Machine learning to build and validate a model for radiation pneumonitis prediction in patients with non–small cell lung cancer

Hao Yu, Huanmei Wu, Weili Wang, Shruti Jolly, Jian Yue Jin, Chen Hu, Feng Ming Kong

Research output: Contribution to journalArticle

Abstract

Purpose: Radiation pneumonitis is an important adverse Results: A total of 131 patients were eligible and 17 (13.0%) event in patients with non–small cell lung cancer (NSCLC) developed RP2. IL8 and CCL2 had significantly (Bonferroni) receiving thoracic radiotherapy. However, the risk of radiation lower expression levels in patients with RP2 than without RP2. pneumonitis grade 2 (RP2) has not been well predicted. This But none of the changes in cytokine levels during radiotherapy study hypothesized that inflammatory cytokines or the was significantly associated with RP2. The final predictive GLM dynamic changes during radiotherapy can improve predictive model for RP2 was established, including IL8 and CCL2 at accuracy for RP2. baseline level and two clinical variables. Nomogram was Experimental Design: Levels of 30 inflammatory cyto-constructed based on the GLM model. The model's predicting kines and clinical information in patients with stages I–ability was validated in the completely independent test set III NSCLC treated with radiotherapy were from our (AUC ¼ 0.863, accuracy ¼ 80.0%, sensitivity ¼ 100%, spec-prospective studies. Statistical analysis was used to select ificity ¼ 76.5%). predictive cytokine candidates and clinical covariates for Conclusions: By machine learning, this study has developed adjustment. Machine learning algorithm was used to and validated a comprehensive model integrating inflamma-develop the generalized linear model for predicting risk tory cytokines with clinical variables to predict RP2 before RP2. radiotherapy that provides an opportunity to guide clinicians.

Original languageEnglish (US)
Pages (from-to)4343-4350
Number of pages8
JournalClinical Cancer Research
Volume25
Issue number14
DOIs
StatePublished - Jan 1 2019

Fingerprint

Radiation Pneumonitis
Non-Small Cell Lung Carcinoma
Radiotherapy
Cytokines
Interleukin-8
Nomograms
Area Under Curve
Linear Models
Pneumonia
Research Design
Thorax
Machine Learning
Prospective Studies
Radiation

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Machine learning to build and validate a model for radiation pneumonitis prediction in patients with non–small cell lung cancer. / Yu, Hao; Wu, Huanmei; Wang, Weili; Jolly, Shruti; Jin, Jian Yue; Hu, Chen; Kong, Feng Ming.

In: Clinical Cancer Research, Vol. 25, No. 14, 01.01.2019, p. 4343-4350.

Research output: Contribution to journalArticle

Yu, Hao ; Wu, Huanmei ; Wang, Weili ; Jolly, Shruti ; Jin, Jian Yue ; Hu, Chen ; Kong, Feng Ming. / Machine learning to build and validate a model for radiation pneumonitis prediction in patients with non–small cell lung cancer. In: Clinical Cancer Research. 2019 ; Vol. 25, No. 14. pp. 4343-4350.
@article{ffc992d4f94442578745c2bbdeda5dfe,
title = "Machine learning to build and validate a model for radiation pneumonitis prediction in patients with non–small cell lung cancer",
abstract = "Purpose: Radiation pneumonitis is an important adverse Results: A total of 131 patients were eligible and 17 (13.0{\%}) event in patients with non–small cell lung cancer (NSCLC) developed RP2. IL8 and CCL2 had significantly (Bonferroni) receiving thoracic radiotherapy. However, the risk of radiation lower expression levels in patients with RP2 than without RP2. pneumonitis grade 2 (RP2) has not been well predicted. This But none of the changes in cytokine levels during radiotherapy study hypothesized that inflammatory cytokines or the was significantly associated with RP2. The final predictive GLM dynamic changes during radiotherapy can improve predictive model for RP2 was established, including IL8 and CCL2 at accuracy for RP2. baseline level and two clinical variables. Nomogram was Experimental Design: Levels of 30 inflammatory cyto-constructed based on the GLM model. The model's predicting kines and clinical information in patients with stages I–ability was validated in the completely independent test set III NSCLC treated with radiotherapy were from our (AUC ¼ 0.863, accuracy ¼ 80.0{\%}, sensitivity ¼ 100{\%}, spec-prospective studies. Statistical analysis was used to select ificity ¼ 76.5{\%}). predictive cytokine candidates and clinical covariates for Conclusions: By machine learning, this study has developed adjustment. Machine learning algorithm was used to and validated a comprehensive model integrating inflamma-develop the generalized linear model for predicting risk tory cytokines with clinical variables to predict RP2 before RP2. radiotherapy that provides an opportunity to guide clinicians.",
author = "Hao Yu and Huanmei Wu and Weili Wang and Shruti Jolly and Jin, {Jian Yue} and Chen Hu and Kong, {Feng Ming}",
year = "2019",
month = "1",
day = "1",
doi = "10.1158/1078-0432.CCR-18-1084",
language = "English (US)",
volume = "25",
pages = "4343--4350",
journal = "Clinical Cancer Research",
issn = "1078-0432",
publisher = "American Association for Cancer Research Inc.",
number = "14",

