PurposeThe value of lymphadenectomy during radical nephroureterectomy (RNU) remains unclear. This study aimed to determine the effects of the removed lymph node (RLN) counts, positive lymph node (pLN) counts, and pLN density (pLND) on survival outcomes in patients with node-positive upper urinary tract urothelial cancer (UTUC). MethodsA total of 306 patients with node-positive UTUC in the Surveillance, Epidemiology, and End Results database between 2004 and 2016 were identified. Multivariable Cox regression analyses were used to evaluate the effect of RLN counts, pLN counts, and pLND on survival outcomes. The maximally selected rank statistics were used to determine the most informative cutoff value for pLND on survival outcomes. ResultsThe RLN counts or pLN counts were not associated with survival outcomes, whereas higher pLND was associated with lower cancer-specific survival (CSS) and overall survival (OS) [hazard ratio (HR) 1.75, P = 0.014 and HR 1.62, P = 0.036, respectively]. The most informative cutoff value for pLND in relation to survival was 27%. Patients with pLND >= 27% had worse 5-year survival rates than those with pLND <27% (52.9% vs. 75.9% for CSS and 18.7% vs. 34.2% for OS, each P < 0.05). Furthermore, the multivariable Cox regression model with pLND could predict 5-year CSS (AUC 0.732 vs. 0.647) or OS (AUC 0.704 vs. 0.621) more accurately than the model without pLND. ConclusionsFor patients with node-positive UTUC, more lymph nodes removed do not offer a better therapeutic effect. However, pLND provides additional prognostic value.