Modeling and Predicting Pulmonary Tuberculosis Incidence and Its Association with Air Pollution and Meteorological Factors Using an ARIMAX Model: An Ecological Study in Ningbo of China

Abstract

The autoregressive integrated moving average with exogenous regressors (ARIMAX) modeling studies of pulmonary tuberculosis (PTB) are still rare. This study aims to explore whether incorporating air pollution and meteorological factors can improve the performance of a time series model in predicting PTB. We collected the monthly incidence of PTB, records of six air pollutants and six meteorological factors in Ningbo of China from January 2015 to December 2019. Then, we constructed the ARIMA, univariate ARIMAX, and multivariate ARIMAX models. The ARIMAX model incorporated ambient factors, while the ARIMA model did not. After prewhitening, the cross-correlation analysis showed that PTB incidence was related to air pollution and meteorological factors with a lag effect. Air pollution and meteorological factors also had a correlation. We found that the multivariate ARIMAX model incorporating both the ozone with 0-month lag and the atmospheric pressure with 11-month lag had the best performance for predicting the incidence of PTB in 2019, with the lowest fitted mean absolute percentage error (MAPE) of 2.9097% and test MAPE of 9.2643%. However, ARIMAX has limited improvement in prediction accuracy compared with the ARIMA model. Our study also suggests the role of protecting the environment and reducing pollutants in controlling PTB and other infectious diseases.

Keywords: air pollution; meteorological factor; pulmonary tuberculosis; time series.

Figure 1

Time series of the monthly incidence of PTB, the monthly average air pollutants concentration, and meteorological factors in Ningbo from 2015 to 2019.

Figure 2

Actual incidence, fitted and predicted incidences of ARIMA (0,0,0) (1,1,0)₁₂ and ARIMA (0,0,0) (1,1,0)₁₂ with O₃ (0-month lag) and MAP (11-month lag) in Ningbo.