School of Energy and Environment, Southeast University, Nanjing, 210096, China; State Key Laboratory of Environmental Medicine Engineering, Ministry of Education, Southeast University, Nanjing, 210096, PR China.
School of Architecture and Urban Planning, Nanjing University, No. 22, Hankoulu Road, Nanjing, 210093, PR China.
Chemosphere. 2020 Oct;257:127176. doi: 10.1016/j.chemosphere.2020.127176. Epub 2020 May 27.
The efficiency of disease prevention and medical care service necessitated the prediction of incidence. However, predictive accuracy and power were largely impeded in a complex system including multiple environmental stressors and health outcome of which the occurrence might be episodic and irregular in time. In this study, we established four different deep learning (DL) models to capture inherent long-term dependencies in sequences and potential complex relationships among constituents by initiating with the original input into a representation at a higher abstract level. We collected 504,555 and 786,324 hospital outpatient visits of grouped categories of respiratory (RESD) and circulatory system disease (CCD), respectively, in Nanjing from 2013 through 2018. The matched observations in time-series that might pose risk to cardiopulmonary health involved conventional air pollutants concentrations and metrological conditions. The results showed that a well-trained network architecture built upon long short-term memory block and a working day enhancer achieved optimal performance by three quantitative statistics, i.e., 0.879 and 0.902 of Nash-Sutcliffe efficiency, 0.921% and 0.667% of percent bias, and 0.347 and 0.312 of root mean square error-standard deviation ratio for RESD and CCD hospital visits, respectively. We observed the non-linear association of nitrogen dioxide and ambient air temperature with CCD hospital visits. Furthermore, these two environmental stressors were identified as the most sensitive predictive variables, and exerted synergetic effect for two health outcomes, particular in winter season. Our study indicated that high-quality surveillance data of atmospheric environments could provide novel opportunity for anticipating temporal trend of cardiopulmonary health outcomes based on DL model.
疾病预防和医疗服务的效率需要进行预测。然而，在包括多个环境压力源和健康结果的复杂系统中，预测的准确性和能力受到了很大的阻碍，因为这些健康结果的发生可能是间歇性的，且时间上不规则。在这项研究中，我们建立了四个不同的深度学习（DL）模型，通过将原始输入初始化为更高抽象层次的表示，来捕捉序列中的固有长期依赖关系和成分之间潜在的复杂关系。我们收集了 2013 年至 2018 年期间南京市 504555 例和 786324 例分组类别为呼吸系统（RESD）和循环系统疾病（CCD）的医院门诊就诊记录。时间序列中可能对心肺健康构成风险的匹配观察涉及常规空气污染物浓度和气象条件。结果表明，基于长短期记忆块和工作日增强器构建的训练有素的网络架构通过三个定量统计量实现了最佳性能，即 RESD 和 CCD 医院就诊的纳什-苏特克里夫效率分别为 0.879 和 0.902、偏度百分比分别为 0.921%和 0.667%、均方根误差-标准差比分别为 0.347 和 0.312。我们观察到二氧化氮和环境空气温度与 CCD 医院就诊之间存在非线性关联。此外，这两个环境压力源被确定为最敏感的预测变量，并且对两种健康结果产生协同作用，特别是在冬季。我们的研究表明，高质量的大气环境监测数据为基于 DL 模型预测心肺健康结果的时间趋势提供了新的机会。
