Development and validation of a nomogram model for predicting lymph node metastasis in early non-small-cell lung cancer.

Abstract

This study aimed to identify risk factors associated with lymph node metastasis (LNM) in early non-small-cell lung cancer (eNSCLC) patients and to develop a nomogram model for individualized LNM risk assessment. A retrospective analysis was conducted using clinical data from 1013 eNSCLC patients treated at Beijing Jishuitan Hospital between January 2019 and June 2024. Patients were divided into a training group (668 patients), a validation group (345 patients), and an external group (112 patients). Multivariate logistic regression analysis was performed to identify independent risk factors for LNM. The factors identified were integrated into a nomogram model, and its predictive performance was assessed using the area under the receiver operating characteristic curve (AUC). Independent risk factors for LNM included age, tumor size, degree of differentiation, and CYFRA21-1 levels (all P<0.05). The nomogram demonstrated strong predictive performance with AUC values of 0.828, 0.751, and 0.789 in the training, validation, and external groups, respectively. Calibration curves showed good agreement between predicted and observed probabilities, and decision curve analysis confirmed the model's clinical utility. The developed nomogram is an effective tool for predicting LNM risk in eNSCLC patients. It may help optimize individualized treatment strategies, potentially improving patient outcomes.