An investigation of seasonal trend model in the prediction of the number of outpatient visits in dog injury clinics

Abstract

Abstract
Background: Dog bite injuries pose a significant public health concern, with outpatient visits to dog injury clinics showing potential seasonal and temporal patterns. Accurate prediction of these visits can help optimize resource allocation and improve prevention efforts. This study investigates the application of a seasonal trend model to predict the number of outpatient visits in dog injury clinics.
Methods: Outpatient visit data from dog injury clinics over [specific years, e.g., 2016–2022] were collected. Time-series analysis was conducted using a seasonal trend decomposition model and a seasonal autoregressive integrated moving average (SARIMA) model to identify patterns and forecast future visits. Model performance was evaluated based on goodness-of-fit measures such as mean absolute percentage error (MAPE) and root mean square error (RMSE).
Results: The number of outpatient visits exhibited a clear seasonal trend, with peaks occurring in [e.g., summer months] and lower numbers in [e.g., winter months]. The seasonal trend model accurately captured these fluctuations and provided reliable forecasts of visit numbers. The SARIMA model showed good fit to the observed data, with MAPE and RMSE values of [X%] and [Y], respectively, indicating high predictive accuracy.
Conclusion: The seasonal trend model is effective in predicting the number of outpatient visits to dog injury clinics, capturing both seasonal and long-term trends. These findings can support public health planning, resource allocation, and targeted prevention campaigns to reduce the burden of dog bite injuries.
Keywords: dog bite injuries, outpatient visits, seasonal trend model, time series analysis, prediction