ObjectivesThis study aimed to investigate the prognostic value of Log odds of positive lymph nodes (LODDS) for predicting the long-term prognosis of patients with node-positive lung neuroendocrine tumors (LNETs).Materials and MethodsWe collected 506 eligible patients with resected N1/N2 classification LNETs from the Surveillance, Epidemiology, and End Results (SEER) database between 2004 and 2015. First, we applied the Cox proportional-hazards regression model to evaluate the relationship between LODDS and study endpoints (cancer-specific survival [CSS] and overall survival [OS]) based on the entire cohort. Second, the study cohort was divided into derivation cohort (n=300) and external validation cohort (n=206) based on different geographic regions. Nomograms were constructed and validated based on these two cohorts to predict the 1-, 3- and 5-year survival of patients with LNETs. The accuracy and clinical practicability of nomograms were tested and compared by Harrell’s concordance index (C-index), integrated discrimination improvement (IDI), net reclassification improvement (NRI), calibration plots, and decision curve analyses.ResultsThe Cox proportional-hazards model showed the high LODDS group (-0.33≤LODDS≤1.14) had significantly higher mortality compared to those in the low LODDS group (-1.44 ≤LODDSConclusionsWe created visualized nomograms for CSS and OS of LNET patients, facilitating clinicians to provide highly individualized risk assessment and therapy.