected baseline demographic, clinicopathological, and laboratory data, with AL as the primary outcome defined by the Esophagectomy Complications Consensus Group (ECCG).
• Statistical Analysis: Utilized univariable and multivariable logistic regression, restricted cubic splines (RCS), and nomogram development to identify predictors, assessing model performance with ROC curve, calibration plots, and decision curve analysis (DCA).

Key Findings:

• Seven significant predictors of AL were identified: age, neoadjuvant radiotherapy, C-reactive protein-albumin-lymphocyte (CALLY) index, hypertension, neutrophil-to-lymphocyte ratio (NLR), neutrophil-to-monocyte ratio (NMR), and platelet-to-lymphocyte ratio (PLR).
• The nomogram model developed showed good discrimination with an area under the curve (AUC) of 0.813 in the training set.
• The validation cohort demonstrated moderate predictive accuracy with an AUC of 0.763, and decision curve analysis indicated consistent net benefits across different risk thresholds.

Interpretation:

The study established a predictive model for AL risk that may facilitate individualized risk stratification.

Limitations:

• Retrospective design may introduce selection bias.
• Single-center study limits generalizability of findings.

Conclusion:

The predictive model for AL risk may assist in clinical decision-making.