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

Overview

Journal Radiother Oncol

Specialties Oncology
Radiology

Date 2016 Jun 1

PMID 27240717

Citations 41

Authors

Jamie A Dean

Kee H Wong

Liam C Welsh

Ann-Britt Jones

Ulrike Schick

Kate L Newbold

Shreerang A Bhide

Kevin J Harrington

Christopher M Nutting

Sarah L Gulliford

Affiliations

Soon will be listed here.

Abstract

Background And Purpose: Severe acute mucositis commonly results from head and neck (chemo)radiotherapy. A predictive model of mucositis could guide clinical decision-making and inform treatment planning. We aimed to generate such a model using spatial dose metrics and machine learning.

Materials And Methods: Predictive models of severe acute mucositis were generated using radiotherapy dose (dose-volume and spatial dose metrics) and clinical data. Penalised logistic regression, support vector classification and random forest classification (RFC) models were generated and compared. Internal validation was performed (with 100-iteration cross-validation), using multiple metrics, including area under the receiver operating characteristic curve (AUC) and calibration slope, to assess performance. Associations between covariates and severe mucositis were explored using the models.

Results: The dose-volume-based models (standard) performed equally to those incorporating spatial information. Discrimination was similar between models, but the RFCstandard had the best calibration. The mean AUC and calibration slope for this model were 0.71 (s.d.=0.09) and 3.9 (s.d.=2.2), respectively. The volumes of oral cavity receiving intermediate and high doses were associated with severe mucositis.

Conclusions: The RFCstandard model performance is modest-to-good, but should be improved, and requires external validation. Reducing the volumes of oral cavity receiving intermediate and high doses may reduce mucositis incidence.

Citing Articles

Improved Efficacy of a Predictive Model for Swallowing-Induced Breakthrough Pain Based on a Redefined Delineation Method in Locally Advanced Nasopharyngeal Carcinoma.

Sun J, Chen Z, Liu S, Ye F, Tang T, Zhou Z Adv Radiat Oncol. 2025; 10(2):101690.

PMID: 39871950 PMC: 11770509. DOI: 10.1016/j.adro.2024.101690.

Performance Comparison of 10 State-of-the-Art Machine Learning Algorithms for Outcome Prediction Modeling of Radiation-Induced Toxicity.

Salazar R, Nair S, Leone A, Xu T, Mumme R, Duryea J Adv Radiat Oncol. 2024; 10(2):101675.

PMID: 39717195 PMC: 11665468. DOI: 10.1016/j.adro.2024.101675.

A multi-center, multi-organ, multi-omic prediction model for treatment-induced severe oral mucositis in nasopharyngeal carcinoma.

Nicol A, Lam S, Ching J, Tam V, Teng X, Zhang J Radiol Med. 2024; 130(2):161-178.

PMID: 39570458 PMC: 11870888. DOI: 10.1007/s11547-024-01901-z.

Artificial intelligence-based predictive model for guidance on treatment strategy selection in oral and maxillofacial surgery.

Dong F, Yan J, Zhang X, Zhang Y, Liu D, Pan X Heliyon. 2024; 10(15):e35742.

PMID: 39170321 PMC: 11336844. DOI: 10.1016/j.heliyon.2024.e35742.

Cluster-Based Toxicity Estimation of Osteoradionecrosis Via Unsupervised Machine Learning: Moving Beyond Single Dose-Parameter Normal Tissue Complication Probability by Using Whole Dose-Volume Histograms for Cohort Risk Stratification.

Hosseinian S, Hemmati M, Dede C, Salzillo T, van Dijk L, Mohamed A Int J Radiat Oncol Biol Phys. 2024; 119(5):1569-1578.

PMID: 38462018 PMC: 11262961. DOI: 10.1016/j.ijrobp.2024.02.021.

References

Sonis S . The pathobiology of mucositis. Nat Rev Cancer. 2004; 4(4):277-84. DOI: 10.1038/nrc1318. View

Langendijk J, Lambin P, De Ruysscher D, Widder J, Bos M, Verheij M . Selection of patients for radiotherapy with protons aiming at reduction of side effects: the model-based approach. Radiother Oncol. 2013; 107(3):267-73. DOI: 10.1016/j.radonc.2013.05.007. View

Wopken K, Bijl H, van der Schaaf A, van der Laan H, Chouvalova O, Steenbakkers R . Development of a multivariable normal tissue complication probability (NTCP) model for tube feeding dependence after curative radiotherapy/chemo-radiotherapy in head and neck cancer. Radiother Oncol. 2014; 113(1):95-101. DOI: 10.1016/j.radonc.2014.09.013. View

Bhide S, Gulliford S, Fowler J, Rosenfelder N, Newbold K, Harrington K . Characteristics of response of oral and pharyngeal mucosa in patients receiving chemo-IMRT for head and neck cancer using hypofractionated accelerated radiotherapy. Radiother Oncol. 2010; 97(1):86-91. DOI: 10.1016/j.radonc.2010.08.013. View

