A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer.

2.50
Hdl Handle:
http://hdl.handle.net/10541/78801
Title:
A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer.
Authors:
Lisboa, P J G; Wong, H; Harris, P; Swindell, Ric
Abstract:
A Bayesian framework is introduced to carry out Automatic Relevance Determination (ARD) in feedforward neural networks to model censored data. A procedure to identify and interpret the prognostic group allocation is also described. These methodologies are applied to 1616 records routinely collected at Christie Hospital, in a monthly cohort study with 5-year follow-up. Two cohort studies are presented, for low- and high-risk patients allocated by standard clinical staging. The results of contrasting the Partial Logistic Artificial Neural Network (PLANN)-ARD model with the proportional hazards model are that the two are consistent, but the neural network may be more specific in the allocation of patients into prognostic groups. With automatic model selection, the regularised neural network is more conservative than the default stepwise forward selection procedure implemented by SPSS with the Akaike Information Criterion.
Affiliation:
School of Computing and Mathematical Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK. mwajner@ufrgs.br
Citation:
A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer. 2003, 28 (1):1-25 Artif Intell Med
Journal:
Artificial Intelligence in Medicine
Issue Date:
May-2003
URI:
http://hdl.handle.net/10541/78801
DOI:
10.1016/S0933-3657(03)00033-2
PubMed ID:
12850311
Type:
Article
Language:
en
ISSN:
0933-3657
Appears in Collections:
All Christie Publications

Full metadata record

DC FieldValue Language
dc.contributor.authorLisboa, P J G-
dc.contributor.authorWong, H-
dc.contributor.authorHarris, P-
dc.contributor.authorSwindell, Ric-
dc.date.accessioned2009-08-27T08:49:35Z-
dc.date.available2009-08-27T08:49:35Z-
dc.date.issued2003-05-
dc.identifier.citationA Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer. 2003, 28 (1):1-25 Artif Intell Meden
dc.identifier.issn0933-3657-
dc.identifier.pmid12850311-
dc.identifier.doi10.1016/S0933-3657(03)00033-2-
dc.identifier.urihttp://hdl.handle.net/10541/78801-
dc.description.abstractA Bayesian framework is introduced to carry out Automatic Relevance Determination (ARD) in feedforward neural networks to model censored data. A procedure to identify and interpret the prognostic group allocation is also described. These methodologies are applied to 1616 records routinely collected at Christie Hospital, in a monthly cohort study with 5-year follow-up. Two cohort studies are presented, for low- and high-risk patients allocated by standard clinical staging. The results of contrasting the Partial Logistic Artificial Neural Network (PLANN)-ARD model with the proportional hazards model are that the two are consistent, but the neural network may be more specific in the allocation of patients into prognostic groups. With automatic model selection, the regularised neural network is more conservative than the default stepwise forward selection procedure implemented by SPSS with the Akaike Information Criterion.en
dc.language.isoenen
dc.subjectBreast Canceren
dc.subject.meshBayes Theorem-
dc.subject.meshBreast Neoplasms-
dc.subject.meshCohort Studies-
dc.subject.meshFemale-
dc.subject.meshHumans-
dc.subject.meshModels, Theoretical-
dc.subject.meshNeural Networks (Computer)-
dc.subject.meshPrognosis-
dc.subject.meshRisk Assessment-
dc.titleA Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer.en
dc.typeArticleen
dc.contributor.departmentSchool of Computing and Mathematical Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, UK. mwajner@ufrgs.bren
dc.identifier.journalArtificial Intelligence in Medicineen

Related articles on PubMed

All Items in Christie are protected by copyright, with all rights reserved, unless otherwise indicated.