Predicting monthly hospital outpatient visits based on meteorological environmental factors using the ARIMA model

Abstract

Accurate forecasting of hospital outpatient visits is beneficial to the rational planning and allocation of medical resources to meet medical needs. Several studies have suggested that outpatient visits are related to meteorological environmental factors. We aimed to use the autoregressive integrated moving average (ARIMA) model to analyze the relationship between meteorological environmental factors and outpatient visits. Also, outpatient visits can be forecast for the future period. Monthly outpatient visits and meteorological environmental factors were collected from January 2015 to July 2021. An ARIMAX model was constructed by incorporating meteorological environmental factors as covariates to the ARIMA model, by evaluating the stationary $${R}^{2}$$ R 2 , coefficient of determination $${R}^{2}$$ R 2 , mean absolute percentage error (MAPE), and normalized Bayesian information criterion (BIC). The ARIMA $${(0, 1, 1) (0, 1, 0)}_{12}$$ ( 0 , 1 , 1 ) ( 0 , 1 , 0 ) 12 model with the covariates of $$\text{SO}_{2}$$ SO 2 , $${PM}_{2.5}$$ PM 2.5 , and $$\text{CO}$$ CO was the optimal model. Monthly outpatient visits in 2019 can be predicted using average data from past years. The relative error between the predicted and actual values for 2019 was 2.77%. Our study suggests that $$\text{SO}_{2}$$ SO 2 , $${PM}_{2.5}$$ PM 2.5 , and $$\text{CO}$$ CO concentration have a significant impact on outpatient visits. The model built has excellent predictive performance and can provide some references for the scientific management of hospitals to allocate staff and resources.

Statistical machine learning models for prediction of China’s maritime emergency patients in dynamic: ARIMA model, SARIMA model, and dynamic Bayesian network model

“…Peak periods for rescue and treatment operations typically occur during the winter months of October, November, and December, while quieter months are observed in June and July. Similar seasonal patterns have been identified in other studies ( 32 , 33 ). However, both the DBN model and the time series model effectively capture these seasonal fluctuations and trends in rescue numbers, serving as dynamic tools for forecasting data with periodic characteristics.…”

Chinas Urban and Rural CPI Prediction Based on ARIMA Model

“…Hongye Cai and Wenxuan Qiu use ARIMA (2,2,3) model to predict Shenzhen GDP in the next 5 years and the relative error between the actual data and the prediction results is less than 3 percent [6]. Lu Bai, Ke Lu et al combined ARIMA (0, 1, 1) (0, 1, 0) [12] model with the covariates of PM2.5, SO2, and CO to form the SARIMAX model, which also has an error of less than 3 percent [7]. In 2021, Yao Ma and others once analyzed and predicted the CPI of China, the United States, and Germany.…”

A New Hybrid Prediction Method of El Niño/La Niña Events by Combining TimesNet and ARIMA

“…In this study, the expert modeller [56] available in SPSS was employed to ascertain the ARIMA parameters, namely p and q. The original series exhibited stationarity following the first-order differencing, thereby enabling the identification of the appropriate value of d as 1.…”