Model Cross-Validation Evaluation Indicators.

BackgroundWhile time-series models have been applied to forecast brucellosis incidence in China, systematic comparisons of multiple models remain relatively limited. This study aimed to elucidate the epidemic characteristics of human brucellosis and to provide a comparative assessment of several time-series prediction models, in order to identify a suitable predictive framework for future incidence forecasting.MethodsMonthly and annual incidence rates (per 100,000 population) of brucellosis in China from January 2011 to December 2020 were used as raw data. Seven time-series models were developed and compared using R software (version 4.3.1): Seasonal Autoregressive Integrated Moving Average (SARIMA), Holt-Winters additive model, Holt-Winters multiplicative model, Neural Network Autoregressive (NNAR) model, Exponential Smoothing State Space (ETS) model, TBATS model, and Prophet model. A rolling-window cross-validation was applied to assess model stability. Model performance was evaluated using root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE).ResultsAmong the seven models evaluated, the Holt-Winters multiplicative model demonstrated the most stable and superior predictive performance on the test set (MAE = 0.034, RMSE = 0.040, MAPE = 14.881%, MASE = 0.891), which serves as strong evidence for its best generalization capability among the compared models.ConclusionsGiven its stable and superior performance in the test set, the Holt-Winters multiplicative model is recommended for short-term brucellosis forecasting in China. It captures the characteristic spring-summer peak, and its integration into surveillance systems could enhance early warning and targeted interventions.