Continuous and Discrete Time Survival Analysis: Neural Network Approaches

Author

Eleuteri, A. ; Aung, M.S.H. ; Taktak, A.F.G. ; Damato, B. ; Lisboa, P.J.G.

Author_Institution

R. Liverpool Univ. Hosp., Liverpool

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

5420

Lastpage

5423

Abstract

In this paper we describe and compare two neural network models aimed at survival analysis modeling, based on formulations in continuous and discrete time. Learning in both models is approached in a Bayesian inference framework. We test the models on a real survival analysis problem, and we show that both models exhibit good discrimination and calibration capabilities. The C index of discrimination varied from 0.8 (SE=0.093) at year 1, to 0.75 (SE=0.034) at year 7 for the continuous time model; from 0.81 (SE=0.07) at year 1, to 0.75 (SE=0.033) at year 7 for the discrete time model. For both models the calibration was good (p<0.05) up to 7 years.

Keywords

Bayes methods; learning (artificial intelligence); medical computing; neural nets; Bayesian inference; calibration; continuous time model; continuous time survival analysis; discrete time model; discrete time survival analysis; learning; neural network; survival analysis modeling; Bayesian methods; Calibration; Computer architecture; Continuous time systems; Hazards; Hospitals; Neural networks; Parametric statistics; Proposals; Testing; Algorithms; Data Interpretation, Statistical; Discriminant Analysis; Eye Neoplasms; Humans; Incidence; Melanoma; Neural Networks (Computer); Pattern Recognition, Automated; Risk Assessment; Risk Factors; Survival Analysis; Survival Rate;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4353568

Filename

4353568