Individual prediction of the hypertensive patient condition based on computational intelligence

The problem of development of information technology for individual health prediction of hypertensive patient is solved. The method of neuro-fuzzy networks synthesis based on parallel computing is proposed. It uses the stochastic approach for finding the values of adjustable parameters of neuro-fuzzy networks. It consists of the distribution of the most resource-intensive stages on the nodes of parallel computing system that reduces the time of calculation of synthesized neuro-model´s parameters. The software implementing the proposed parallel method is developed. The experiments on the solution of practical problem of individual health prediction of hypertensive patient are conducted.