AUTHOR=Feng Tianyu , Zheng Zhou , Xu Jiaying , Liu Minghui , Li Ming , Jia Huanhuan , Yu Xihe TITLE=The comparative analysis of SARIMA, Facebook Prophet, and LSTM for road traffic injury prediction in Northeast China JOURNAL=Frontiers in Public Health VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.946563 DOI=10.3389/fpubh.2022.946563 ISSN=2296-2565 ABSTRACT=Abstract Background: Road traffic injuries (RTIs) are a serious public health problem in developing countries. However, the number and trend of patients admitted to hospital for RTIs is difficult to predict. The aim of this study is to develop a reliable short-term prediction model to forecast the number of RTIs in Northeast China through a comparative study to provide a policy basis for healthcare administration. Methods: Seasonal auto-regressive integrated moving average (SARIMA), long shot term memory (LSTM) and Facebook Prophet (Prophet) models were used for time series prediction of the number of RTIs inpatients. The three models were trained using data from 2015 to 2019, and their prediction accuracy was compared using data from 2020 as a test set. The parameters of the SARIMA model were determined using the autocorrelation function (ACF) and the partial autocorrelation function (PACF). The LSTM uses linear as the activation function, the mean square error (MSE) as the loss function and the Adam optimizer to construct the model, while the Prophet model is built on the Python platform. The root mean squared error (RMSE) and mean absolute error (MAE) are used to measure the predictive performance of the model. Results: In this study, the LSTM model had the highest prediction accuracy, followed by the Prophet model, and the SARIMA model had the lowest prediction accuracy. the trend in medical expenditure of RTIs inpatients overlapped highly with the number of RTIs inpatients. Conclusions: By adjusting the activation function and optimizer the LSTM predicts the number of RTIs inpatients more accurately and robustly than other models. the LSTM can provide a better basis for planning and management in the healthcare administration.