Comparison of ARIMAX and multivariate LSTM model in predicting daily death toll in Yancheng City / 公共卫生与预防医学

Objective To compare the effects of Autoregressive Integrated Moving Average model-X (ARIMAX) and multivariate Long Short Term Memory Network (multivariate LSTM) in the prediction of daily total death toll in Yancheng City. Methods Based on total death toll data, meteorological data and air quality data from January 1st, 2014 to June 30th,2017 in Yancheng City, Jiangsu province, ARIMAX model and multivariate LSTM model were established to predict the daily total death toll from July 1st,2017 to July 14th,2017. RMSE, MAE and MAPE were used as evaluation indexes to compare the prediction effects of these two models. Results RMSE, MAE and MAPE of ARIMAX model and multivariate LSTM model were 20.742、15.094、9.921 and 47.182、35.863、19.633, respectively. Conclusion ARIMAX model is better than multivariate LSTM model to predict the daily death toll in Yancheng city.

A time-series study on the impact of air pollution on the death of permanent residents in Yancheng City / 公共卫生与预防医学

Objective To investigate the effects of air pollution on non-accidental death of residents in Yancheng City. Methods Data of daily air pollutions (PM2.5, PM10, NO2, SO2 and O3), average temperature, average relative humidity, and daily death information during 2014-2019 were collected. The time series semi parametric generalized additive model was used to analyze the impact of short-term exposure of air pollutants on non-accidental death in Yancheng City. Results The average daily non-accidental deaths of the entire population, respiratory system, and circulatory system were 154, 25, and 51, respectively. With the increase of 10 µg/m3 SO2, the risk of the estimated non-accidental death and respiratory death was increased by 1.19% (95%CI: 0.26%-2.12%) and 2.37% (95%CI: 0.65%-4.12 %), respectively. With the increase of 10 µ g/m3 NO2, the risk of the estimated non-accidental death, circulatory system death and respiratory death was increased by 1.50%（95%CI:0.94%-2.05%）, 1.11%（95%CI:0.08%-2.16%）, and 1.53%（95%CI:0.71%-2.36%）, respectively. With the increase of 10 µg/m3 O3, the risk of the estimated non-accidental death, circulatory system death and respiratory death was increased by 0.64%（95%CI: 0.25%-1.04%）, 0.81%（95%CI: 0.04%-1.58%）, and 0.78%（95%CI: 0.18%-1.37%）, respectively. Conclusion The short-term exposure of air pollutants affects the non-accidental death of the residents in Yancheng, and there are lag effects, of which NO2, SO2 and O3 have a greater impact.