Skip to main content

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

From: Comparing the performance of time series models with or without meteorological factors in predicting incident pulmonary tuberculosis in eastern China

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

  1. 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