Functional Data Analysis Applied to Modeling of Severe Acute Mucositis and Dysphagia Resulting From Head and Neck Radiation Therapy
Dean, J. A., Wong, K. H., Gay, H., Welsh, L. C., Jones, A. B., Schick, U., Oh, J. H., Apte, A., Newbold, K. L., Bhide, S. A., Harrington, K. J., Deasy, J. O., Nutting, C. M., Gulliford, S. L.
(2016)
Functional Data Analysis Applied to Modeling of Severe Acute Mucositis and Dysphagia Resulting From Head and Neck Radiation Therapy.
INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 96 (4).
pp. 820-831.
ISSN 0360-3016
|
Text
15451.pdf Download (621kB) | Preview |
Abstract
Purpose: Current normal tissue complication probability modeling using logistic regression suffers from bias and high uncertainty in the presence of highly correlated radiation therapy (RT) dose data. This hinders robust estimates of dose-response associations and, hence, optimal normal tissue-sparing strategies from being elucidated. Using functional data analysis (FDA) to reduce the dimensionality of the dose data could overcome this limitation. Methods and Materials: FDA was applied to modeling of severe acute mucositis and dysphagia resulting from head and neck RT. Functional partial least squares regression (FPLS) and functional principal component analysis were used for dimensionality reduction of the dose-volume histogram data. The reduced dose data were input into functional logistic regression models (functional partial least squareselogistic regression [FPLS-LR] and functional principal componentelogistic regression [FPC-LR]) along with clinical data. This approach was compared with penalized logistic regression (PLR) in terms of predictive performance and the significance of treatment covariate-response associations, assessed using bootstrapping. Results: The area under the receiver operating characteristic curve for the PLR, FPCLR, and FPLS-LR models was 0.65, 0.69, and 0.67, respectively, for mucositis (internal validation) and 0.81, 0.83, and 0.83, respectively, for dysphagia (external validation). The calibration slopes/intercepts for the PLR, FPC-LR, and FPLS-LR models were 1.6/-0.67, 0.45/0.47, and 0.40/0.49, respectively, for mucositis (internal validation) and 2.5/-0.96, 0.79/-0.04, and 0.79/0.00, respectively, for dysphagia (external validation). The bootstrapped odds ratios indicated significant associations between RT dose and severe toxicity in the mucositis and dysphagia FDA models. Cisplatin was significantly associated with severe dysphagia in the FDA models. None of the covariates was significantly associated with severe toxicity in the PLR models. Dose levels greater than approximately 1.0 Gy/fraction were most strongly associated with severe acute mucositis and dysphagia in the FDA models. Conclusions: FPLS and functional principal component analysis marginally improved predictive performance compared with PLR and provided robust dose-response associations. FDA is recommended for use in normal tissue complication probability modeling. (C) 2016 The Author(s). Published by Elsevier Inc.
Item Type: | Article |
---|---|
Authors (ICR Faculty only): | Nutting, Chris and Harrington, Kevin |
All Authors: | Dean, J. A., Wong, K. H., Gay, H., Welsh, L. C., Jones, A. B., Schick, U., Oh, J. H., Apte, A., Newbold, K. L., Bhide, S. A., Harrington, K. J., Deasy, J. O., Nutting, C. M., Gulliford, S. L. |
Additional Information: | ISI Document Delivery No.: DZ0JG Times Cited: 0 Cited Reference Count: 49 Dean, Jamie A. Wong, Kee H. Gay, Hiram Welsh, Liam C. Jones, Ann-Britt Schick, Ulrike Oh, Jung Hun Apte, Aditya Newbold, Kate L. Bhide, Shreerang A. Harrington, Kevin J. Deasy, Joseph O. Nutting, Christopher M. Gulliford, Sarah L. Engineering and Physical Sciences Research Council; Cancer Research UK Programme Grant [A13407]; NHS; Cancer Research UK [CRUK/03/005, CRUK/08/004] This work was supported by the Engineering and Physical Sciences Research Council, Cancer Research UK Programme Grant A13407, and NHS funding to the National Institute for Health Research Biomedical Research Centre at The Royal Marsden and The Institute of Cancer Research. The PARSPORT and COSTAR trials were supported by Cancer Research UK (trial reference No. CRUK/03/005 and CRUK/08/004). None of the funding sources had any role in any part of the study or manuscript preparation and submission. 0 1 ELSEVIER SCIENCE INC NEW YORK INT J RADIAT ONCOL |
Uncontrolled Keywords: | INTENSITY-MODULATED RADIOTHERAPY PRINCIPAL COMPONENT ANALYSIS NORMAL TISSUE COMPLICATIONS DOSE-VOLUME HISTOGRAMS INDUCTION CHEMOTHERAPY RECTAL TOXICITY PROSTATE-CANCER LINEAR-MODELS MIXED MODELS REGRESSION |
Research teams: | ICR divisions > Cancer Biology > Targeted Therapy ICR divisions > Radiotherapy and Imaging > Targeted Therapy Clinical Units > Head & Neck Cancer Unit |
Depositing User: | Barry Jenkins |
Date Deposited: | 18 Nov 2016 15:45 |
Last Modified: | 18 Nov 2016 16:00 |
URI: | http://publications.icr.ac.uk/id/eprint/15451 |
Actions (login required)
![]() |
View Item |