Buettner F, Miah A, Gulliford S, Hall E, Harrington K, Webb S . Novel approaches to improve the therapeutic index of head and neck radiotherapy: an analysis of data from the PARSPORT randomised phase III trial. Radiother Oncol. 2012; 103(1):82-7. DOI: 10.1016/j.radonc.2012.02.006. View

Tucker S, Michalski J, Bosch W, Mohan R, Dong L, Winter K . Use of fractional dose-volume histograms to model risk of acute rectal toxicity among patients treated on RTOG 94-06. Radiother Oncol. 2012; 104(1):109-13. PMC: 3413409. DOI: 10.1016/j.radonc.2012.04.023. View

Moons K, Altman D, Reitsma J, Ioannidis J, Macaskill P, Steyerberg E . Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015; 162(1):W1-73. DOI: 10.7326/M14-0698. View

Steyerberg E, Harrell Jr F, Borsboom G, Eijkemans M, Vergouwe Y, Habbema J . Internal validation of predictive models: efficiency of some procedures for logistic regression analysis. J Clin Epidemiol. 2001; 54(8):774-81. DOI: 10.1016/s0895-4356(01)00341-9. View

Bourhis J, Overgaard J, Audry H, Ang K, Saunders M, Bernier J . Hyperfractionated or accelerated radiotherapy in head and neck cancer: a meta-analysis. Lancet. 2006; 368(9538):843-54. DOI: 10.1016/S0140-6736(06)69121-6. View

10.

Steyerberg E, Vickers A, Cook N, Gerds T, Gonen M, Obuchowski N . Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2009; 21(1):128-38. PMC: 3575184. DOI: 10.1097/EDE.0b013e3181c30fb2. View

11.

Trotti A, Bellm L, Epstein J, Frame D, Fuchs H, Gwede C . Mucositis incidence, severity and associated outcomes in patients with head and neck cancer receiving radiotherapy with or without chemotherapy: a systematic literature review. Radiother Oncol. 2003; 66(3):253-62. DOI: 10.1016/s0167-8140(02)00404-8. View

12.

Bentzen S . Preventing or reducing late side effects of radiation therapy: radiobiology meets molecular pathology. Nat Rev Cancer. 2006; 6(9):702-13. DOI: 10.1038/nrc1950. View

13.

Dean J, Welsh L, McQuaid D, Wong K, Aleksic A, Dunne E . Assessment of fully-automated atlas-based segmentation of novel oral mucosal surface organ-at-risk. Radiother Oncol. 2016; 119(1):166-71. PMC: 4868144. DOI: 10.1016/j.radonc.2016.02.022. View

14.

Dean J, Welsh L, Gulliford S, Harrington K, Nutting C . A novel method for delineation of oral mucosa for radiotherapy dose-response studies. Radiother Oncol. 2015; 115(1):63-6. PMC: 4641317. DOI: 10.1016/j.radonc.2015.02.020. View

15.

Malek M, Berger D, Coburn J . On the inappropriateness of stepwise regression analysis for model building and testing. Eur J Appl Physiol. 2007; 101(2):263-4. DOI: 10.1007/s00421-007-0485-9. View

16.

Buettner F, Gulliford S, Webb S, Sydes M, Dearnaley D, Partridge M . The dose-response of the anal sphincter region--an analysis of data from the MRC RT01 trial. Radiother Oncol. 2012; 103(3):347-52. DOI: 10.1016/j.radonc.2012.03.002. View

17.

Beetz I, Schilstra C, van der Schaaf A, van den Heuvel E, Doornaert P, van Luijk P . NTCP models for patient-rated xerostomia and sticky saliva after treatment with intensity modulated radiotherapy for head and neck cancer: the role of dosimetric and clinical factors. Radiother Oncol. 2012; 105(1):101-6. DOI: 10.1016/j.radonc.2012.03.004. View

18.

Kaba H, Fukuda H, Yamamoto S, Ohashi Y . [Reliability at the National Cancer Institute-Common Toxicity Criteria version 2.0]. Gan To Kagaku Ryoho. 2004; 31(8):1187-92. View

19.

Lambin P, Roelofs E, Reymen B, Velazquez E, Buijsen J, Zegers C . 'Rapid Learning health care in oncology' - an approach towards decision support systems enabling customised radiotherapy'. Radiother Oncol. 2013; 109(1):159-64. DOI: 10.1016/j.radonc.2013.07.007. View

20.

Nutting C, Morden J, Harrington K, Urbano T, Bhide S, Clark C . Parotid-sparing intensity modulated versus conventional radiotherapy in head and neck cancer (PARSPORT): a phase 3 multicentre randomised controlled trial. Lancet Oncol. 2011; 12(2):127-36. PMC: 3033533. DOI: 10.1016/S1470-2045(10)70290-4. View