A Risk Prediction Model by LASSO for Radiation-Induced Xerostomia in Patients With Nasopharyngeal Carcinoma Treated With Comprehensive Salivary Gland-Sparing Helical Tomotherapy Technique.

Feng Teng,Lin Ma,Wenjun Fan,Yanrong Luo,Hanshun Gong,Xinxin Zhang,Shouping Xu,Xiaoning Wang,Ruigang Ge

doi:10.3389/fonc.2021.633556

Abstract

ObjectiveThis study aimed to develop a least absolute shrinkage and selection operator (LASSO)-based multivariable normal tissue complication probability (NTCP) model to predict radiation-induced xerostomia in patients with nasopharyngeal carcinoma (NPC) treated with comprehensive salivary gland–sparing helical tomotherapy technique.Methods and MaterialsLASSO with the extended bootstrapping technique was used to build multivariable NTCP models to predict factors of patient-reported xerostomia relieved by 50% and 80% compared with the level at the end of radiation therapy within 1 year and 2 years, R50-1year and R80-2years, in 203 patients with NPC. The model assessment was based on 10-fold cross-validation and the area under the receiver operating characteristic curve (AUC).ResultsThe prediction model by LASSO with 10-fold cross-validation showed that radiation-induced xerostomia recovery could be predicted by prognostic factors of R50-1year (age, gender, T stage, UICC/AJCC stage, parotid Dmean, oral cavity Dmean, and treatment options) and R80-2years (age, gender, T stage, UICC/AJCC stage, oral cavity Dmean, N stage, and treatment options). These prediction models also demonstrated a good performance by the AUC.ConclusionThe prediction models of R50-1year and R80-2years by LASSO with 10-fold cross-validation were recommended to validate the NTCP model before comprehensive salivary gland–sparing radiation therapy in patients with NPC.

Highlights

At present, intensity-modulated radiation therapy (IMRT) combined with chemotherapy is the main treatment model in patients with nasopharyngeal carcinoma (NPC) [1]
A previous study reported that comprehensive protection of salivary glands, including parotid glands (PGs), submandibular glands (SMGs), and accessory salivary glands in the oral cavity (OC), minimized xerostomia in patients with head and neck cancer (HNC) treated with helical tomotherapy (HT) technique, without increasing early locoregional recurrence risk [8]
During the period of two-dimensional RT and three-dimensional conformal RT (3DCRT), prediction of radiation-induced xerostomia has been frequently studied based on normal tissue complication probability (NTCP) models depending on the dose–volume relationship with the probability of side effects, using either a univariate or a multivariate logistic regression model [10, 13, 14]

Summary

Introduction

Intensity-modulated radiation therapy (IMRT) combined with chemotherapy is the main treatment model in patients with nasopharyngeal carcinoma (NPC) [1]. During the period of two-dimensional RT and three-dimensional conformal RT (3DCRT), prediction of radiation-induced xerostomia has been frequently studied based on normal tissue complication probability (NTCP) models depending on the dose–volume relationship with the probability of side effects, using either a univariate or a multivariate logistic regression model [10, 13, 14]. The sum of absolute values of the mandatory coefficients is less than a fixed value; some regression coefficients are set to zero. It retains the advantage of subset contraction and is a biased estimate for processing data with complex collinearity [15]. Lee et al [17] reported that using a multivariate regression model with

Methods

Results

Conclusion