Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy
Objective: We explore whether a knowledge–discovery approach building a Classification and Regression Tree (CART) prediction model for weight loss (WL) in head and neck cancer (HNC) patients treated with radiation therapy (RT) is feasible. Methods and materials: HNC patients from 2007 to 2015 were i...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2018-07-01
|
| Series: | Advances in Radiation Oncology |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2452109417302294 |
| id |
doaj-ddd58f81c04b42b097cb24959f3c7845 |
|---|---|
| record_format |
Article |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Zhi Cheng, MD MPH Minoru Nakatsugawa, PhD Chen Hu, PhD Scott P. Robertson, PhD Xuan Hui, MD MS Joseph A. Moore, PhD Michael R. Bowers, BS Ana P. Kiess, MD PhD Brandi R. Page, MD Laura Burns, BSN Mariah Muse, BSN Amanda Choflet, MS RN OCN Kousuke Sakaue, MS Shinya Sugiyama, MS Kazuki Utsunomiya, MS John W. Wong, PhD Todd R. McNutt, PhD Harry Quon, MD MS |
| spellingShingle |
Zhi Cheng, MD MPH Minoru Nakatsugawa, PhD Chen Hu, PhD Scott P. Robertson, PhD Xuan Hui, MD MS Joseph A. Moore, PhD Michael R. Bowers, BS Ana P. Kiess, MD PhD Brandi R. Page, MD Laura Burns, BSN Mariah Muse, BSN Amanda Choflet, MS RN OCN Kousuke Sakaue, MS Shinya Sugiyama, MS Kazuki Utsunomiya, MS John W. Wong, PhD Todd R. McNutt, PhD Harry Quon, MD MS Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy Advances in Radiation Oncology |
| author_facet |
Zhi Cheng, MD MPH Minoru Nakatsugawa, PhD Chen Hu, PhD Scott P. Robertson, PhD Xuan Hui, MD MS Joseph A. Moore, PhD Michael R. Bowers, BS Ana P. Kiess, MD PhD Brandi R. Page, MD Laura Burns, BSN Mariah Muse, BSN Amanda Choflet, MS RN OCN Kousuke Sakaue, MS Shinya Sugiyama, MS Kazuki Utsunomiya, MS John W. Wong, PhD Todd R. McNutt, PhD Harry Quon, MD MS |
| author_sort |
Zhi Cheng, MD MPH |
| title |
Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy |
| title_short |
Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy |
| title_full |
Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy |
| title_fullStr |
Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy |
| title_full_unstemmed |
Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy |
| title_sort |
evaluation of classification and regression tree (cart) model in weight loss prediction following head and neck cancer radiation therapy |
| publisher |
Elsevier |
| series |
Advances in Radiation Oncology |
| issn |
2452-1094 |
| publishDate |
2018-07-01 |
| description |
Objective: We explore whether a knowledge–discovery approach building a Classification and Regression Tree (CART) prediction model for weight loss (WL) in head and neck cancer (HNC) patients treated with radiation therapy (RT) is feasible. Methods and materials: HNC patients from 2007 to 2015 were identified from a prospectively collected database Oncospace. Two prediction models at different time points were developed to predict weight loss ≥5 kg at 3 months post-RT by CART algorithm: (1) during RT planning using patient demographic, delineated dose data, planning target volume–organs at risk shape relationships data and (2) at the end of treatment (EOT) using additional on-treatment toxicities and quality of life data. Results: Among 391 patients identified, WL predictors during RT planning were International Classification of Diseases diagnosis; dose to masticatory and superior constrictor muscles, larynx, and parotid; and age. At EOT, patient-reported oral intake, diagnosis, N stage, nausea, pain, dose to larynx, parotid, and low-dose planning target volume–larynx distance were significant predictive factors. The area under the curve during RT and EOT was 0.773 and 0.821, respectively. Conclusions: We demonstrate the feasibility and potential value of an informatics infrastructure that has facilitated insight into the prediction of WL using the CART algorithm. The prediction accuracy significantly improved with the inclusion of additional treatment-related data and has the potential to be leveraged as a strategy to develop a learning health system. |
| url |
http://www.sciencedirect.com/science/article/pii/S2452109417302294 |
| work_keys_str_mv |
AT zhichengmdmph evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT minorunakatsugawaphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT chenhuphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT scottprobertsonphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT xuanhuimdms evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT josephamoorephd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT michaelrbowersbs evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT anapkiessmdphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT brandirpagemd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT lauraburnsbsn evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT mariahmusebsn evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT amandachofletmsrnocn evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT kousukesakauems evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT shinyasugiyamams evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT kazukiutsunomiyams evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT johnwwongphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT toddrmcnuttphd evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy AT harryquonmdms evaluationofclassificationandregressiontreecartmodelinweightlosspredictionfollowingheadandneckcancerradiationtherapy |
| _version_ |
1725418971208876032 |
| spelling |
doaj-ddd58f81c04b42b097cb24959f3c78452020-11-25T00:07:19ZengElsevierAdvances in Radiation Oncology2452-10942018-07-0133346355Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapyZhi Cheng, MD MPH0Minoru Nakatsugawa, PhD1Chen Hu, PhD2Scott P. Robertson, PhD3Xuan Hui, MD MS4Joseph A. Moore, PhD5Michael R. Bowers, BS6Ana P. Kiess, MD PhD7Brandi R. Page, MD8Laura Burns, BSN9Mariah Muse, BSN10Amanda Choflet, MS RN OCN11Kousuke Sakaue, MS12Shinya Sugiyama, MS13Kazuki Utsunomiya, MS14John W. Wong, PhD15Todd R. McNutt, PhD16Harry Quon, MD MS17Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland; Toshiba America Research, Inc., Baltimore, MarylandOncology Center—Biostatistics/Bioinformatics, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandCanon Medical Systems Corporation, Otawara, JapanCanon Medical Systems Corporation, Otawara, JapanCanon Medical Systems Corporation, Otawara, JapanDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, MarylandDepartment of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland; Corresponding author. Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, 401 North Broadway, Suite 1440, Baltimore, MD 21231.Objective: We explore whether a knowledge–discovery approach building a Classification and Regression Tree (CART) prediction model for weight loss (WL) in head and neck cancer (HNC) patients treated with radiation therapy (RT) is feasible. Methods and materials: HNC patients from 2007 to 2015 were identified from a prospectively collected database Oncospace. Two prediction models at different time points were developed to predict weight loss ≥5 kg at 3 months post-RT by CART algorithm: (1) during RT planning using patient demographic, delineated dose data, planning target volume–organs at risk shape relationships data and (2) at the end of treatment (EOT) using additional on-treatment toxicities and quality of life data. Results: Among 391 patients identified, WL predictors during RT planning were International Classification of Diseases diagnosis; dose to masticatory and superior constrictor muscles, larynx, and parotid; and age. At EOT, patient-reported oral intake, diagnosis, N stage, nausea, pain, dose to larynx, parotid, and low-dose planning target volume–larynx distance were significant predictive factors. The area under the curve during RT and EOT was 0.773 and 0.821, respectively. Conclusions: We demonstrate the feasibility and potential value of an informatics infrastructure that has facilitated insight into the prediction of WL using the CART algorithm. The prediction accuracy significantly improved with the inclusion of additional treatment-related data and has the potential to be leveraged as a strategy to develop a learning health system.http://www.sciencedirect.com/science/article/pii/S2452109417302294 |