SUMMARY
The problem of mathematical support development is solved to automate the process of individual health prediction of hypertensivepatient. The object of study is the process of model synthesis for medical diagnosis. The subject of study are methods of neuro-fuzzy model synthesis for medical diagnosis. The purpose of the work is to improve the efficiency of the process of neuro-fuzzy network synthesis for constructing diagnostic models based on training samples. The stochastic method for the synthesis of neuro-fuzzy models based on parallel computing is proposed. It uses the stochastic approach for finding the values of adjustable parameters, and consists in the distribution of the most demanding stages on the nodes in parallel computing system. The proposed method can reduce the time of parameters calculation (the weighting coefficients and parameters of membership functions of neurons) of synthesized neuromodels. The software implementing proposed method is developed. The experiments to study the properties of the proposed method are conducted. The experimental results allow to recommend the proposed method for use in practice.