Estimation of the Most Influential Factors for Survival Probability Prediction of Prostate Cancer Patients.

The objective of the study was to address some important questions related to prostate cancer treatments and survivorship. One of possibility to improve the survival probability of prostate cancer patients is to improve predictive strategies. Therefore in this article was created short-term multistep ahead predictive model for survival probability prediction of prostate cancer patients. Neuro-fuzzy model was used to select the most important inputs for the predictive model. As the inputs, current and time lagged variables were used. The results could be useful for simplification of predictive models to avoid multiple inputs.