Early warning on measles through the neural networks / 中华流行病学杂志

To discuss the effects on early warning of measles, using the neural networks.Based on the available data through monthly and weekly reports on measles from January 1986 to August 2006 in Wuhan city. The modal was developed using the neural networks to predict and analyze the prevalence and incidence of measles. When the dynamic time series modal was established with back propagation(BP) networks consisting of two layers, if p was assigned as 9, the convergence speed was acceptable and the correlation coefficient was equal to 0.85. It was more acceptable for monthly forecasting the specific value, but better for weekly forecasting the classification under probabilistic neural networks (PNN). When data was big enough to serve the purpose, it seemed more feasible for early warning using the two-layer BP networks. However, when data was not enough, then PNN could be used for the purpose of prediction. This method seemed feasible to be used in the system for early warning.

An assessment on the effectiveness of condom use in reducing the incidence of chlamydia through mathematical modelling / 中华流行病学杂志

<p><b>OBJECTIVE</b>To determine the relationship between the rate of condom use and incidence of Chlamydia amongst commercial sex worker, using a mathematical model.</p><p><b>METHODS</b>Assuming that p(%) is the rate of condom use by female sex workers, and r(%) is the incidence of Chlamydia. If the use of condom increases by delta p, then the incidence of Chlamydia will decrease by delta r. k is the relative rate of change. Then, the mathematical model established becomes dr/dp = -kr.</p><p><b>RESULTS</b>The solution of the differential equation is r (p) = r (P0) exp [-k (p - p0)]. Using the surveillance data gathered from 100% Condom Use Program in Wuhan City, the k value is calculated to be 4.36. If k indicates the contribution coefficient of reducing Chlamydia after condom use, when the rate of condom use increases by 16%, then the incidence of Chlamydia will decrease by 50%. The average difference between the actual incidence and the incidence calculated from the mathematical model is only 6.2%. This result demonstrates a good fit. The predicted result of using this mathematical model shows that at the time of lower levels of condom use, a small increment on the rate of condom use would considerably reduce the infection rate of Chlamydia.</p><p><b>CONCLUSION</b>When k remains constant, this mathematical model reflects the qualitative relationship between the rate of condom use and the incidence of Chlamydia.</p>