作者: Hazlina Hamdan , Jonathan M Garibaldi , None
DOI:
关键词:
摘要: Intelligent Modelling and Analysis (IMA) Research Group, School of Computer ScienceThe University Nottingham, Jubilee Campus, Wollaton Road, NG8 1BB, U.K.fhzh, jmgg@cs.nott.ac.ukKeywords: Adaptive neuro-fuzzy inference system, Survival analysis, Breast cancer, Nottingham prognostic index.Abstract: Fuzzy systems have been applied in recent years various medical fields due to their ability toobtain good results featuring white-box models. Neuro-Fuzzy Inference System (ANFIS), whichcombines adaptive neural network capabilities with the fuzzy logic qualitative approach, has previouslyused modelling survival breast cancer patients based on patient groups derived from NottinghamPrognostic Index (NPI), as discussed our previous paper. In this paper, we extend work toexamine whether ANFIS model can be trained better match data NPI variable representedas a real number, rather than categorical group. Two input models developed withdifferent structures ANFIS. The performance these models, capability predict ratein following operative surgery for is examined.