Construction and verification of 5-year survival prediction model for post-op ESCC patients

To develop a predictive model for the 5-year postoperative survival rate of patients with esophageal squamous cell carcinoma (ESCC), and to provide a basis for the accurate assessment of clinical prognosis.

A total of 260 ESCC patients who underwent surgery between January 2017 and June 2019 were included and randomly divided into a training set (n=182) and a validation set (n=78) at a 7:3 ratio. Univariate and multivariate Cox proportional hazards regression analyses were performed in the training set to identify independent predictors of 5-year overall survival (OS). A nomogram was constructed based on the selected factors. The model's performance was evaluated using the concordance index (C-index), calibration curves, time-dependent receiver operating characteristic (ROC) curves, and decision curve analysis (DCA).

The 5-year OS rate in the training set was 63.7% (116/182). Multivariate Cox regression identified five independent predictors of 5-year OS: American Joint Committee on Cancer stage (HR = 1.347, 95% CI: 1.209-1.510), lymph node metastasis (HR = 4.698, 95% CI: 3.282-8.994), tumor differentiation grade (HR = 1.235, 95% CI: 1.105-1.276), microvessel density (HR = 1.089, 95% CI: 1.023-1.159), and Vascular Endothelial Growth Factor (VEGF) expression (HR = 2.451, 95% CI: 1.127-6.372). The nomogram demonstrated good discrimination, with C-index values of 0.886 (training set) and 0.845 (validation set). The areas under the ROC curves were 0.889 (95% CI: 0.822-0.955) and 0.844 (95% CI: 0.695-0.992), respectively. Calibration curves and DCA indicated satisfactory agreement and clinical net benefit across a wide threshold probability range.

The nomogram integrating clinicopathological and molecular factors effectively predicts 5-year OS in ESCC patients after surgery, offering a reliable visual tool for individualized risk stratification and clinical decision-making.