LASSO-Cox Model in the Prognostic Evaluation of Radiochemotherapy Efficacy for Lymph Node Metastatic Nasopharyngeal Carcinoma

Simin LuXin ZhengXin ZhangGang LiHaizhen ZhangYinghong ZhongDaijie Wang^*

• Luzhou People's Hospital, Luzhou, China

This retrospective study aimed to develop and validate a prognostic evaluation system based on the LASSO-Cox regression model for nasopharyngeal carcinoma (NPC) patients undergoing radiochemotherapy.Data from 186 patients treated between 2013 and 2019 at three tertiary hospitals in China were analyzed.Patients were randomly divided into a training set and a validation set in a 7:3 ratio. In the training cohort, the LASSO + Cox regression analysis was conducted to identify independent prognostic factors influencing progression-free survival (PFS). Based on these independent factors, a nomogram was constructed to predict 2-, 3-, and 5-year PFS. The predictive performance of the nomogram was then evaluated in the validation cohort.Using the LASSO method for variable selection, three prognostic indicators were initially identified, and stepwise Cox regression in the training cohort further confirmed that clinical stage and EBV level were independent predictors of PFS. A nomogram was constructed based on these factors, which achieved areas under the receiver operating characteristic curves (AUC-ROC) of 0.801, 0.760, and 0.749 for predicting 2-, 3-, and 5-year PFS, respectively, in the validation cohort. The model also demonstrated robust performance through calibration and decision curve analyses.This nomogram provides a practical tool for personalized risk assessment and treatment planning, facilitating early identification of high-risk patients who may benefit from intensified treatment strategies.