Construction of a prediction model for nosocomial infection in hospital ICU of tropical region
Objective To predict the incidence of nosocomial infection in hospital intensive care unit(ICU)of tropical region,and to provide scientific basis for the prevention and control of nosocomial infection.Methods Multivariate analysis method was used to construct a prediction model for nosocomial infection in ICU of a comprehensive hospital in Haikou City,and the fitting and predictive performances were evaluated.Results The average absolute errors for predicted values of ARIMA model and grey prediction model were 14.56%and 16.39%,respectively.The fitting and predictive performance of ARIMA model was better than that of grey prediction model.Conclusion The ARIMA model can better predict the risk of nosocomial infections in ICU,and can provide reference for overall monitoring and management of nosocomial infections.
tropical regionnosocomial infectionintensive care unitprediction model
NETL
NSTL
万方数据
