Evolutionary Forecasting Method of Treatment Results

Processing method of poorly formalized multivariable arrays of biomedical information, based on evolutional method for solving of extreme tasks of multivariable function, is presented in the article. Method allows predicting treatment results take account of biomedical and social features of the patients. Method allows selecting the weights of input parameters without preliminary reduction of the multidimensional feature space which eliminates the loss of important information and to identify weak links in these information arrays. Results of numerical experiments which have shown high efficiency of method are presented. Value of the mean average prognostication error amounted to 10-17%. Developed method can be used in various subject areas in which information about the objects kept in the large volume data sets, are described in the protocols of "input-output", and for them the hypothesis of monotony of the decision- making in the local area is valid