Partial Logistic Artificial Neural Network for Competing Risks Regularized With Automatic Relevance Determination

Author

Lisboa, Paulo J G ; Etchells, Terence A. ; Jarman, Ian H. ; Arsene, Corneliu T C ; Aung, M. S Hane ; Eleuteri, Antonio ; Taktak, Azzam F G ; Ambrogi, Federico ; Boracchi, Patrizia ; Biganzoli, Elia

Author_Institution

Sch. of Comput. & Math. Sci., Liverpool John Moores Univ., Liverpool, UK

Volume

20

Issue

9

fYear

2009

Firstpage

1403

Lastpage

1416

Abstract

Time-to-event analysis is important in a wide range of applications from clinical prognosis to risk modeling for credit scoring and insurance. In risk modeling, it is sometimes required to make a simultaneous assessment of the hazard arising from two or more mutually exclusive factors. This paper applies to an existing neural network model for competing risks (PLANNCR), a Bayesian regularization with the standard approximation of the evidence to implement automatic relevance determination (PLANNCR-ARD). The theoretical framework for the model is described and its application is illustrated with reference to local and distal recurrence of breast cancer, using the data set of Veronesi (1995).

Keywords

Bayes methods; neural nets; Bayesian regularization; automatic relevance determination; clinical prognosis; competing risks; credit scoring; partial logistic artificial neural network; risk modeling; time-to-event analysis; Censorship; prognostic modeling; risk analysis; survival modeling; time-to-event data; Adolescent; Adult; Aged; Algorithms; Automation; Bayes Theorem; Breast Neoplasms; Computer Simulation; Databases, Factual; Female; Follow-Up Studies; Humans; Logistic Models; Middle Aged; Neoplasm Recurrence, Local; Neural Networks (Computer); Nonlinear Dynamics; Probability; Proportional Hazards Models; Risk; Survival Analysis; Time Factors; Young Adult;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2009.2023654

Filename

5170090