Partial logistic artificial neural networks (PLANN) for flexible modeling of censored survival data

Authors:
Elia M. Biganzoli;Federico Ambrogi;Patrizia Boracchi
Affiliations:
Department of Medical Statistics and Bioinformatics "G. A. Maccacaro", Università degli Studi di Milano and Insituto Nazionale dei Tumori, Milano, Italy;Department of Medical Statistics and Bioinformatics "G. A. Maccacaro", Università degli Studi di Milano, Milano, Italy;Department of Medical Statistics and Bioinformatics "G. A. Maccacaro", Università degli Studi di Milano, Milano, Italy
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 7
Cited 0

Statistical modelling in GLIM

Statistical modelling in GLIM
An introduction to genetic algorithms

An introduction to genetic algorithms
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
A general framework for neural network models on censored survival data

Neural Networks
Artificial neural network for the joint modelling of discrete cause-specific hazards

Artificial Intelligence in Medicine
Partial logistic artificial neural network for competing risks regularized with automatic relevance determination

IEEE Transactions on Neural Networks
A Bayesian neural network approach for modelling censored data with an application to prognosis after surgery for breast cancer

Artificial Intelligence in Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linear and non-linear flexible regression analysis techniques, such as those based on splines and feed forward artificial neural networks (FFANN), have been proposed for the statistical analysis of censored survival time data, to account for the presence of non linear effects of predictors. Among survival functions, the hazard has a biological interest for the study of the disease dynamics, moreover it allows for the estimation of cum ulative incidence functions for predicting outcome probabilities over follow-up. Therefore, specific error functions and data representation have been introduced for FFANN extensions of generalized linear models, in the perspective of modelling the hazard function of censored survival data. These techniques can be applied to account for the prognostic contribution of new biomarkers in addition to the traditional ones.