Comparison of proximal and distal gastric neuroendocrine carcinoma based on SEER database

The occurrence of gastric neuroendocrine carcinoma (GNEC) is on the rise, and its prognosis is extremely poor. We compared survival outcomes between distal and proximal GNEC and developed a nomogram incorporating tumor site to enhance personalized management for patients with GNEC. 1807 patients were divided into DGNEC and PGNEC groups. We performed analyses by using propensity score matching (PSM) and Fine-Gray competing risk methods. A predictive nomogram for the prognosis of GNEC was constructed and validated. The cumulative incidence of cancer-specific death (CSD) in the DGNEC group was lower than that in the PGNEC group. Subgroup analysis showed lower CSD of DGNEC in males, females, tumor sizes (<= 2 cm, 2 < tumor size <= 5 cm, > 5 cm, and unknown), grade stage I-II, and AJCC stage I-III, chemotherapy or no chemotherapy, surgery or no surgery groups (P < 0.05). Multivariate analysis revealed a significant association between PGNEC and CSD (HR, 1.4; 95% CI 1.13-1.73; P = 0.02). The independent predictors of CSD in patients with GNEC were primary site, gender, age, tumor size, AJCC stage, T stage, N stage, grade stage, and surgery. A predictive model based on multivariate analysis was constructed to estimate the probability of CSD at 1-, 3-, and 5-year. The calibration curves demonstrated excellent consistency between the predicted and observed probabilities of CSD. Patients with DGNEC have a better prognosis than those with PGNEC. The model exhibits strong predictive capability for these patients.