Show simple item record

dc.contributor.authorKanwar, MK
dc.contributor.authorGomberg-Maitland, M
dc.contributor.authorHoeper, M
dc.contributor.authorPausch, C
dc.contributor.authorPittrow, D
dc.contributor.authorStrange, G
dc.contributor.authorAnderson, JJ
dc.contributor.authorZhao, C
dc.contributor.authorScott, JV
dc.contributor.authorDruzdzel, MJ
dc.contributor.authorKraisangka, J
dc.contributor.authorLohmueller, L
dc.contributor.authorAntaki, J
dc.contributor.authorBenza, RL
dc.date.accessioned2020-09-22T04:19:40Z
dc.date.available2020-09-22T04:19:40Z
dc.date.issued2020
dc.identifier.issn0903-1936
dc.identifier.doi10.1183/13993003.00008-2020
dc.identifier.urihttp://hdl.handle.net/10072/397776
dc.description.abstractBACKGROUND: Current risk stratification tools in pulmonary arterial hypertension (PAH) are limited in their discriminatory abilities, partly due to the assumption that prognostic clinical variables have an independent and linear relationship to clinical outcomes. We sought to demonstrate the utility of Bayesian network-based machine learning in enhancing the predictive ability of an existing state-of-the-art risk stratification tool, REVEAL 2.0. METHODS: We derived a tree-augmented naïve Bayes model (titled PHORA) to predict 1-year survival in PAH patients included in the REVEAL registry, using the same variables and cut-points found in REVEAL 2.0. PHORA models were validated internally (within the REVEAL registry) and externally (in the COMPERA and PHSANZ registries). Patients were classified as low-, intermediate- and high-risk (<5%, 5-20% and >10% 12-month mortality, respectively) based on the 2015 European Society of Cardiology/European Respiratory Society guidelines. RESULTS: PHORA had an area under the curve (AUC) of 0.80 for predicting 1-year survival, which was an improvement over REVEAL 2.0 (AUC 0.76). When validated in the COMPERA and PHSANZ registries, PHORA demonstrated an AUC of 0.74 and 0.80, respectively. 1-year survival rates predicted by PHORA were greater for patients with lower risk scores and poorer for those with higher risk scores (p<0.001), with excellent separation between low-, intermediate- and high-risk groups in all three registries. CONCLUSION: Our Bayesian network-derived risk prediction model, PHORA, demonstrated an improvement in discrimination over existing models. This is reflective of the ability of Bayesian network-based models to account for the interrelationships between clinical variables on outcome, and tolerance to missing data elements when calculating predictions.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherEuropean Respiratory Society (ERS)
dc.relation.ispartofpagefrom2000008
dc.relation.ispartofissue2
dc.relation.ispartofjournalThe European respiratory journal
dc.relation.ispartofvolume56
dc.subject.fieldofresearchApplied statistics
dc.subject.fieldofresearchBiomedical and clinical sciences
dc.subject.fieldofresearchClinical sciences
dc.subject.fieldofresearchcode490501
dc.subject.fieldofresearchcode32
dc.subject.fieldofresearchcode3202
dc.titleRisk stratification in pulmonary arterial hypertension using Bayesian analysis
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationKanwar, MK; Gomberg-Maitland, M; Hoeper, M; Pausch, C; Pittrow, D; Strange, G; Anderson, JJ; Zhao, C; Scott, JV; Druzdzel, MJ; Kraisangka, J; Lohmueller, L; Antaki, J; Benza, RL, Risk stratification in pulmonary arterial hypertension using Bayesian analysis, The European respiratory journal, 2020, 56 (2), pp. 2000008
dcterms.dateAccepted2020-04-22
dc.date.updated2020-09-22T04:13:18Z
gro.hasfulltextNo Full Text
gro.griffith.authorAnderson, James


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record