NEURAL-NETWORK ANALYSIS TO PREDICT TREATMENT OUTCOME

Citation
Hj. Kappen et Jp. Neijt, NEURAL-NETWORK ANALYSIS TO PREDICT TREATMENT OUTCOME, Annals of oncology, 4, 1993, pp. 31-34
Citations number
24
Categorie Soggetti
Oncology
Journal title
ISSN journal
09237534
Volume
4
Year of publication
1993
Supplement
4
Pages
31 - 34
Database
ISI
SICI code
0923-7534(1993)4:<31:NATPTO>2.0.ZU;2-T
Abstract
Background: Quantitative methods for the analysis of prognostic inform ation are important in order to use this knowledge optimally. The neur al network is a new quantitative method where the fundamental building blocks are units which can be likened to neurons, and weighted connec tions which can be likened to synapses. The more the hidden units, the more complex the patterns that can be learnt. Materials and methods: Data from two Dutch studies in ovarian cancer were used to compare the previously reported survival rates predicted by the Cox's prognostic index with the prediction obtained by a neural network. Results: Both the Cox's analysis and the neural network agreed on residual tumour si ze, stage, and performance status as being important for survival. The neural network identified additional predictive factors such as place of diagnosis and age. As the Cox's prognostic index has not been test ed to predict survival on an independent data set a comparison with th e results obtained in the neural network test set could not be perform ed. Conclusions: Neural networks perform at least as well as Cox's met hod for the prediction of survival, and prognostic factors can easily be identified. The analysis not only revealed the predictive power of some characteristics, but also the non-predictive power of the others.