Medical service demand forecasting using a hybrid model based on ARIMA and self-adaptive filtering method

Abstract

Background: Accurate forecasting of medical service demand is beneficial for the reasonable healthcare resource planning and allocation. The daily outpatient volume is characterized by randomness, periodicity and trend, and the time series methods, like ARIMA are often used for short-term outpatient visits forecasting. Therefore, to further enlarge the prediction horizon and improve the prediction accuracy, a hybrid prediction model integrating ARIMA and self-adaptive filtering method is proposed.

Methods: The ARIMA model is first used to identify the features like cyclicity and trend of the time series data and to estimate the model parameters. The parameters are then adjusted by the steepest descent algorithm in the adaptive filtering method to reduce the prediction error. The hybrid model is validated and compared with traditional ARIMA by several test sets from the Time Series Data Library (TSDL), a weekly emergency department (ED) visit case from literature study, and the real cases of prenatal examinations and B-ultrasounds in a maternal and child health care center (MCHCC) in Ningbo.

Results: For TSDL cases the prediction accuracy of the hybrid prediction is improved by 80-99% compared with the ARIMA model. For the weekly ED visit case, the forecasting results of the hybrid model are better than those of both traditional ARIMA and ANN model, and similar to the ANN combined data decomposition model mentioned in the literature. For the actual data of MCHCC in Ningbo, the MAPE predicted by the ARIMA model in the two departments was 18.53 and 27.69%, respectively, and the hybrid models were 2.79 and 1.25%, respectively.

Conclusions: The hybrid prediction model outperforms the traditional ARIMA model in both accurate predicting result with smaller average relative error and the applicability for short-term and medium-term prediction.

Keywords: ARIMA model; Hybrid forecasting model; Medical forecasting; Self-adaptive filtering; Time series.

Fig. 1

The flow chat of hybrid forecasting model Based on ARIMA and Self-adaptive Filtering Method. ACF: Auto-correlation function, PACF: Partial auto-correlation function, MAE: Average absolute error

Fig. 2

Time series of observed and predicted monthly average employment from 1962 to 1975 and values of monthly average gasoline production from 1956 to 1995. ARIMA: auto-regressive integrated moving average, Hybrid model: ARIMA-self-adaptive filtering hybrid forecasting model

Fig. 3

Error convergence in term of iterations and iteration rounds

Fig. 4

The forecasting results using the hybrid forecasting method

Fig. 5

Daily time-series data of PEV and BUEA in January 2017–March 2018. PEV: prenatal examination visits, BUEV: B-ultrasound examination visitors

Fig. 6

Comparison of PEV and BUEA forecasting values and observed values. ARIMA: auto-regressive integrated moving average, Hybrid model: ARIMA-self-adaptive filtering hybrid forecasting model, PEV: prenatal examination visits, BUEV: B-ultrasound examination visit