Dataset Information

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.

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.

SUBMITTER: Dean JA

PROVIDER: S-EPMC5021201 | biostudies-literature | 2016 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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.

Dean Jamie A JA Wong Kee H KH Welsh Liam C LC Jones Ann-Britt AB Schick Ulrike U Newbold Kate L KL Bhide Shreerang A SA Harrington Kevin J KJ Nutting Christopher M CM Gulliford Sarah L SL

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology 20160527 1

<h4>Background and purpose</h4>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.<h4>Materials and methods</h4>Predictive models of severe acute mucositis were generated using radiotherapy dose (dose-volume and spatial dose metrics) and clinical data. Penalised logistic regression, suppo ...[more]

PMID: 27240717

Similar Datasets

Project description:PurposeOsteoradionecrosis (ORN) of the mandible represents a severe, debilitating complication of radiation therapy (RT) for head and neck cancer (HNC). At present, no normal tissue complication probability (NTCP) models for risk of ORN exist. The aim of this study was to develop a multivariable clinical/dose-based NTCP model for the prediction of ORN any grade (ORNI-IV) and grade IV (ORNIV) after RT (±chemotherapy) in patients with HNC.Methods and materialsIncluded patients with HNC were treated with (chemo-)RT between 2005 and 2015. Mandible bone radiation dose-volume parameters and clinical variables (ie, age, sex, tumor site, pre-RT dental extractions, chemotherapy history, postoperative RT, and smoking status) were considered as potential predictors. The patient cohort was randomly divided into a training (70%) and independent test (30%) cohort. Bootstrapped forward variable selection was performed in the training cohort to select the predictors for the NTCP models. Final NTCP model(s) were validated on the holdback test subset.ResultsOf 1259 included patients with HNC, 13.7% (n = 173 patients) developed any grade ORN (ORNI-IV primary endpoint) and 5% (n = 65) ORNIV (secondary endpoint). All dose and volume parameters of the mandible bone were significantly associated with the development of ORN in univariable models. Multivariable analyses identified D30% and pre-RT dental extraction as independent predictors for both ORNI-IV and ORNIV best-performing NTCP models with an area under the curve (AUC) of 0.78 (AUCvalidation = 0.75 [0.69-0.82]) and 0.81 (AUCvalidation = 0.82 [0.74-0.89]), respectively.ConclusionsThis study presented NTCP models based on mandible bone D30% and pre-RT dental extraction that predict ORNI-IV and ORNIV (ie, needing invasive surgical intervention) after HNC RT. Our results suggest that less than 30% of the mandible should receive a dose of 35 Gy or more for an ORNI-IV risk lower than 5%. These NTCP models can improve ORN prevention and management by identifying patients at risk of ORN.

Project description:PurposeMultiparametric magnetic resonance tomography (mpMRI) and prostate specific membrane antigen positron emission tomography (PSMA-PET/CT) are used to guide focal radiotherapy (RT) dose escalation concepts. Besides improvements of treatment effectiveness, maintenance of a good quality of life is essential. Therefore, this planning study investigates whether urethral sparing in moderately hypofractionated RT with focal RT dose escalation influences tumour control probability (TCP) and normal tissue complication probability (NTCP).Patients and methods10 patients with primary prostate cancer (PCa), who underwent 68Ga PSMA-PET/CT and mpMRI followed by radical prostatectomy were enrolled. Intraprostatic tumour volumes (gross tumor volume, GTV) based on both imaging techniques (GTV-MRI and -PET) were contoured manually using validated contouring techniques and GTV-Union was created by summing both. For each patient three IMRT plans were generated with 60 Gy to the whole prostate and a simultaneous integrated boost up to 70 Gy to GTV-Union in 20 fractions by (Plan 1) not respecting and (Plan 2) respecting dose constraints for urethra as well as (Plan 3) respecting dose constraints for planning organ at risk volume for urethra (PRV = urethra + 2mm expansion). NTCP for urethra was calculated applying a Lyman-Kutcher-Burman model. TCP-Histo was calculated based on PCa distribution in co-registered histology (GTV-Histo). Complication free tumour control probability (P+) was calculated. Furthermore, the intrafractional movement was considered.ResultsMedian overlap of GTV-Union and PRV-Urethra was 1.6% (IQR 0-7%). Median minimum distance of GTV-Histo to urethra was 3.6 mm (IQR 2 - 7 mm) and of GTV-Union to urethra was 1.8 mm (IQR 0.0 - 5.0 mm). The respective prescription doses and dose constraints were reached in all plans. Urethra-sparing in Plans 2 and 3 reached significantly lower NTCP-Urethra (p = 0.002) without significantly affecting TCP-GTV-Histo (p = p > 0.28), NTCP-Bladder (p > 0.85) or NTCP-Rectum (p = 0.85), resulting in better P+ (p = 0.006). Simulation of intrafractional movement yielded even higher P+ values for Plans 2 and 3 compared to Plan 1.ConclusionUrethral sparing may increase the therapeutic ratio and should be implemented in focal RT dose escalation concepts.

Dataset Information

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.

Background and purpose

Materials and methods

Results

Conclusions

Publications

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.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets