A hybrid ARIMA-LSTM model optimized by BP in the forecast of outpatient visits
- PDF / 1,568,458 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 12 Downloads / 183 Views
ORIGINAL RESEARCH
A hybrid ARIMA‑LSTM model optimized by BP in the forecast of outpatient visits Yamin Deng1,2 · Huifang Fan1 · Shiman Wu1 Received: 31 January 2020 / Accepted: 3 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Effective hospital outpatient forecasting is an important prerequisite for modern hospitals to implement intelligent management of medical resources. As outpatient visits flow may be complex and diverse volatility, we propose a hybrid Autoregressive Integrated Moving Average (ARIMA)-Long Short Term Memory (LSTM) model, which hybridizes the ARIMA model and LSTM model to obtain the linear tendency and nonlinear tendency correspondingly. Instead of the traditional methods that artificially assume the linear components and nonlinear components should be linearly added, we propose employing backpropagation neural networks (BP) to imitate the real relationship between them. The proposed hybrid model is applied to real data analysis and experimental analysis to justify its performance against single ARIMA model, single LSTM model and the hybrid ARIMA-LSTM model based on the traditional method. Compared with competitors, the proposed hybrid model produced the lowest RMSE, MAE and MAPE. It achieves more accurate and stable prediction. Therefore, the proposed model can be a promising alternative in outpatient visit predictive problems. Keywords Hybrid forecasting model · Neural networks · ARIMA · LSTM · BP · Outpatient visits
1 Introduction As the aging population increases, medical services in China are facing a shortage of health resources and a disproportional distribution of medical investment (Kadri et al. 2014; Luo et al. 2017). With the rapid development of the Internet of Medical Things, hospital medical work has become increasingly meticulous, intelligent and efficient. Thus, how to make reasonable health resource management decisions has received more attention. In addition, accurately forecasting the healthcare demand and resource availability becomes more important and critical (Kadri et al. 2014; Liu 2009). Outpatient departments (ODs) which are windows Electronic supplementary material The online version of this article (https://doi.org/10.1007/s12652-020-02602-x) contains supplementary material, which is available to authorized users. * Yamin Deng [email protected] 1
Department of Statistics, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, People’s Republic of China
Division of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi, People’s Republic of China
2
of hospital service, experiences increasing pressure year by year (Luo et al. 2017). Effective hospital outpatient forecasting is an important prerequisite for modern hospitals to manage medical resources intelligently. Accurate outpatient visit prediction aids in planning and decision-making for future arrangements and is the foundation for better utilization of resources and improving the levels of service (Zhou et al. 2016)
Data Loading...
