File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

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

TitleUnraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis
Authors
KeywordsBiophysical interactions
Lung cancer
Radiation pneumonitis
Bayesian network analysis
Issue Date2017
Citation
Radiotherapy and Oncology, 2017, v. 123, n. 1, p. 85-92 How to Cite?
Abstract© 2017 Elsevier B.V. Background In non-small-cell lung cancer radiotherapy, radiation pneumonitis ≥ grade 2 (RP2) depends on patients’ dosimetric, clinical, biological and genomic characteristics. Methods 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. Results 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. Conclusions 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.
Persistent Identifierhttp://hdl.handle.net/10722/266783
ISSN
2017 Impact Factor: 4.942
2015 SCImago Journal Rankings: 2.654
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLuo, Yi-
dc.contributor.authorEl Naqa, Issam-
dc.contributor.authorMcShan, Daniel L.-
dc.contributor.authorRay, Dipankar-
dc.contributor.authorLohse, Ines-
dc.contributor.authorMatuszak, Martha M.-
dc.contributor.authorOwen, Dawn-
dc.contributor.authorJolly, Shruti-
dc.contributor.authorLawrence, Theodore S.-
dc.contributor.authorKong, Feng Ming (Spring)-
dc.contributor.authorTen Haken, Randall K.-
dc.date.accessioned2019-01-31T07:19:34Z-
dc.date.available2019-01-31T07:19:34Z-
dc.date.issued2017-
dc.identifier.citationRadiotherapy and Oncology, 2017, v. 123, n. 1, p. 85-92-
dc.identifier.issn0167-8140-
dc.identifier.urihttp://hdl.handle.net/10722/266783-
dc.description.abstract© 2017 Elsevier B.V. Background In non-small-cell lung cancer radiotherapy, radiation pneumonitis ≥ grade 2 (RP2) depends on patients’ dosimetric, clinical, biological and genomic characteristics. Methods 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. Results 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. Conclusions 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.-
dc.languageeng-
dc.relation.ispartofRadiotherapy and Oncology-
dc.subjectBiophysical interactions-
dc.subjectLung cancer-
dc.subjectRadiation pneumonitis-
dc.subjectBayesian network analysis-
dc.titleUnraveling biophysical interactions of radiation pneumonitis in non-small-cell lung cancer via Bayesian network analysis-
dc.typeArticle-
dc.description.natureLink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.radonc.2017.02.004-
dc.identifier.pmid28237401-
dc.identifier.scopuseid_2-s2.0-85010761422-
dc.identifier.volume123-
dc.identifier.issue1-
dc.identifier.spage85-
dc.identifier.epage92-
dc.identifier.eissn1879-0887-
dc.identifier.isiWOS:000400719500013-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats