Evaluation of classification and regression tree (CART) model in weight loss prediction following head and neck cancer radiation therapy

Abstract 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...

Full description

Saved in:

Bibliographic Details
Published in:	Advances in radiation oncology 2018-07, Vol.3 (3), p.346-355
Main Authors:	Cheng, Zhi, MD MPH, Nakatsugawa, Minoru, PhD, Hu, Chen, PhD, Robertson, Scott P., PhD, Hui, Xuan, MD MS, Moore, Joseph A., PhD, Bowers, Michael R., BS, Kiess, Ana P., MD PhD, Page, Brandi R., MD, Burns, Laura, BSN, Muse, Mariah, BSN, Choflet, Amanda, MS RN OCN, Sakaue, Kousuke, MS, Sugiyama, Shinya, MS, Utsunomiya, Kazuki, MS, Wong, John W., PhD, McNutt, Todd R., PhD, Quon, Harry, MD MS
Format:	Article
Language:	eng
Subjects:	Head and Neck Cancer Hematology, Oncology, and Palliative Medicine
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Abstract 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.
ISSN:	2452-1094 2452-1094