Development and validation of a novel competing risk model for predicting survival of esophagogastric junction adenocarcinoma: a SEER population-based study and external validation

Abstract

Background Adenocarcinoma in Esophagogastric Junction (AEG) is a severe gastrointestinal malignancy with a unique clinicopathological feature. Hence, we aimed to develop a competing risk nomogram for predicting survival for AEG patients and compared it with new 8th traditional tumor-node-metastasis (TNM) staging system. Methods Based on data from the Surveillance, Epidemiology, and End Results (SEER) database of AEG patients between 2004 and 2010, we used univariate and multivariate analysis to filter clinical factors and then built a competing risk nomogram to predict AEG cause-specific survival. We then measured the clinical accuracy by comparing them to the 8th TNM stage with a Receiver Operating Characteristic (ROC) curve, Brier score, and Decision Curve Analysis (DCA). External validation was performed in 273 patients from China National Cancer Center. Results A total of 1755 patients were included in this study. The nomogram was based on five variables: Number of examined lymph nodes, grade, invasion, metastatic LNs, and age. The results of the nomogram was greater than traditional TNM staging with ROC curve (1-year AUC: 0.747 vs. 0.641, 3-year AUC: 0.761 vs. 0.679, 5-year AUC: 0.759 vs. 0.682, 7-year AUC: 0.749 vs. 0.673, P \u2009<\u20090.001), Brier score (3-year: 0.198 vs. 0.217, P \u2009=\u20090.012; 5-year: 0.198 vs. 0.216, P \u2009=\u20090.008; 7-year: 0.199 vs. 0.215, P \u2009=\u20090.014) and DCA. In external validation, the nomogram also showed better diagnostic value than traditional TNM staging and great prediction accuracy. Conclusion We developed and validated a novel nomogram and risk stratification system integrating clinicopathological characteristics for AEG patients. The model showed superior prediction ability for AEG patients than traditional TNM classification.