Patrik Edén
Universitetslektor
Ensembles of genetically trained artificial neural networks for survival analysis
Författare
Summary, in English
We have developed a prognostic index model for survival data based on an ensemble of artificial neural networks that optimizes directly on the concordance index. Approximations of the c-index are avoided with the use of a genetic algorithm, which does not require gradient information. The model is compared with Cox proportional hazards (COX) and three support vector machine (SVM) models by Van Belle et al. [10] on two clinical data sets, and only with COX on one artificial data set. Results indicate comparable performance to COX and SVM models on clinical data and superior performance compared to COX on non-linear data.
Avdelning/ar
- Beräkningsbiologi och biologisk fysik - Genomgår omorganisation
Publiceringsår
2013
Språk
Engelska
Sidor
333-338
Publikation/Tidskrift/Serie
ESANN 2013 proceedings, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Dokumenttyp
Konferensbidrag
Ämne
- Other Computer and Information Science
Conference name
21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2013
Conference date
2013-04-24 - 2013-04-26
Conference place
Bruges, Belgium
Status
Published
ISBN/ISSN/Övrigt
- ISBN: 9782874190810