Cardiorespiratory Mortality Prediction Based on Air Pollution Using Tree-Based Ensemble Models
Abstract
Air pollution has a substantial negative impact on human wellbeing and health. Cardiorespiratory mortality is one of the primary effects of air pollution. In this study, we provide analysis of air pollution, cardiorespiratory mortality and the cardiorespiratory mortality is predicted based on air pollution using tree-based ensemble models. The tree-based ensemble models utilized in this study are Voting Regressor (VR), Random Forest (RF), Gradient Tree Boosting (GB), and Extreme Gradient Boosting (XGBoost). The used dataset contains data for five research locations: Shah Alam (SA), Klang (KLN), Putrajaya (PUJ), Cheras, Kuala Lumpur (CKL), and Petaling Jaya (PJ) from January 2006 to December 2016. The results show that XGBoost and VR models outperformed the rest of the models with the best evaluation metric scores in the Klang study area, XGBoost(MAE:0.005, RMSE:0.010, MAPE:0.70%) and VR (MAE:0.005, RMSE:0.011, MAPE:0.70%). The results reveal that the utilized models provided an excellent and accurate prediction of cardiorespiratory mortality based on air pollution and can follow the trend of cardiorespiratory mortality.
References
[1] WHO, “World Health Organization - Health Burden.” 2021, [Online]. Available: https://www.who.int/health-topics/cardiovascular-diseases.
[2] Y. Liu, J. Sun, Y. Gou, X. Sun, D. Zhang, and F. Xue, “Analysis of short-term effects of air pollution on cardiovascular disease using Bayesian spatio-temporal models,” Int. J. Environ. Res. Public Health, vol. 17, no. 3, p. 879, 2020.
[3] Q. Chen, Q. Wang, B. Xu, Y. Xu, Z. Ding, and H. Sun, “Air pollution and cardiovascular mortality in Nanjing, China: Evidence highlighting the roles of cumulative exposure and mortality displacement,” Chemosphere, vol. 265, p. 129035, 2021.
[4] N. Sarrafzadegan and N. Mohammmadifard, “Cardiovascular disease in Iran in the last 40 years: prevalence, mortality, morbidity, challenges and strategies for cardiovascular prevention,” Arch. Iran. Med., vol. 22, no. 4, pp. 204–210, 2019.
[5] W. R. W. Mahiyuddin, “AIR POLLUTION AND CARDIORESPIRATORY HOSPITALIZATION TRENDS BASED ON THE DAYS OF THE WEEK IN KLANG VALLEY, MALAYSIA,” Asia Pacific Environ. Occup. Heal. J., vol. 4, no. 3, 2018.
[6] C. L. Lokotola, C. Y. Wright, and J. Wichmann, “Temperature as a modifier of the effects of air pollution on cardiovascular disease hospital admissions in Cape Town, South Africa,” Environ. Sci. Pollut. Res., vol. 27, no. 14, pp. 16677–16685, 2020.
[7] J. Huang, X. Pan, X. Guo, and G. Li, “Health impact of China’s Air Pollution Prevention and Control Action Plan: an analysis of national air quality monitoring and mortality data,” Lancet Planet. Heal., vol. 2, no. 7, pp. e313–e323, 2018, doi: 10.1016/S2542-5196(18)30141-4.
[8] D. J. Nowak, S. Hirabayashi, M. Doyle, M. McGovern, and J. Pasher, “Air pollution removal by urban forests in Canada and its effect on air quality and human health,” Urban For. Urban Green., vol. 29, no. April 2017, pp. 40–48, 2018, doi: 10.1016/j.ufug.2017.10.019.
[9] U. Im et al., “Assessment and economic valuation of air pollution impacts on human health over Europe and the United States as calculated by a multi-model ensemble in the framework of AQMEII3,” Atmos. Chem. Phys., vol. 18, no. 8, pp. 5967–5989, 2018.
[10] S. G. Al-Kindi, R. D. Brook, S. Biswal, and S. Rajagopalan, “Environmental determinants of cardiovascular disease: lessons learned from air pollution,” Nat. Rev. Cardiol., vol. 17, no. 10, pp. 656–672, 2020.
