Dataset Information

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis.

ABSTRACT: In non-small-cell lung cancer radiotherapy, radiation pneumonitis?grade 2 (RP2) depends on patients' dosimetric, clinical, biological and genomic characteristics.We developed a Bayesian network (BN) approach to explore its potential for interpreting biophysical signaling pathways influencing RP2 from a heterogeneous dataset including single nucleotide polymorphisms, micro RNAs, cytokines, clinical data, and radiation treatment plans before and during the course of radiotherapy. Model building utilized 79 patients (21 with RP2) with complete data, and model testing used 50 additional patients with incomplete data. A developed large-scale Markov blanket approach selected relevant predictors. Resampling by k-fold cross-validation determined the optimal BN structure. Area under the receiver-operating characteristics curve (AUC) measured performance.Pre- and during-treatment BNs identified biophysical signaling pathways from the patients' relevant variables to RP2 risk. Internal cross-validation for the pre-BN yielded an AUC=0.82 which improved to 0.87 by incorporating during treatment changes. In the testing dataset, the pre- and during AUCs were 0.78 and 0.82, respectively.Our developed BN approach successfully handled a high number of heterogeneous variables in a small dataset, demonstrating potential for unraveling relevant biophysical features that could enhance prediction of RP2, although the current observations would require further independent validation.

SUBMITTER: Luo Y

PROVIDER: S-EPMC5386796 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis.

Luo Yi Y El Naqa Issam I McShan Daniel L DL Ray Dipankar D Lohse Ines I Matuszak Martha M MM Owen Dawn D Jolly Shruti S Lawrence Theodore S TS Kong Feng-Ming Spring FS Ten Haken Randall K RK

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology 20170222 1

<h4>Background</h4>In non-small-cell lung cancer radiotherapy, radiation pneumonitis≥grade 2 (RP2) depends on patients' dosimetric, clinical, biological and genomic characteristics.<h4>Methods</h4>We developed a Bayesian network (BN) approach to explore its potential for interpreting biophysical signaling pathways influencing RP2 from a heterogeneous dataset including single nucleotide polymorphisms, micro RNAs, cytokines, clinical data, and radiation treatment plans before and during the course ...[more]

PMID: 28237401

Similar Datasets

Project description:PurposeRadiation pneumonitis (RP) is a common and potentially life-threatening toxicity from lung cancer radiation therapy. Data sets reporting RP rates after postoperative radiation therapy (PORT) have historically been small and with predominantly outdated field designs and radiation techniques. We examined a large cohort of patients in this context to assess the incidence and causes of RP in the modern era.Methods and materialsWe reviewed 285 patients with non-small cell lung cancer treated with PORT at our institution from May 2004 to January 2017. Complete dosimetric data and clinical records were reviewed and analyzed with grade 2 or higher RP as the endpoint (RP2+) (Common Terminology Criteria for Adverse Events v4.0). Patients were a median of 67 years old (range, 28-87), and most had pathologic stage III non-small cell lung cancer (91%) and received trimodality therapy (90%). Systematic dosimetric analyses using Dx increments of 5% and Vx increments of 2 Gy were performed to robustly evaluate dosimetric variables. Lung V5 was also evaluated.ResultsThe incidence of RP2+ after PORT was 12.6%. Dosimetric factors most associated with RP2+ were total lungV4 (hazard ratio [HR] 1.04, P < .001) and heart V16 (HR 1.03, P = .001). On univariate analysis, the clinical factors of age (HR 1.05, P = .006) and carboplatin chemotherapy (HR 2.32, P = .012) were correlated with RP2+. On step-up multivariate analysis, only bivariate models remained significant, including lungV5 (HR 1.037, P < .001) and age (HR 1.052, P = .011).ConclusionsThe incidence of RP after PORT is consistent with the literature. Factors correlated with RP include lung and heart doses, age, and carboplatin chemotherapy. These data also suggest that elderly patients may be more susceptible to lower doses of radiation to the lung. Based on these data, dose constraints to limit the risk of RP2+ to <5% in the setting of PORT include lungV5 ≤65% in patients <65 years old and lungV5 ≤36% in patients 65 years or older.

Project description:BackgroundRadiation pneumonitis and immune-related pneumonitis have been studied independently, but little information has emerged on the interactions between radiation therapy (RT) and immune checkpoint inhibition (ICI). We examine whether RT and ICI are synergistic in causing pneumonitis.MethodsA retrospective cohort was assembled using the Surveillance, Epidemiology, and End Results-Medicare database, including Medicare beneficiaries diagnosed with American Joint Committee on Cancer 7th ed. (AJCC) stages IIIB-IV NSCLC between 2013-2017. Exposures to RT and ICI were determined by evaluating for treatment within 12 months of diagnosis (RT group and ICI group) and for a second exposure (e.g., ICI after RT) within 3 months after the first exposure (RT + ICI group). Untreated controls were matched to treated patients who were diagnosed in the same three-month window. A validated algorithm for identifying cases of pneumonitis in claims data was used to evaluate for the outcome within 6 months after treatment. The primary outcome was the relative excess risk due to interaction (RERI), a quantitative measure of additive interaction between two treatments.ResultsThere were 18,780 patients included in the analysis with 9,345 (49.8%), 7,533 (40.2%), 1,332 (7.1%), and 550 (2.9%) in the control, RT, ICI, and RT + ICI groups, respectively. Relative to controls, the hazards ratios of pneumonitis were 11.5 (95% CI: 7.9 to 17.0), 6.2 (95% CI: 3.8 to 10.3), and 10.7 (95% CI: 6.0 to 19.2) in the RT, ICI, and RT-ICI groups, respectively. The RERIs were -6.1 (95% CI: -13.1 to -0.6, P=0.97) and -4.0 (95% CI: -10.7 to 1.5, P=0.91) in the unadjusted and adjusted analyses, respectively, consistent with no evidence of additive interaction (RERI ≤0) between RT and ICI.ConclusionsIn this study of Medicare beneficiaries with advanced NSCLC, RT and ICI were, at most, additive rather than synergistic in causing pneumonitis. Pneumonitis risk in patients treated with RT and ICI is not more than could be expected from each therapy alone.

Dataset Information

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis.

Publications

Unraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets