Objective: Set up the model of forecasting the number of circulatorys death toll based on back-propagation (BP) artificial neural networks discuss the relationship between the circulatory system diseases death toll meteorological factors and ambient air pollution.
Methods: The data of tem deaths, meteorological factors, and ambient air pollution within the m 2004 to 2009 in Nanjing were collected. On the basis of analyzing the ficient between CSDDT meteorological factors and ambient air pollution, leutral network model of CSDDT was built for 2004 - 2008 based on factors and ambient air pollution within the same time, and the data of 2009 est the predictive power of the model.
Results: There was a closely system diseases relationship between meteorological factors, ambient air pollution and the circulatory system diseases death toll. The ANN model structure was 17 -16 -1, 17 input notes, 16 hidden notes and 1 output note. The training precision was 0. 005 and the final error was 0. 004 999 42 after 487 training steps. The results of forecast show that predict accuracy over 78. 62%.
Conclusions: This method is easy to be finished with smaller error, and higher ability on circulatory system death toll on independent prediction, which can provide a new method for forecasting medical-meteorological forecast and have the value of further research.