Title :
Partial logistic artificial neural networks (PLANN) for flexible modeling of censored survival data
Author :
Biganzoli, Elia M. ; Ambrogi, Federico ; Boracchi, Patrizia
Author_Institution :
Dept. of Med. Stat. & Bioinf., G.A. Maccacaro Univ. degli Studi di Milano, Milan, Italy
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 cumulative 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.
Keywords :
data handling; data structures; feedforward neural nets; medical computing; regression analysis; biological interest; censored survival data; data representation; feed forward artificial neural networks; linear flexible regression analysis; nonlinear flexible regression analysis; partial logistic artificial neural networks; specific error functions; statistical analysis; Artificial neural networks; Biological system modeling; Biomarkers; Diseases; Feeds; Hazards; Logistics; Probability; Regression analysis; Statistical analysis;
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2009.5178824