ObjectiveTo establish an autoregressive integrated moving average (ARIMA) model for predicting the demand of clinical erythrocyte blood in the urban area of Suzhou, and to guide the blood collection and supply institutions to reasonably collect and scientifically allocate blood resources in the region based on the demand.

MethodsThe historical data of regional clinical blood were combed, and time series analysis method was adopted to select the monthly data of clinical use of erythrocyte blood in Suzhou urban area from 2009 to 2019 for modeling.SPSS 26 software was used for data analysis, and the ARIMA model was constructed.The optimal model of clinical erythrocyte blood prediction was determined by model recognition, parameter estimation and optimal model test.The optimal model was used to predict the clinical consumption of erythrocyte blood from January to November 2020, and the predicted value was compared with the actual value to verify the prediction effect of the model.

ResultsThe optimal model was ARIMA(0, 1, 1)(0, 1, 1)12, and the values of ACF autocorrelation function and PACF partial autocorrelation function of residual were both within 95%CI.Meanwhile, the Yang Box Q statistic value was 17.992 (P>0.05), indicating that there was no autocorrelation of residual sequence, which passed the white noise test.The clinical consumption of erythrocyte blood in Suzhou urban area from January to November 2020 was predicted, and the curve trend of the predicted value was basically the same as the actual value, and the predicted value was within 95% CI, and the average relative error was small (8.21%), indicating that the prediction effect of the model was good.

ConclusionsARIMA(0, 1, 1)(0, 1, 1)12 is the optimal model for the prediction of clinical erythrocyte blood demand in Suzhou area.