The purpose of this work is to present an evidence that cancer is a complex system, that future prognostic factors will be nonmonotonic and they will exhibit complex interactions. Because TNM staging systems do not give the desired accuracy, artificial neural networks (ANNs) were considered. It was shown that ANNs can perform as well as the best traditional prediction methods, and they can capture the power of nonmonotonic predictors and discover complex interactions.
|Number of pages||3|
|State||Published - 1994|
|Event||Proceedings of the 1994 IEEE Instrumentation and Measurement Technology Conference. Part 2 (of 3) - Hamamatsu, Jpn|
Duration: 10 May 1994 → 12 May 1994
|Conference||Proceedings of the 1994 IEEE Instrumentation and Measurement Technology Conference. Part 2 (of 3)|
|Period||10/05/94 → 12/05/94|