Table 4.
Evaluation of the performance of the ARIMA, ARIMAX, and RNN models in predicting the monthly number of pulmonary tuberculosis cases in the three cities in 2018
| City | Diagnostic indicator | Model | ||
|---|---|---|---|---|
| ARIMA | ARIMAX | RNN | ||
| Xuzhou | MAPE (%) | 12.54 | 11.96 | 12.36 |
| RMSE | 36.194 | 33.956 | 34.785 | |
| Nantong | MAPE (%) | 15.57 | 11.16 | 14.09 |
| RMSE | 34.073 | 25.884 | 31.828 | |
| Wuxi | MAPE (%) | 9.70 | 9.66 | 12.50 |
| RMSE | 19.545 | 19.026 | 26.019 | |
ARIMA autoregressive integrated moving average, ARIMAX autoregressive integrated moving average with exogenous variables, RNN recurrent neural network, MAPE mean absolute percentage error, RMSE root mean square error