Application of a support vector machine on the prediction of the incidences of infectious diseases
Xie He-chua · Xiandai yufang yixue · 2013
OBJECTIVE The study focused on the prediction of infectious disease morbidity by establishing a prediction model using support vector regression(SVR) and the incidence of bacillary dysentery in China, aiming to explore new techniques for the prediction of infectious diseases. METHODS A model was established based on the monthly morbidity of bacillary dysentery in China between 2004 and 2009 by using a time series-based support vector machine. The model was then used to predict morbidity of bacillary dysentery for the year of 2010. RESULTS The prediction was effective and consistent with the actual trends of morbidity(MSE = 0.0896, MAPE = 13.23%). CONCLUSION Support vector machine is suitable for the preliminary prediction of morbidity trends of infectious diseases.