Healthcare Revenue Forecasting Based on ARIMA and Linear Regression Models

The aim of this study is to provide accurate forecasting of hospital outpatient revenue using ARIMA and linear regression models to support hospital financial management and resource allocation. Firstly, missing values were dealt with in the study by differential mean padding method and the data were systematically tested for smoothness, seasonality, trend, and covariance. Then, based on various medical data of the Department of Rehabilitation Medicine, ARIMA and Prophet models were used to predict the outpatient revenue of the ward respectively. Then, a weighted average integration model and a linear regression integration model were developed to predict the outpatient revenue of other wards by combining the prediction results of ARIMA and Prophet models. The integrated model was also fine-tuned using existing ward data to improve prediction accuracy. Finally, the predictive effects of the models were compared by various assessment indicators to select the best model. The results of the study show that the constructed time series prediction model has good effect in medical revenue prediction, which provides an important reference for hospitals in the optimization of intelligent medical system.