}

TY - JOUR

T1 - Machine learning to build and validate a model for radiation pneumonitis prediction in patients with non–small cell lung cancer

AU - Yu, Hao

AU - Wu, Huanmei

AU - Wang, Weili

AU - Jolly, Shruti

AU - Jin, Jian Yue

AU - Hu, Chen

AU - Kong, Feng Ming

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Purpose: Radiation pneumonitis is an important adverse Results: A total of 131 patients were eligible and 17 (13.0%) event in patients with non–small cell lung cancer (NSCLC) developed RP2. IL8 and CCL2 had significantly (Bonferroni) receiving thoracic radiotherapy. However, the risk of radiation lower expression levels in patients with RP2 than without RP2. pneumonitis grade 2 (RP2) has not been well predicted. This But none of the changes in cytokine levels during radiotherapy study hypothesized that inflammatory cytokines or the was significantly associated with RP2. The final predictive GLM dynamic changes during radiotherapy can improve predictive model for RP2 was established, including IL8 and CCL2 at accuracy for RP2. baseline level and two clinical variables. Nomogram was Experimental Design: Levels of 30 inflammatory cyto-constructed based on the GLM model. The model's predicting kines and clinical information in patients with stages I–ability was validated in the completely independent test set III NSCLC treated with radiotherapy were from our (AUC ¼ 0.863, accuracy ¼ 80.0%, sensitivity ¼ 100%, spec-prospective studies. Statistical analysis was used to select ificity ¼ 76.5%). predictive cytokine candidates and clinical covariates for Conclusions: By machine learning, this study has developed adjustment. Machine learning algorithm was used to and validated a comprehensive model integrating inflamma-develop the generalized linear model for predicting risk tory cytokines with clinical variables to predict RP2 before RP2. radiotherapy that provides an opportunity to guide clinicians.

AB - Purpose: Radiation pneumonitis is an important adverse Results: A total of 131 patients were eligible and 17 (13.0%) event in patients with non–small cell lung cancer (NSCLC) developed RP2. IL8 and CCL2 had significantly (Bonferroni) receiving thoracic radiotherapy. However, the risk of radiation lower expression levels in patients with RP2 than without RP2. pneumonitis grade 2 (RP2) has not been well predicted. This But none of the changes in cytokine levels during radiotherapy study hypothesized that inflammatory cytokines or the was significantly associated with RP2. The final predictive GLM dynamic changes during radiotherapy can improve predictive model for RP2 was established, including IL8 and CCL2 at accuracy for RP2. baseline level and two clinical variables. Nomogram was Experimental Design: Levels of 30 inflammatory cyto-constructed based on the GLM model. The model's predicting kines and clinical information in patients with stages I–ability was validated in the completely independent test set III NSCLC treated with radiotherapy were from our (AUC ¼ 0.863, accuracy ¼ 80.0%, sensitivity ¼ 100%, spec-prospective studies. Statistical analysis was used to select ificity ¼ 76.5%). predictive cytokine candidates and clinical covariates for Conclusions: By machine learning, this study has developed adjustment. Machine learning algorithm was used to and validated a comprehensive model integrating inflamma-develop the generalized linear model for predicting risk tory cytokines with clinical variables to predict RP2 before RP2. radiotherapy that provides an opportunity to guide clinicians.

UR - http://www.scopus.com/inward/record.url?scp=85069042247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069042247&partnerID=8YFLogxK

U2 - 10.1158/1078-0432.CCR-18-1084

DO - 10.1158/1078-0432.CCR-18-1084

M3 - Article

C2 - 30992302

AN - SCOPUS:85069042247

VL - 25

SP - 4343

EP - 4350

JO - Clinical Cancer Research

JF - Clinical Cancer Research

SN - 1078-0432

IS - 14

ER -