Study on cholecystitis incidence rate forecasting with BP neural network method

Objective The different BP structures and algorithm of artificial neural network (ANN) are applied to seek the cholecystitis incidence rate forecasting method based on the meteorological data for 7 years in Haixizhou region, Qinghai province. Methods It is logical to select the three meteorological factors monthly mean temperature, mean pressure, mean relative humidity, as the input in the forecasting model. The forecasting model of cholecystitis incidence rate in Haixizhou region has three network structures (7-9-1), flowing from input factors determination to layer and node choice then to function activation of each layer and output factors determination. Results It can be conclude that the accelerated BP algorithm has faster training speed and higher convergence accuracy compared with the normal BP, and can reach the high forecasting precision of 98%, much larger than that of traditional multi-linear regression model. Conclusion This cholecystitis incidence rate forecasting model based on accelerated BP neural network has characteristics of simplicity, convenience, high precision and intelligence, and so can be extended in field of regional cholecystitis incidence rate forecast.