Clinical management often relies on stratification of patients by outcome. The application of flexible non-linear time-to-event models to stratification of patient populations into different and clinically meaningful risk groups is currently an important area of research. This paper proposes a definition of prognostic index for neural network models of survival. This index underpins different stratification strategies including k-means clustering, regression trees and recursive application of the log-rank test. It was obtained with multiple imputation applied to a neural network model of survival fitted to a substantial data set for breast cancer (n=931) and was evaluated with a large out of sample data set (n=4,083). It was found that the constraint imposed by regression trees on the form of the permitted rules makes it less specific than stratifying directly from the prognostic index and deriving unconstrained low-order rules with Orthogonal Search Rule Extraction.
Stratification Methodologies for Neural Networks Models of Survival / A.S. Fernandes, I.H. Jarman, T.A. Etchells, J.M. Fonseca, E. Biganzoli, C. Bajdik, P.J.G. Lisboa (LECTURE NOTES IN COMPUTER SCIENCE). - In: Bio-Inspired Systems: Computational and Ambient Intelligence[s.l] : Springer, 2009. - ISBN 978-3-642-02477-1. - pp. 989-996 (( Intervento presentato al 10. convegno IWANN International Work-Conference on Artificial Neural Networks : June, 10th - 12th tenutosi a Salamanca (Spain) nel 2009 [10.1007/978-3-642-02478-8_124].
Stratification Methodologies for Neural Networks Models of Survival
E. Biganzoli;
2009
Abstract
Clinical management often relies on stratification of patients by outcome. The application of flexible non-linear time-to-event models to stratification of patient populations into different and clinically meaningful risk groups is currently an important area of research. This paper proposes a definition of prognostic index for neural network models of survival. This index underpins different stratification strategies including k-means clustering, regression trees and recursive application of the log-rank test. It was obtained with multiple imputation applied to a neural network model of survival fitted to a substantial data set for breast cancer (n=931) and was evaluated with a large out of sample data set (n=4,083). It was found that the constraint imposed by regression trees on the form of the permitted rules makes it less specific than stratifying directly from the prognostic index and deriving unconstrained low-order rules with Orthogonal Search Rule Extraction.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
