Feng Teng1,2, Wenjun Fan3,4,5, Yanrong Luo2,6, Shouping Xu6, Hanshun Gong6, Ruigang Ge6, Xinxin Zhang7, Xiaoning Wang8,9, Lin Ma2,6. 1. Department of Radiation Oncology, China-Japan Friendship Hospital, Beijing, China. 2. Department of Radiation Oncology, Medical School of the Chinese People's Liberation Army (PLA), Beijing, China. 3. Affiliated Foshan Maternity and Child Healthcare Hospital, Southern Medical University, Foshan, China. 4. Department of Radiation Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, China. 5. Department of Radiation Oncology, Armed Police Corps Hospital of Henan Province, Zhengzhou, China. 6. Department of Radiation Oncology, First Medical Center of Chinese PLA General Hospital, Beijing, China. 7. Departmant of Otorhinolaryngology, First Medical Center of Chinese PLA General Hospital, Beijing, China. 8. School of Data Science and Media Intelligence, Communication University of China, Beijing, China. 9. State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing, China.
Abstract
OBJECTIVE: This 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 MATERIALS: LASSO 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). RESULTS: The 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. CONCLUSION: The 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.
OBJECTIVE: This 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 MATERIALS: LASSO 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). RESULTS: The 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. CONCLUSION: The 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.
Authors: Ivo Beetz; Cornelis Schilstra; Peter van Luijk; Miranda E M C Christianen; Patricia Doornaert; Henk P Bijl; Olga Chouvalova; Edwin R van den Heuvel; Roel J H M Steenbakkers; Johannes A Langendijk Journal: Radiother Oncol Date: 2011-12-12 Impact factor: 6.280
Authors: Issam El Naqa; Jeffrey Bradley; Angel I Blanco; Patricia E Lindsay; Milos Vicic; Andrew Hope; Joseph O Deasy Journal: Int J Radiat Oncol Biol Phys Date: 2006-03-15 Impact factor: 7.038
Authors: Ivo Beetz; Cornelis Schilstra; Arjen van der Schaaf; Edwin R van den Heuvel; Patricia Doornaert; Peter van Luijk; Arjan Vissink; Bernard F A M van der Laan; Charles R Leemans; Henk P Bijl; Miranda E M C Christianen; Roel J H M Steenbakkers; Johannes A Langendijk Journal: Radiother Oncol Date: 2012-04-18 Impact factor: 6.280
Authors: Heather D Pacholke; Robert J Amdur; Christopher G Morris; Jonathan G Li; James F Dempsey; Russell W Hinerman; William M Mendenhall Journal: Am J Clin Oncol Date: 2005-08 Impact factor: 2.339
Authors: S Tribius; J Sommer; C Prosch; A Bajrovic; A Muenscher; M Blessmann; A Kruell; C Petersen; M Todorovic; P Tennstedt Journal: Strahlenther Onkol Date: 2013-01-27 Impact factor: 3.621
Authors: Chad M Amosson; Bin S Teh; T John Van; Nathan Uy; Eugene Huang; Wei-Yuan Mai; Anna Frolov; Shiao Y Woo; J Kam Chiu; L Steven Carpenter; Hsin H Lu; Walter H Grant; E Brian Butler Journal: Int J Radiat Oncol Biol Phys Date: 2003-05-01 Impact factor: 7.038