Considerable heterogeneity exists in the risk of recurrence after curative resection of pancreatic neuroendocrine tumors (PanNETs). Current clinicopathological parameters (e.g., grade, TNM stage) have limited capacity for individualized risk stratification. There is an urgent need for a clinically accessible and operationally simple predictive tools to identify high-risk PanNETs for optimizing personalized postoperative treatment and follow-up strategies. This study aims to identify risk factors associated with recurrence of PanNETs and to develop a clinically applicable risk stratification tool based on multi-center cohorts and multi-omics validation for identifying high-risk patients.

To identify risk factors associated with recurrence after curative resection of PanNETs; To develop a predictive tool for recurrence of PanNETs based on routine clinicopathological features; To evaluate and validate the discriminative ability, calibration, and clinical benefit of the predictive tool; To perform biological validation of the predictive tool;

Inclusion Criteria:

- Pathologically confirmed PanNETs; Underwent curative surgical resection (R0 or R1); Complete clinicopathological data (see detailed variable list); Complete postoperative follow-up data.

Exclusion Criteria:

- Received neoadjuvant therapy before surgery; Hereditary PanNETs or pancreatic neuroendocrine carcinoma (PNEC); Distant metastasis before surgery.

Patients with pathologically confirmed PanNETs who underwent curative surgical resection (R0/R1).