Department of Public Health Sciences, Graduate School of Public Health, Seoul National University, Seoul, Republic of Korea.
Department of Public Health, University of Copenhagen, Copenhagen, Denmark.
Environ Sci Pollut Res Int. 2022 Dec;29(58):88318-88329. doi: 10.1007/s11356-022-21768-9. Epub 2022 Jul 14.
Environmental exposure constantly changes with time and various interactions that can affect health outcomes. Machine learning (ML) or deep learning (DL) algorithms have been used to solve complex problems, such as multiple exposures and their interactions. This study developed predictive models for cause-specific mortality using ML and DL algorithms with the daily or hourly measured meteorological and air pollution data. The ML algorithm improved the performance compared to the conventional methods, even though the optimal algorithm depended on the adverse health outcomes. The best algorithms were extreme gradient boosting, ridge, and elastic net, respectively, for non-accidental, cardiovascular, and respiratory mortality with daily measurement; they were superior to the generalized additive model reducing a mean absolute error by 4.7%, 4.9%, and 16.8%, respectively. With hourly measurements, the ML model tended to outperform the conventional models, even though hourly data, instead of daily data, did not enhance the performance in some models. The proposed model allows a better understanding and development of robust predictive models for health outcomes using multiple environmental exposures.
环境暴露随时间不断变化，并受到各种相互作用的影响，这些相互作用可能会影响健康结果。机器学习 (ML) 或深度学习 (DL) 算法已被用于解决复杂问题，例如多重暴露及其相互作用。本研究使用 ML 和 DL 算法，结合每日或每小时测量的气象和空气污染数据，开发了针对特定原因死亡率的预测模型。与传统方法相比，ML 算法提高了性能，尽管最佳算法取决于不良健康结果。对于非意外、心血管和呼吸死亡率，每日测量的最佳算法分别为极端梯度提升、岭和弹性网，它们分别优于广义加性模型，降低平均绝对误差分别为 4.7%、4.9%和 16.8%。对于每小时测量，即使使用每小时数据而不是每日数据并未在某些模型中提高性能，ML 模型也倾向于优于传统模型。该模型有助于更好地理解和开发使用多种环境暴露的稳健预测健康结果的模型。
