Prognostic nomogram and risk factors for predicting survival in patients with pT2N0M0 esophageal squamous carcinoma

Abstract

This study analyzed the impact of factors affecting overall survival in patients with pT2N0M0 esophageal squamous carcinoma (ESCC) and developed a nomogram to predict overall survival (OS). We reviewed the clinical data of 413 patients with pathological T2N0M0 ESCC after radical esophagectomy in two hospitals. Data from one institution was used as the training cohort. A nomogram was established using Cox proportional hazard regression for identifying the prognostic factors affecting for OS in ESCC patients. The area under the curve (AUC), calibration curves and decision curve analysis (DCA) were used to evaluate prognostic efficacy, which was validated in an independent validation cohort. In the training cohort (N = 304), the median OS was 69.33 months, and the 3-, 5- and 10-year OS rates were 76.80%, 67.00% and 56.90%, respectively. The median OS of the validation cohort (N = 109) was 73.50 months, and the 3-, 5- and 10-year OS rates were 77.00%, 67.80% and 55.60%, respectively. According to Cox univariate and multivariate analyses, sex, age, tumor length and the number of resected lymph nodes were identified as predictors of OS. We developed nomograms and performed internal and external validation. The time-dependent receiver operating characteristic (ROC) curve and area under the curve (AUC) value, calibration curve and decision curve analysis (DCA) showed good prediction ability of the nomogram. The developed nomogram can effectively predict OS after esophagectomy in patients with pT2N0M0 ESCC.

Figure 1

Kaplan–Meier curves for the OS of the training cohort. Age group (A), sex group (B), length group (C), lymph node metastasis (LNM) group (D).

Figure 2

Nomogram predicting the 3-,5- and 10-year OS rates from the training cohort.

Figure 3

(A) ROC curves for 3-, 5-, and 10-year OS based on the nomogram for the training cohort. (B) Calibration curve of predicted 3-year OS. (C) Calibration curve of the predicted 5-year OS. (D) Calibration curve of the predicted 10-year OS.

Figure 4

(A) ROC curves for 3-, 5-, and 10-year OS based on the nomogram for the validation cohort. (B) Time-dependent AUC curve showing the performance of the nomogram in predicting OS in the validation cohort. (C) Calibration curve of the predicted 3-year OS. (D) Decision curve analysis for 3-year OS.