[11] S. Jaafari, A. A. Shabani, M. Moeinaddini, A. Danehkar, and Y. Sakieh, “Applying landscape metrics and structural equation modeling to predict the effect of urban green space on air pollution and respiratory mortality in Tehran,” Environ. Monit. Assess., vol. 192, pp. 1–15, 2020.
[12] O.-J. Kim, S.-Y. Kim, and H. Kim, “Association between long-term exposure to particulate matter air pollution and mortality in a South Korean National Cohort: comparison across different exposure assessment approaches,” Int. J. Environ. Res. Public Health, vol. 14, no. 10, p. 1103, 2017.
[13] P. Yin et al., “Particulate air pollution and mortality in 38 of China’s largest cities: Time series analysis,” BMJ, vol. 356, p. j667, 2017, doi: 10.1136/bmj.j667.
[14] Q. Di et al., “Air pollution and mortality in the Medicare population,” N. Engl. J. Med., vol. 376, no. 26, pp. 2513–2522, 2017.
[15] Y. Liu et al., “Short-term exposure to ambient air pollution and mortality from myocardial infarction,” J. Am. Coll. Cardiol., vol. 77, no. 3, pp. 271–281, 2021.
[16] C. Bellinger, M. S. Mohomed Jabbar, O. Zaïane, and A. Osornio-Vargas, “A systematic review of data mining and machine learning for air pollution epidemiology,” BMC Public Health, vol. 17, no. 1, pp. 1–19, 2017, doi: 10.1515/JPEM.2001.14.2.151.
[17] D. N. Khojasteh, G. Goudarzi, R. Taghizadeh-Mehrjardi, A. B. Asumadu-Sakyi, and M. Fehresti-Sani, “Long-term effects of outdoor air pollution on mortality and morbidity--prediction using nonlinear autoregressive and artificial neural networks models,” Atmos. Pollut. Res., vol. 12, no. 2, pp. 46–56, 2021.
[18] K. C. Dewi, W. F. Mustika, and H. Murfi, “Ensemble learning for predicting mortality rates affected by air quality,” in Journal of Physics: Conference Series, 2019, doi: 10.1088/1742-6596/1192/1/012021.
[19] C. Vitolo, M. Scutari, M. Ghalaieny, A. Tucker, and A. Russell, “Modeling Air Pollution, Climate, and Health Data Using Bayesian Networks: A Case Study of the English Regions,” Earth Sp. Sci., vol. 5, no. 4, pp. 76–88, 2018, doi: 10.1002/2017EA000326.
[20] Y. Li, Z. Chen, and J. Li, “How many people died due to PM2.5 and where the mortality risks increased? A case study in Beijing,” in International Geoscience and Remote Sensing Symposium (IGARSS), 2017, doi: 10.1109/IGARSS.2017.8126997.
[21] Theborneopost, “Malaysia’s population stood at 32.6 million in Q4 2018.” 2018, Accessed: Dec. 31, 2020. [Online]. Available: http://www.theborneopost.com/2019/02/13/malaysias-population-stood-at-32-6-million-in-q4-2018/.
[22] A. Populations, “Shah Alam.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://all-populations.com/en/my/population-of-shah-alam.html.
[23] WorldoMeters, “Malaysia Population 2020,” Worldometers. 2020, Accessed: Dec. 31, 2020. [Online]. Available: https://www.worldometers.info/world-population/malaysia-population/.
[24] iContainers, “List of busiest container ports.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://www.icontainers.com/top-20-ports-in-the-world/.
[25] Wikipedia, “Petaling Jaya.” pp. 1–8, 2020, Accessed: Dec. 31, 2020. [Online]. Available: https://en.wikipedia.org/wiki/Petaling%7B%5C_%7DJaya.
[26] A. Population, “Kuala Lumpur.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://all-populations.com/en/my/population-of-kuala-lumpur.html.
[27] R. S. A. Usmani, W. N. F. B. W. Azmi, A. M. Abdullahi, I. A. T. Hashem, and T. R. Pillai, “A novel feature engineering algorithm for air quality datasets,” Indones. J. Electr. Eng. Comput. Sci., vol. 19, no. 3, Sep. 2020.
