Does the addition of air-quality factors to historical HFMD rates and temperature data improve the forecasting accuracy of hand, foot, and mouth disease outbreaks?
Incorporating air-quality factors alongside historical disease rates and temperature data in an XGBoost model improves the forecasting accuracy of hand, foot, and mouth disease outbreaks.
Hand, foot, and mouth disease (HFMD) is caused by a group of enteroviruses. It infects millions of children in the Southeast Asian area. An accurate forecasting of outbreaks of HFMD could facilitate public health officials to suggest public health actions earlier. Many researchers tried to develop an early warning system for HFMD to lower the damage caused by a HFMD outbreak. The research data based on daily level could help figure out the relationship between HFMD and environmental factors, but nevertheless is difficult to collect. In this study, we collected the daily clinical data from the Shenzhen Health Information Center and multiple environmental factors to analyze the outbreaks of HFMD. Considering the incubation period of HFMD, we fed the previous 60 days' HFMD rates, 7 days' temperature factors and 7 days' air-quality factors into the tree model, XGBoost. The following conclusions were drawn in this study: i) Compared with the model only using the previous HFMD rate and temperature factors, the addition of the air-quality factors could make the model better, improving MAE nearly 16.7%. ii) By analyzing the Pearson correlation, we found that the temperature showed a positive correlation and the air quality showed a negative correlation for the HFMD outbreaks. Improving the air quality, especially decreasing PM2.5 and PM10 could decrease the risk of HFMD outbreaks.
Ren et al. (2018) studied this question.