Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy
Severe acute dysphagia commonly results from head and neck radiotherapy (RT). A model enabling prediction of severity of acute dysphagia for individual patients could guide clinical decision-making. Statistical associations between RT dose distributions and dysphagia could inform RT planning protoco...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2018-01-01
|
Series: | Clinical and Translational Radiation Oncology |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405630817300460 |
id |
doaj-13d34f39398248ddbc6e61ff9e1bd026 |
---|---|
record_format |
Article |
spelling |
doaj-13d34f39398248ddbc6e61ff9e1bd0262021-06-02T02:53:25ZengElsevierClinical and Translational Radiation Oncology2405-63082018-01-018C273910.1016/j.ctro.2017.11.009Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapyJamie Dean0Kee Wong1Hiram Gay2Liam Welsh3Ann-Britt Jones4Ulricke Schick5Jung Hun Oh6Aditya Apte7Kate Newbold8Shreerang Bhide9Kevin Harrington10Joseph Deasy11Christopher Nutting12Sarah Gulliford13Joint Department of Physics at the Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, London SM2 5NG, UKHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKDepartment of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USAHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USADepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USAHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKDepartment of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USAHead and Neck Unit, The Royal Marsden NHS Foundation Trust, Fulham Road, London SW3 6JJ, UKJoint Department of Physics at the Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, London SM2 5NG, UKSevere acute dysphagia commonly results from head and neck radiotherapy (RT). A model enabling prediction of severity of acute dysphagia for individual patients could guide clinical decision-making. Statistical associations between RT dose distributions and dysphagia could inform RT planning protocols aiming to reduce the incidence of severe dysphagia. We aimed to establish such a model and associations incorporating spatial dose metrics. Models of severe acute dysphagia were developed using pharyngeal mucosa (PM) RT dose (dose-volume and spatial dose metrics) and clinical data. Penalized logistic regression (PLR), support vector classification and random forest classification (RFC) models were generated and internally (173 patients) and externally (90 patients) validated. These were compared using area under the receiver operating characteristic curve (AUC) to assess performance. Associations between treatment features and dysphagia were explored using RFC models. The PLR model using dose-volume metrics (PLRstandard) performed as well as the more complex models and had very good discrimination (AUC = 0.82) on external validation. The features with the highest RFC importance values were the volume, length and circumference of PM receiving 1 Gy/fraction and higher. The volumes of PM receiving 1 Gy/fraction or higher should be minimized to reduce the incidence of severe acute dysphagia.http://www.sciencedirect.com/science/article/pii/S2405630817300460 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jamie Dean Kee Wong Hiram Gay Liam Welsh Ann-Britt Jones Ulricke Schick Jung Hun Oh Aditya Apte Kate Newbold Shreerang Bhide Kevin Harrington Joseph Deasy Christopher Nutting Sarah Gulliford |
spellingShingle |
Jamie Dean Kee Wong Hiram Gay Liam Welsh Ann-Britt Jones Ulricke Schick Jung Hun Oh Aditya Apte Kate Newbold Shreerang Bhide Kevin Harrington Joseph Deasy Christopher Nutting Sarah Gulliford Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy Clinical and Translational Radiation Oncology |
author_facet |
Jamie Dean Kee Wong Hiram Gay Liam Welsh Ann-Britt Jones Ulricke Schick Jung Hun Oh Aditya Apte Kate Newbold Shreerang Bhide Kevin Harrington Joseph Deasy Christopher Nutting Sarah Gulliford |
author_sort |
Jamie Dean |
title |
Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy |
title_short |
Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy |
title_full |
Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy |
title_fullStr |
Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy |
title_full_unstemmed |
Incorporating spatial dose metrics in machine learning-based normal tissue complication probability (NTCP) models of severe acute dysphagia resulting from head and neck radiotherapy |
title_sort |
incorporating spatial dose metrics in machine learning-based normal tissue complication probability (ntcp) models of severe acute dysphagia resulting from head and neck radiotherapy |
publisher |
Elsevier |
series |
Clinical and Translational Radiation Oncology |
issn |
2405-6308 |
publishDate |
2018-01-01 |
description |
Severe acute dysphagia commonly results from head and neck radiotherapy (RT). A model enabling prediction of severity of acute dysphagia for individual patients could guide clinical decision-making. Statistical associations between RT dose distributions and dysphagia could inform RT planning protocols aiming to reduce the incidence of severe dysphagia. We aimed to establish such a model and associations incorporating spatial dose metrics. Models of severe acute dysphagia were developed using pharyngeal mucosa (PM) RT dose (dose-volume and spatial dose metrics) and clinical data. Penalized logistic regression (PLR), support vector classification and random forest classification (RFC) models were generated and internally (173 patients) and externally (90 patients) validated. These were compared using area under the receiver operating characteristic curve (AUC) to assess performance. Associations between treatment features and dysphagia were explored using RFC models. The PLR model using dose-volume metrics (PLRstandard) performed as well as the more complex models and had very good discrimination (AUC = 0.82) on external validation. The features with the highest RFC importance values were the volume, length and circumference of PM receiving 1 Gy/fraction and higher. The volumes of PM receiving 1 Gy/fraction or higher should be minimized to reduce the incidence of severe acute dysphagia. |
url |
http://www.sciencedirect.com/science/article/pii/S2405630817300460 |
work_keys_str_mv |
AT jamiedean incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT keewong incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT hiramgay incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT liamwelsh incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT annbrittjones incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT ulrickeschick incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT junghunoh incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT adityaapte incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT katenewbold incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT shreerangbhide incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT kevinharrington incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT josephdeasy incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT christophernutting incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy AT sarahgulliford incorporatingspatialdosemetricsinmachinelearningbasednormaltissuecomplicationprobabilityntcpmodelsofsevereacutedysphagiaresultingfromheadandneckradiotherapy |
_version_ |
1721409022886674432 |