[28] R. S. A. Usmani, T. R. Pillai, I. A. T. Hashem, N. Z. Jhanjhi, and A. Saeed, “A Spatial Feature Engineering Algorithm for Creating Air Pollution Health Datasets,” International Journal of Cognitive Computing in Engineering. Elsevier, Nov. 2020, doi: 10.1016/j.ijcce.2020.11.004.
[29] J. Eisfeld, “International Statistical Classification of Diseases and Related Health Problems,” TSQ Transgender Stud. Q., 2014, doi: 10.1215/23289252-2399740.
[30] M. A. Hassan, A. Khalil, S. Kaseb, and M. A. Kassem, “Exploring the potential of tree-based ensemble methods in solar radiation modeling,” Appl. Energy, 2017, doi: 10.1016/j.apenergy.2017.06.104.
[31] T. Hochkirchen, “Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning,” J. R. Stat. Soc. Ser. A (Statistics Soc., 2010, doi: 10.1111/j.1467-985x.2009.00634_10.x.
[32] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[33] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794, doi: 10.1145/2939672.2939785.
[34] R. S. A. Usmani, I. A. T. Hashem, T. R. Pillai, A. Saeed, and A. M. Abdullahi, “Geographic Information System and Big Spatial Data,” Int. J. Enterp. Inf. Syst., vol. 16, no. 4, 2020.
[35] Kaggle, “Predict impact of air quality on mortality rates - Overview.” 2016, [Online]. Available: https://www.kaggle.com/c/predict-impact-of-air-quality-on-death-rates/overview.
[36] Y. Jie, “Air pollution associated with sumatran forest fires and mortality on the malay peninsula,” Polish J. Environ. Stud., vol. 26, no. 1, pp. 163–171, 2017, doi: 10.15244/pjoes/64642.
[37] N. A. Mabahwi, O. L. H. Leh, S. N. A. M. Musthafa, and K. Aiyub, “Air quality-related human health in an urban region. Case study: State of Selangor, Malaysia,” EnvironmentAsia, vol. 11, no. 1, pp. 194–216, 2018, doi: 10.14456/ea.2018.15.
[38] M. A. B. A. Tajudin et al., “Risk of concentrations of major air pollutants on the prevalence of cardiovascular and respiratory diseases in urbanized area of Kuala Lumpur, Malaysia,” Ecotoxicol. Environ. Saf., vol. 171, no. June 2018, pp. 290–300, 2019, doi: 10.1016/j.ecoenv.2018.12.057.
[2] Y. Liu, J. Sun, Y. Gou, X. Sun, D. Zhang, and F. Xue, “Analysis of short-term effects of air pollution on cardiovascular disease using Bayesian spatio-temporal models,” Int. J. Environ. Res. Public Health, vol. 17, no. 3, p. 879, 2020.
[3] Q. Chen, Q. Wang, B. Xu, Y. Xu, Z. Ding, and H. Sun, “Air pollution and cardiovascular mortality in Nanjing, China: Evidence highlighting the roles of cumulative exposure and mortality displacement,” Chemosphere, vol. 265, p. 129035, 2021.
[4] N. Sarrafzadegan and N. Mohammmadifard, “Cardiovascular disease in Iran in the last 40 years: prevalence, mortality, morbidity, challenges and strategies for cardiovascular prevention,” Arch. Iran. Med., vol. 22, no. 4, pp. 204–210, 2019.
[5] W. R. W. Mahiyuddin, “AIR POLLUTION AND CARDIORESPIRATORY HOSPITALIZATION TRENDS BASED ON THE DAYS OF THE WEEK IN KLANG VALLEY, MALAYSIA,” Asia Pacific Environ. Occup. Heal. J., vol. 4, no. 3, 2018.
[6] C. L. Lokotola, C. Y. Wright, and J. Wichmann, “Temperature as a modifier of the effects of air pollution on cardiovascular disease hospital admissions in Cape Town, South Africa,” Environ. Sci. Pollut. Res., vol. 27, no. 14, pp. 16677–16685, 2020.
