Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees.

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Abstract Text:

Shiva K Das,Sumin Zhou,Junan Zhang,Fang-Fang Yin,Mark W Dewhirst,Lawrence B Marks,

PURPOSE: To develop and test a model to predict for lung radiation-induced Grade 2+ pneumonitis. METHODS AND MATERIALS: The model was built from a database of 234 lung cancer patients treated with radiotherapy (RT), of whom 43 were diagnosed with pneumonitis. The model augmented the predictive capability of the parametric dose-based Lyman normal tissue complication probability (LNTCP) metric by combining it with weighted nonparametric decision trees that use dose and nondose inputs. The decision trees were sequentially added to the model using a "boosting" process that enhances the accuracy of prediction. The model's predictive capability was estimated by 10-fold cross-validation. To facilitate dissemination, the cross-validation result was used to extract a simplified approximation to the complicated model architecture created by boosting. Application of the simplified model is demonstrated in two example cases. RESULTS: The area under the model receiver operating characteristics curve for cross-validation was 0.72, a significant improvement over the LNTCP area of 0.63 (p = 0.005). The simplified model used the following variables to output a measure of injury: LNTCP, gender, histologic type, chemotherapy schedule, and treatment schedule. For a given patient RT plan, injury prediction was highest for the combination of pre-RT chemotherapy, once-daily treatment, female gender and lowest for the combination of no pre-RT chemotherapy and nonsquamous cell histologic type. Application of the simplified model to the example cases revealed that injury prediction for a given treatment plan can range from very low to very high, depending on the settings of the nondose variables. CONCLUSIONS: Radiation pneumonitis prediction was significantly enhanced by decision trees that added the influence of nondose factors to the LNTCP formulation.

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Publishing Authors By Initials

SK Das,S Zhou,J Zhang,FF Yin,MW Dewhirst,LB Marks,

For similar investigative techniques: epidemiologic methods: epidemiologic research design: reproducibility of results research abstracts see: investigative techniques: epidemiologic methods: epidemiologic research design: reproducibility of results research

PUBMED ID PMID:

MEDLINE DATE:

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Journal Published:

PUBLICATION TYPE: Research Support, N.I.H., Extr

Journal: International journal of radiation oncology, biolo

VOLUME: 68

Page Numbers: 1212-21

Journal Abbreviation: Int. J. Radiat. Oncol. Biol. P

ISSN: 0360-3016

DAY: 15

MONTH: Jul

YEAR: 2007

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 7603616

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Keywords Mesh Terms:

KEYWORDS: Reproducibility of Results

MESH TERMS: etiology

Chemical & Substance for Abstract: Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees.

AFFILIATION: Department of Radiation Oncology, Duke University Medical Center, Durham, NC 27710, USA. shiva.das@duke.edu

Country: United States

AGENCY: United States NCI

GRANT: R01 CA 69579

ACRONYM: CA

MEDLINETA: Int J Radiat Oncol Biol Phys

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees Related Publications

• 5alpha-reductase: history and clinical importance.
• A novel assay for monitoring internalization of nanocarrier coupled antibodies.
• Anxiety sensitivity and auditory perception of heartbeat.
• Cannabis laws: an analysis of costs.
• Continuous participation in voluntary groups as a protective factor for the psychological well-being of adults who develop functional limitations: evidence from the national survey of families and households.
• Darkness descends with two Rabs.
• Evaluation of expression based markers for the detection of breast cancer cells.
• Genetic diversity among Botulinum Neurotoxin-producing clostridial strains.
• Granulocyte transfusions in the G-CSF era. Where do we stand?
• Histone deacetylase inhibitors selectively suppress expression of HDAC7.
• Histone deacetylase inhibitors: molecular mechanisms of action.
• Impact of single-chain Fv antibody fragment affinity on nanoparticle targeting of epidermal growth factor receptor-expressing tumor cells.
• Interrogational neuroimaging in counterterrorism: a "no-brainer" or a human rights hazard?
• MOSQUITOES (CULICIDAE) BITING A FISH (PERIOPHTHALMIDAE).
• Mechanisms of disease: Cytokine and adipokine signaling in uremic cachexia.
• Molecular evolution of antibody cross-reactivity for two subtypes of type A botulinum neurotoxin.
• Morbidity and cost of atopic eczema in Australia.
• One-pot terminal alkene homologation using a tandem olefin cross-metathesis/allylic carbonate reduction sequence.
• Penetrating spinal injury with wooden fragments causing cauda equina syndrome: case report and literature review.
• Predicting lung radiotherapy-induced pneumonitis using a model combining parametric Lyman probit with nonparametric decision trees.
• Recombinant full-length human IgG1s targeting hormone-refractory prostate cancer.
• Regulation of central melanocortin signaling by interleukin-1 beta.
• Self-consistent tumor control probability and normal tissue complication probability models based on generalized EUD.
• Skin cancer: a practical guide to management.
• The impact of induction chemotherapy and the associated tumor response on subsequent radiation-related changes in lung function and tumor response.
• The role of functional imaging in the diagnosis and management of late normal tissue injury.
• The subtypes of nicotinic acetylcholine receptors on dopaminergic terminals of mouse striatum.
• The way of all flesh - the 21st Century.
• Updated assessment of the six-minute walk test as predictor of acute radiation-induced pneumonitis.
• Who really wants to save the apes?