Study on the causes of hypertension with improved BP neural network

An improved neural network based on L-M (Levenberg-Marquard) algorithm neural network has been applied to the model for the analysis of factors on Hypertension. It can remedy the shortcoming of the slow convergence rate of traditional BP algorithm neural network. This model can determine which factors are the main reasons for high blood pressure. We have adopted the lattice fuzzy close-degree assessment and expert scoring method which quantified the various data of the factors on high blood pressure. We used the matlab to program and simulate. The results showed that: the improved BP neural network, can determine the main factors which causing the high blood pressure correctly, the error between the Predictive value and the actual value is very small. it reached the desired goal.