[7] J. Huang, X. Pan, X. Guo, and G. Li, “Health impact of China’s Air Pollution Prevention and Control Action Plan: an analysis of national air quality monitoring and mortality data,” Lancet Planet. Heal., vol. 2, no. 7, pp. e313–e323, 2018, doi: 10.1016/S2542-5196(18)30141-4.
[8] D. J. Nowak, S. Hirabayashi, M. Doyle, M. McGovern, and J. Pasher, “Air pollution removal by urban forests in Canada and its effect on air quality and human health,” Urban For. Urban Green., vol. 29, no. April 2017, pp. 40–48, 2018, doi: 10.1016/j.ufug.2017.10.019.
[9] U. Im et al., “Assessment and economic valuation of air pollution impacts on human health over Europe and the United States as calculated by a multi-model ensemble in the framework of AQMEII3,” Atmos. Chem. Phys., vol. 18, no. 8, pp. 5967–5989, 2018.
[10] S. G. Al-Kindi, R. D. Brook, S. Biswal, and S. Rajagopalan, “Environmental determinants of cardiovascular disease: lessons learned from air pollution,” Nat. Rev. Cardiol., vol. 17, no. 10, pp. 656–672, 2020.
[11] S. Jaafari, A. A. Shabani, M. Moeinaddini, A. Danehkar, and Y. Sakieh, “Applying landscape metrics and structural equation modeling to predict the effect of urban green space on air pollution and respiratory mortality in Tehran,” Environ. Monit. Assess., vol. 192, pp. 1–15, 2020.
[12] O.-J. Kim, S.-Y. Kim, and H. Kim, “Association between long-term exposure to particulate matter air pollution and mortality in a South Korean National Cohort: comparison across different exposure assessment approaches,” Int. J. Environ. Res. Public Health, vol. 14, no. 10, p. 1103, 2017.
[13] P. Yin et al., “Particulate air pollution and mortality in 38 of China’s largest cities: Time series analysis,” BMJ, vol. 356, p. j667, 2017, doi: 10.1136/bmj.j667.
[14] Q. Di et al., “Air pollution and mortality in the Medicare population,” N. Engl. J. Med., vol. 376, no. 26, pp. 2513–2522, 2017.
[15] Y. Liu et al., “Short-term exposure to ambient air pollution and mortality from myocardial infarction,” J. Am. Coll. Cardiol., vol. 77, no. 3, pp. 271–281, 2021.
[16] C. Bellinger, M. S. Mohomed Jabbar, O. Zaïane, and A. Osornio-Vargas, “A systematic review of data mining and machine learning for air pollution epidemiology,” BMC Public Health, vol. 17, no. 1, pp. 1–19, 2017, doi: 10.1515/JPEM.2001.14.2.151.
[17] D. N. Khojasteh, G. Goudarzi, R. Taghizadeh-Mehrjardi, A. B. Asumadu-Sakyi, and M. Fehresti-Sani, “Long-term effects of outdoor air pollution on mortality and morbidity--prediction using nonlinear autoregressive and artificial neural networks models,” Atmos. Pollut. Res., vol. 12, no. 2, pp. 46–56, 2021.
[18] K. C. Dewi, W. F. Mustika, and H. Murfi, “Ensemble learning for predicting mortality rates affected by air quality,” in Journal of Physics: Conference Series, 2019, doi: 10.1088/1742-6596/1192/1/012021.
[19] C. Vitolo, M. Scutari, M. Ghalaieny, A. Tucker, and A. Russell, “Modeling Air Pollution, Climate, and Health Data Using Bayesian Networks: A Case Study of the English Regions,” Earth Sp. Sci., vol. 5, no. 4, pp. 76–88, 2018, doi: 10.1002/2017EA000326.
[20] Y. Li, Z. Chen, and J. Li, “How many people died due to PM2.5 and where the mortality risks increased? A case study in Beijing,” in International Geoscience and Remote Sensing Symposium (IGARSS), 2017, doi: 10.1109/IGARSS.2017.8126997.
[21] Theborneopost, “Malaysia’s population stood at 32.6 million in Q4 2018.” 2018, Accessed: Dec. 31, 2020. [Online]. Available: http://www.theborneopost.com/2019/02/13/malaysias-population-stood-at-32-6-million-in-q4-2018/.
