Risk factors for regional lymph node metastasis in rectal neuroendocrine tumors: a population-based study

Abstract

Introduction: The identification of risk factors for regional lymph node (r-LN) metastasis in rectal neuroendocrine tumors (R-NETs) remains challenging. Our objective was to investigate the risk factors associated with patients diagnosed with R-NETs exhibiting r-LN metastasis.

Methods: Patient information was obtained from the Surveillance, Epidemiology, and End Results (SEER) database, complemented by data from the West China Hospital (WCH) databases. The construction cohort comprised patients diagnosed with R-NETs from the SEER database, while cases from the WCH database were utilized as the validation cohort. A novel nomogram was developed to predict the probability of r-LN metastasis, employing a logistic regression model.

Results: Univariate analysis identified four independent risk factors associated with poor r-LN metastasis: age (HR = 1.027, p < 0.05), grade (HR = 0.010, p < 0.05), T stage (HR = 0.010, p < 0.05), and tumor size (HR = 0.005, p < 0.05). These factors were selected as predictors for nomogram construction.

Discussion: The novel nomogram serves as a reliable tool for predicting the risk of r-LN metastasis, providing clinicians with valuable assistance in identifying high-risk patients and tailoring individualized treatments.

Keywords: SEER; West China hospital databases; rectal neuroendocrine tumors; regional lymph node metastasis; tumor size.

Figure 1

A flowchart of patient selection and study design. NETs, neuroendocrine tumors; ICD-O-3, international classification of diseases for oncology, 3rd edition; SEER, the surveillance, epidemiology, and end results dataset.

Figure 2

Kaplan–Meier curves of OS for patients with or without r-LN metastasis using the SEER database. Compared to negative r-LN metastasis, positive r-LN metastasis was significantly associated with worse OS (mOS: 21 vs. 58 months, 95%CI = 15.06–34.94, p < 0.001).

Figure 3

Forest plot of multivariate logistic analysis using the SEER database. (A) Multivariate logistic analysis of the risk of r-LN metastasis for patients diagnosed with rectal neuroendocrine tumors from the SEER database. (B) Multivariate logistic analysis of the risk of distant metastasis for patients diagnosed with rectal neuroendocrine tumors from the SEER database. HR indicates hazard ratio.

Figure 4

Nomogram to predict the risk of r-LN metastasis in patients with rectal neuroendocrine tumors. Points for age, tumor size, tumor grade and T stage are obtained by drawing a line upward from the corresponding values to the “Points” line. The sum of the points of these 4 factors is located on the “Total points” line.

Figure 5

AUC value of ROC prediction for the nomogram using the training and validation sets. (A) Calibration plots of the nomogram for the risk of r-LN metastasis in the training set. (B) Calibration plots of the nomogram for the risk of r-LN metastasis in the validation set. Sky blue area under the curves of the two models to predict risk rates of r-LN metastasis. (C) Calibration curves in the training set. (D) Calibration curves in the validation set. AUC, area under the curve; ROC, receiver operating characteristic.