Name
Abstract | ||
|---|---|---|
Illustrates the relative performance of several techniques for nonlinear predictive modeling of simulated censored clinical survival data on the basis of measured risk factors: a neural net approach developed in our group, the CART (classification and regression trees) technique, and the Cox model with (and without) quadratic interactions. Simulated follow-up data is first generated by combining empirical multivariate distributions of clinical factors in breast cancer patients with hypothetical nonlinear risk structures, which are thus “known”. The performance of these analysis methods is evaluated by comparing the “known” and predicted scores on training and validation (generalization) samples containing 500 patients each. The neural net has the best performance for a complex risk structure in which three-factor interactions play an important role |
Year | DOI | Venue |
|---|---|---|
1999 | 10.1109/KES.1999.820185 | Adelaide, SA |
Keywords | Field | DocType |
forecasting theory,generalisation (artificial intelligence),medical computing,neural nets,pattern classification,performance evaluation,risk management,statistical analysis,trees (mathematics),3-factor interactions,CART technique,Cox models,breast cancer patients,classification,clinical factors,empirical multivariate distributions,generalization,neural nets,nonlinear predictive modeling,nonlinear risk structures,quadratic interactions,regression trees,relative performance,risk factors,simulated censored clinical survival data,simulated follow-up data,training samples,validation samples | Survival data,Regression,Proportional hazards model,Cart,Computer science,Multivariate statistics,Quadratic equation,Risk management,Artificial intelligence,Artificial neural network,Machine learning | Conference |
ISBN | Citations | PageRank |
0-7803-5578-4 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kates, R.E. | 1 | 0 | 0.34 |
| Berger, U. | 2 | 1 | 0.75 |
| Ulm, B.K. | 3 | 0 | 0.34 |
| Harbeck, N. | 4 | 0 | 0.34 |
| H. Graeff | 5 | 0 | 0.34 |
| M. Schmitt | 6 | 3 | 1.88 |