BACKGROUND: Non-functional gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs) are rare tumors, and liver metastasis is the leading cause of death in patients with GEP-NENs. Due to the difficulty in conducting large cohort studies, no reliable tool currently exists to predict the risk of liver metastasis in these patients. This study aimed to develop and validate a nomogram model based on large cohort clinical data to accurately predict the risk of liver metastasis in patients with non-functional GEP-NENs. METHODS: A retrospective cohort study was conducted, encompassing 838 patients with non-functional GEP-NENs diagnosed between 2009 and 2023. Independent risk factors for liver metastasis were identified through univariate and multivariate logistic regression analyses. A nomogram was constructed based on significant predictors, including T stage, N stage, Ki-67 index, primary tumor site, and BMI. The model's performance was evaluated using the C-index, calibration curves, and decision curve analysis (DCA) for both training and validation cohorts. RESULTS: The nomogram demonstrated excellent predictive performance, with C-index values of 0.839 and 0.823 for the training and validation sets, respectively. Risk stratification using the nomogram's total score effectively differentiated high-risk from low-risk patients. Kaplan-Meier survival analysis revealed significant survival differences between these groups (P <
0.0002). Moreover, the calibration curves indicated strong agreement between predicted and observed outcomes. CONCLUSIONS: The developed nomogram is a reliable tool for predicting the risk of liver metastasis in non-functional GEP-NENs. It facilitates early identification of high-risk patients, thereby enabling personalized treatment and timely intervention. Future research should focus on multicenter validation and the integration of molecular markers to enhance the robustness and clinical applicability of the model.