Cargando…

Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence

The purpose of this study is to introduce differential dose–volume histogram (dDVH) features into machine learning for radiation pneumonitis (RP) prediction and to demonstrate the predictive performance of the developed model based on integrated cumulative dose–volume histogram (cDVH) and dDVH featu...

Descripción completa

Detalles Bibliográficos
Autores principales: Katsuta, Yoshiyuki, Kadoya, Noriyuki, Sugai, Yuto, Katagiri, Yu, Yamamoto, Takaya, Takeda, Kazuya, Tanaka, Shohei, Jingu, Keiichi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9221601/
https://www.ncbi.nlm.nih.gov/pubmed/35741164
http://dx.doi.org/10.3390/diagnostics12061354
_version_ 1784732663091822592
author Katsuta, Yoshiyuki
Kadoya, Noriyuki
Sugai, Yuto
Katagiri, Yu
Yamamoto, Takaya
Takeda, Kazuya
Tanaka, Shohei
Jingu, Keiichi
author_facet Katsuta, Yoshiyuki
Kadoya, Noriyuki
Sugai, Yuto
Katagiri, Yu
Yamamoto, Takaya
Takeda, Kazuya
Tanaka, Shohei
Jingu, Keiichi
author_sort Katsuta, Yoshiyuki
collection PubMed
description The purpose of this study is to introduce differential dose–volume histogram (dDVH) features into machine learning for radiation pneumonitis (RP) prediction and to demonstrate the predictive performance of the developed model based on integrated cumulative dose–volume histogram (cDVH) and dDVH features. Materials and methods: cDVH and dDVH features were calculated for 153 patients treated for non-small-cell lung cancer with 60–66 Gy and dose bins ranging from 2 to 8 Gy in 2 Gy increments. RP prediction models were developed with the least absolute shrinkage and selection operator (LASSO) through fivefold cross-validation. Results: Among the 152 patients in the patient cohort, 41 presented ≥grade 2 RP. The interdependencies between cDVH features evaluated by Spearman’s correlation were significantly resolved by the inclusion of dDVH features. The average area under curve for the RP prediction model using cDVH and dDVH model was 0.73, which was higher than the average area under curve using cDVH model for 0.62 with statistically significance (p < 0.01). An analysis using the entire set of regression coefficients determined by LASSO demonstrated that dDVH features represented four of the top five frequently selected features in the model fitting, regardless of dose bin. Conclusions: We successfully developed an RP prediction model that integrated cDVH and dDVH features. The best RP prediction model was achieved using dDVH (dose bin = 4 Gy) features in the machine learning process.
format Online
Article
Text
id pubmed-9221601
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-92216012022-06-24 Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence Katsuta, Yoshiyuki Kadoya, Noriyuki Sugai, Yuto Katagiri, Yu Yamamoto, Takaya Takeda, Kazuya Tanaka, Shohei Jingu, Keiichi Diagnostics (Basel) Article The purpose of this study is to introduce differential dose–volume histogram (dDVH) features into machine learning for radiation pneumonitis (RP) prediction and to demonstrate the predictive performance of the developed model based on integrated cumulative dose–volume histogram (cDVH) and dDVH features. Materials and methods: cDVH and dDVH features were calculated for 153 patients treated for non-small-cell lung cancer with 60–66 Gy and dose bins ranging from 2 to 8 Gy in 2 Gy increments. RP prediction models were developed with the least absolute shrinkage and selection operator (LASSO) through fivefold cross-validation. Results: Among the 152 patients in the patient cohort, 41 presented ≥grade 2 RP. The interdependencies between cDVH features evaluated by Spearman’s correlation were significantly resolved by the inclusion of dDVH features. The average area under curve for the RP prediction model using cDVH and dDVH model was 0.73, which was higher than the average area under curve using cDVH model for 0.62 with statistically significance (p < 0.01). An analysis using the entire set of regression coefficients determined by LASSO demonstrated that dDVH features represented four of the top five frequently selected features in the model fitting, regardless of dose bin. Conclusions: We successfully developed an RP prediction model that integrated cDVH and dDVH features. The best RP prediction model was achieved using dDVH (dose bin = 4 Gy) features in the machine learning process. MDPI 2022-05-31 /pmc/articles/PMC9221601/ /pubmed/35741164 http://dx.doi.org/10.3390/diagnostics12061354 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Katsuta, Yoshiyuki
Kadoya, Noriyuki
Sugai, Yuto
Katagiri, Yu
Yamamoto, Takaya
Takeda, Kazuya
Tanaka, Shohei
Jingu, Keiichi
Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title_full Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title_fullStr Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title_full_unstemmed Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title_short Feasibility of Differential Dose—Volume Histogram Features in Multivariate Prediction Model for Radiation Pneumonitis Occurrence
title_sort feasibility of differential dose—volume histogram features in multivariate prediction model for radiation pneumonitis occurrence
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9221601/
https://www.ncbi.nlm.nih.gov/pubmed/35741164
http://dx.doi.org/10.3390/diagnostics12061354
work_keys_str_mv AT katsutayoshiyuki feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT kadoyanoriyuki feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT sugaiyuto feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT katagiriyu feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT yamamototakaya feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT takedakazuya feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT tanakashohei feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence
AT jingukeiichi feasibilityofdifferentialdosevolumehistogramfeaturesinmultivariatepredictionmodelforradiationpneumonitisoccurrence