Flexible modelling in survival analysis can be useful both for exploratory and predictive purposes. Feed forward neural networks were recently considered for flexible non-linear modelling of censored survival data through the generalization of both discrete and continuous time models. We show that by treating the time interval as an input variable in a standard feed forward network with logistic activation and entropy error function, it is possible to estimate smoothed discrete hazards as conditional probabilities of failure. We considered an easily implementable approach with a fast selection criteria of the best configurations. Examples on data sets from two clinical trials are provided. The proposed artificial neural network (ANN) approach can be applied for the estimation of the functional relationships between covariates and time in survival data to improve model predictivity in the presence of complex prognostic relationships.

Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach / E. Biganzoli, P. Boracchi, L. Mariani, E. Marubini. - In: STATISTICS IN MEDICINE. - ISSN 0277-6715. - 17:10(1998 May 30), pp. 1169-86-1186.

Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach

E. Biganzoli
Primo
;
P. Boracchi
Secondo
;
1998

Abstract

Flexible modelling in survival analysis can be useful both for exploratory and predictive purposes. Feed forward neural networks were recently considered for flexible non-linear modelling of censored survival data through the generalization of both discrete and continuous time models. We show that by treating the time interval as an input variable in a standard feed forward network with logistic activation and entropy error function, it is possible to estimate smoothed discrete hazards as conditional probabilities of failure. We considered an easily implementable approach with a fast selection criteria of the best configurations. Examples on data sets from two clinical trials are provided. The proposed artificial neural network (ANN) approach can be applied for the estimation of the functional relationships between covariates and time in survival data to improve model predictivity in the presence of complex prognostic relationships.
Probability; Lung Neoplasms; Neural Networks (Computer); Logistic Models; Humans; Head and Neck Neoplasms; Prognosis; Clinical Trials as Topic; Data Interpretation, Statistical; Proportional Hazards Models; Survival Analysis
Settore MED/01 - Statistica Medica
Article (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/190096
Citazioni
  • ???jsp.display-item.citation.pmc??? 32
  • Scopus 186
  • ???jsp.display-item.citation.isi??? ND
social impact