A Machine Learning-Based Model for the Prediction of Xerostomia after Head and Neck Radiotherapy
DOI:
https://doi.org/10.63187/ampas.44Keywords:
Machine learning, Xerostomia, Head and neck radiotherrapyAbstract
A Machine Learning-Based Model for the Prediction of Xerostomia after Head and Neck Radiotherapy
Abstract
Aim: The aim of this study is to create an ML model to predict xerostomia in patients undergoing RT.
Methods: Data from patients with LAHNC treated in our department between 2012 and 2017 were used in this retrospective study. The patients were selected with an aim of a minimum follow-up period of longer than two years. RIX was assessed with the XI which includes 11 questions. The ML method of random forest (RF) was used for the prediction of RIX. We developed the model using dosimetric parameters as input and RIX scores as output.
Results: The model worked with an accuracy rate of 96.6% to generate the importance of the survey questions on the total RIX score. The question “I have difficulties swallowing certain foods” was the most effectual and “I suck sweets or cough lollies to relieve dry mouth” was the least effectual question, respectively. Also, our ML model predicted the RIX scores with an accuracy of 81%.
Conclusion: The questions in the XI have different impacts on the total score. Our ML model showed that the XI items could be reduced from 11 to nine, costing an only 0.3% decrease in accuracy. The ML model offers to delineate the parotid stem cells and record the doses to these cells for a more accurate assessment of RIX.
Keywords: Machine learning, Xerostomia, head and neck radiotherapy
References
Wijers OB, Levendag PC, Braaksma MM, Boonzaaijer M, Visch LL, Schmitz PI. Patients with head and neck cancer cured by radiation therapy: a survey of the dry mouth syndrome in long-term survivors. Head Neck. 2002;24:737-47.
Franzén L, Funegård U, Ericson T, Henriksson R. Parotid gland function during and following radiotherapy of malignancies in the head and neck. A consecutive study of salivary flow and patient discomfort. Eur J Cancer. 1992;28:457-62.
Roesink JM, Moerland MA, Battermann JJ, Hordijk GJ, Terhaard CH. Quantitative dose-volume response analysis of changes in parotid gland function after radiotherapy in the head-and-neck region. Int J Radiat Oncol Biol Phys. 2001;51:938-46.
Nutting CM, Morden JP, Harrington KJ, Urbano TG, Bhide SA, Clark C, et al. Parotid-sparing intensity modulated versus conventional radiotherapy in head and neck cancer (PARSPORT): a phase 3 multicentre randomised controlled trial. Lancet Oncol. 2011;12:127-36.
Delporte C, O'Connell BC, He X, Lancaster HE, O'Connell AC, Agre P, et al. Increased fluid secretion after adenoviral-mediated transfer of the aquaporin-1 cDNA to irradiated rat salivary glands. Proc Natl Acad Sci U S A. 1997;94:3268-73.
Spiegel JH, Deschler DG, Cheney ML. Microvascular Transplantation and Replantation of the Rabbit Submandibular Gland. Arch Otolaryngol. 2001;127:991-6.
Sari SY, Yilmaz MT, Elmali A, Yedekci FY, Yuce D, Ozyigit G, et al. Parotid gland stem cells: Mini yet mighty. Head Neck. 2021;43:1122-7.
Steenbakkers R, van Rijn-Dekker MI, Stokman MA, Kierkels RGJ, van der Schaaf A, van den Hoek JGM, et al. Parotid Gland Stem Cell Sparing Radiation Therapy for Patients With Head and Neck Cancer: A Double-Blind Randomized Controlled Trial. Int J Radiat Oncol Biol Phys. 2022;112:306-16.
Deist TM, Dankers FJ, Valdes G, Wijsman R, Hsu IC, Oberije C, et al. Machine learning algorithms for outcome prediction in (chemo) radiotherapy: An empirical comparison of classifiers. Med Phys. 2018;45:3449-59.
Isaksson LJ, Pepa M, Zaffaroni M, Marvaso G, Alterio D, Volpe S, et al. Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy. Front Oncol. 2020;10.
Deasy JO, Moiseenko V, Marks L, Chao KSC, Nam J, Eisbruch A. Radiotherapy dose-volume effects on salivary gland function. Int J Radiat Oncol Biol Phys. 2010;76:S58-S63.
Guchelaar HJ, Vermes A, Meerwaldt JH. Radiation-induced xerostomia: pathophysiology, clinical course and supportive treatment. Support Care Cancer. 1997;5:281-8.
Dirix P, Nuyts S, Van den Bogaert W. Radiation-induced xerostomia in patients with head and neck cancer. Cancer. 2006;107:2525-34.
Thomson WM, Chalmers JM, Spencer AJ, Williams SM. The Xerostomia Inventory: a multi-item approach to measuring dry mouth. Community Dent Health. 1999;16:12-7.
van der Putten G-J, Brand HS, Schols JM, de Baat C. The diagnostic suitability of a xerostomia questionnaire and the association between xerostomia, hyposalivation and medication use in a group of nursing home residents. Clin Oral Inv. 2011;15:185-92.
Dean JA, Wong KH, Welsh LC, Jones A-B, Schick U, Newbold KL, et al. Normal tissue complication probability (NTCP) modelling using spatial dose metrics and machine learning methods for severe acute oral mucositis resulting from head and neck radiotherapy. Radiother Oncol. 2016;120:21-7.
Saednia K, Tabbarah S, Lagree A, Wu T, Klein J, Garcia E, et al. Quantitative Thermal Imaging Biomarkers to Detect Acute Skin Toxicity From Breast Radiation Therapy Using Supervised Machine Learning. Int J Radiat Oncol Biol Phys. 2020;106:1071-83.
Humphrey SP, Williamson RT. A review of saliva: normal composition, flow, and function. J Prost Dent. 2001;85:162-9.
Steenbakkers RJHM, van Rijn–Dekker MI, Stokman MA, Kierkels RGJ, van der Schaaf A, van den Hoek JGM, et al. Parotid Gland Stem Cell Sparing Radiation Therapy for Patients With Head and Neck Cancer: A Double-Blind Randomized Controlled Trial. Int J Radiat Oncol Biol Phys. 2022;112:306-16.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Fazlı Yağız Yedekçi, Melek Tuğçe Yılmaz, Sezin Yüce Sarı, Mustafa Cengiz, Gökhan Özyiğit, Gözde Yazıcı
This work is licensed under a Creative Commons Attribution 4.0 International License.