[22] A. Populations, “Shah Alam.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://all-populations.com/en/my/population-of-shah-alam.html.
[23] WorldoMeters, “Malaysia Population 2020,” Worldometers. 2020, Accessed: Dec. 31, 2020. [Online]. Available: https://www.worldometers.info/world-population/malaysia-population/.
[24] iContainers, “List of busiest container ports.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://www.icontainers.com/top-20-ports-in-the-world/.
[25] Wikipedia, “Petaling Jaya.” pp. 1–8, 2020, Accessed: Dec. 31, 2020. [Online]. Available: https://en.wikipedia.org/wiki/Petaling%7B%5C_%7DJaya.
[26] A. Population, “Kuala Lumpur.” 2021, Accessed: Jan. 13, 2021. [Online]. Available: https://all-populations.com/en/my/population-of-kuala-lumpur.html.
[27] R. S. A. Usmani, W. N. F. B. W. Azmi, A. M. Abdullahi, I. A. T. Hashem, and T. R. Pillai, “A novel feature engineering algorithm for air quality datasets,” Indones. J. Electr. Eng. Comput. Sci., vol. 19, no. 3, Sep. 2020.
[28] R. S. A. Usmani, T. R. Pillai, I. A. T. Hashem, N. Z. Jhanjhi, and A. Saeed, “A Spatial Feature Engineering Algorithm for Creating Air Pollution Health Datasets,” International Journal of Cognitive Computing in Engineering. Elsevier, Nov. 2020, doi: 10.1016/j.ijcce.2020.11.004.
[29] J. Eisfeld, “International Statistical Classification of Diseases and Related Health Problems,” TSQ Transgender Stud. Q., 2014, doi: 10.1215/23289252-2399740.
[30] M. A. Hassan, A. Khalil, S. Kaseb, and M. A. Kassem, “Exploring the potential of tree-based ensemble methods in solar radiation modeling,” Appl. Energy, 2017, doi: 10.1016/j.apenergy.2017.06.104.
[31] T. Hochkirchen, “Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning,” J. R. Stat. Soc. Ser. A (Statistics Soc., 2010, doi: 10.1111/j.1467-985x.2009.00634_10.x.
[32] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[33] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794, doi: 10.1145/2939672.2939785.
[34] R. S. A. Usmani, I. A. T. Hashem, T. R. Pillai, A. Saeed, and A. M. Abdullahi, “Geographic Information System and Big Spatial Data,” Int. J. Enterp. Inf. Syst., vol. 16, no. 4, 2020.
[35] Kaggle, “Predict impact of air quality on mortality rates - Overview.” 2016, [Online]. Available: https://www.kaggle.com/c/predict-impact-of-air-quality-on-death-rates/overview.
[36] Y. Jie, “Air pollution associated with sumatran forest fires and mortality on the malay peninsula,” Polish J. Environ. Stud., vol. 26, no. 1, pp. 163–171, 2017, doi: 10.15244/pjoes/64642.
[37] N. A. Mabahwi, O. L. H. Leh, S. N. A. M. Musthafa, and K. Aiyub, “Air quality-related human health in an urban region. Case study: State of Selangor, Malaysia,” EnvironmentAsia, vol. 11, no. 1, pp. 194–216, 2018, doi: 10.14456/ea.2018.15.
[38] M. A. B. A. Tajudin et al., “Risk of concentrations of major air pollutants on the prevalence of cardiovascular and respiratory diseases in urbanized area of Kuala Lumpur, Malaysia,” Ecotoxicol. Environ. Saf., vol. 171, no. June 2018, pp. 290–300, 2019, doi: 10.1016/j.ecoenv.2018.12.057.
Authors
Abdullahi, A. (2023). Cardiorespiratory Mortality Prediction Based on Air Pollution Using Tree-Based Ensemble Models . International Journal of Advanced Science and Computer Applications, 2(2), 59–68. https://doi.org/10.47679/ijasca.v2i2.30
This work is licensed under a Creative Commons Attribution 4.0 International License.