1.Modification effects of temperature on outpatient visits caused by ozone in Linzhi
Hejia SONG ; Yan' ; e CAO ; Yuzhu HUANG ; Yonghong LI ; Yibin CHENG ; Zhen NI ; Zhuoma PINGCUO ; Xiaoyuan YAO
Journal of Public Health and Preventive Medicine 2022;33(1):17-21
Objective To investigate the modification effect of atmospheric temperature on outpatient visits caused by O3 in Linzhi City. Methods The daily outpatient data, the daily O3 concentration and daily meteorological data (including daily average temperature, average relative humidity, etc.) in Linzhi City from 2018 to 2019 were collected. The distributed lag non-liner-model (DLNM) was used to quantitatively evaluate the impact of O3 in different temperature layers on the risk of outpatient visits. Results At low temperature layers, the cumulative relative risk (CRR) of total outpatient visits and non-injury outpatient visits increased by 53.8%(4.2% -126.9%) and 59.1%(5.8% -139.2%)for every 10 μg/m3 increase of O3 concentration, respectively. The subgroup analysis showed that for every 10 μg/m3 increase of O3 concentration at low temperature, the CRR of patients with circulatory diseases, men, women, and people being <14 years old and 14-65 years old increased by 152.1% (15.1% - 451.9%), 58.3% (2.1%-145.5%), 49.2% (3.0% -116.1%), 39.6% (2.5% - 90.3%), and 61% (0.8%-157.1%), respectively. Conclusion The average temperature may have a modifying effect on the outpatient visits caused by O3 in Linzhi City. In general, the cumulative risk increases as the temperature decreases.
2.Comparison of ARIMAX and multivariate LSTM model in predicting daily death toll in Yancheng City
Yushu HUANG ; Hejia SONG ; Rui ZHANG ; Yonghong LI ; Liancheng HUANG ; Yibin CHENG ; Xiaoyuan YAO
Journal of Public Health and Preventive Medicine 2021;32(5):6-10
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.