Forecasting of non-accidental, cardiovascular, and respiratory mortality with environmental exposures adopting machine learning approaches
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Forecasting of non-accidental, cardiovascular, and respiratory mortality with environmental exposures adopting machine learning approaches. / Lee, Woojoo; Lim, Youn-Hee; Ha, Eunhee; Kim, Yoenjin; Lee, Won Kyung.
In: Environmental Science and Pollution Research, Vol. 89, 2022, p. 88318–88329.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Forecasting of non-accidental, cardiovascular, and respiratory mortality with environmental exposures adopting machine learning approaches
AU - Lee, Woojoo
AU - Lim, Youn-Hee
AU - Ha, Eunhee
AU - Kim, Yoenjin
AU - Lee, Won Kyung
N1 - Correction: 10.1007/s11356-022-22224-4
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - Cardiovascular diseases
KW - Deep learning
KW - Environmental exposures
KW - Machine learning
KW - Respiratory tract diseases
KW - TEMPERATURE
U2 - 10.1007/s11356-022-21768-9
DO - 10.1007/s11356-022-21768-9
M3 - Journal article
C2 - 35834079
VL - 89
SP - 88318
EP - 88329
JO - Environmental Science and Pollution Research
JF - Environmental Science and Pollution Research
SN - 0944-1344
ER -
ID: 314622811