DOI QR코드

DOI QR Code

A Proposal for a Predictive Model for the Number of Patients with Periodontitis Exposed to Particulate Matter and Atmospheric Factors Using Deep Learning

  • Septika Prismasari (Department of Dental Hygiene, College of Software and Digital Healthcare Convergence, Yonsei University) ;
  • Kyuseok Kim (Department of Environmental Planning, Seoul National University) ;
  • Hye Young Mun (Department of Dental Hygiene, College of Software and Digital Healthcare Convergence, Yonsei University) ;
  • Jung Yun Kang (Department of Dental Hygiene, College of Software and Digital Healthcare Convergence, Yonsei University)
  • 투고 : 2024.01.18
  • 심사 : 2024.03.07
  • 발행 : 2024.03.31

초록

Background: Particulate matter (PM) has been extensively observed due to its negative association with human health. Previous research revealed the possible negative effect of air pollutant exposure on oral health. However, the predictive model between air pollutant exposure and the prevalence of periodontitis has not been observed yet. Therefore, this study aims to propose a predictive model for the number of patients with periodontitis exposed to PM and atmospheric factors in South Korea using deep learning. Methods: This study is a retrospective cohort study utilizing secondary data from the Korean Statistical Information Service and the Health Insurance Review and Assessment database for air pollution and the number of patients with periodontitis, respectively. Data from 2015 to 2022 were collected and consolidated every month, organized by region. Following data matching and management, the deep neural networks (DNN) model was applied, and the mean absolute percentage error (MAPE) value was calculated to ensure the accuracy of the model. Results: As we evaluated the DNN model with MAPE, the multivariate model of air pollution including exposure to PM2.5, PM10, and other atmospheric factors predict approximately 85% of the number of patients with periodontitis. The MAPE value ranged from 12.85 to 17.10 (mean±standard deviation=14.12±1.30), indicating a commendable level of accuracy. Conclusion: In this study, the predictive model for the number of patients with periodontitis is developed based on air pollution, including exposure to PM2.5, PM10, and other atmospheric factors. Additionally, various relevant factors are incorporated into the developed predictive model to elucidate specific causal relationships. It is anticipated that future research will lead to the development of a more accurate model for predicting the number of patients with periodontitis.

키워드

과제정보

This research was supported by the National Research Foundation (NRF-2022R1G1A1004843).

참고문헌

  1. Liu Y, Yan M: Trends in all causes and cause specific mortality attributable to ambient particulate matter pollution in China from 1990 to 2019: a secondary data analysis study. PLoS One 18: e0291262, 2023. https://doi.org/10.1371/journal.pone.0291262
  2. He L, Norris C, Cui X, et al.: Oral cavity response to air pollutant exposure and association with pulmonary inflammation and symptoms in asthmatic children. Environ Res 206: 112275, 2022. https://doi.org/10.1016/j.envres.2021.112275
  3. Rajkumar RP: The relationship between ambient fine particulate matter (PM2.5) pollution and depression: an analysis of data from 185 countries. Atmosphere 14: 597, 2023. https://doi.org/10.3390/atmos14030597
  4. Lee DU, Ji MJ, Kang JY, Kyung SY, Hong JH: Dust particles-induced intracellular Ca2+ signaling and reactive oxygen species in lung fibroblast cell line MRC5. Korean J Physiol Pharmacol 21: 327-334, 2017. https://doi.org/10.4196/kjpp.2017.21.3.327
  5. Kim KH, Kabir E, Kabir S: A review on the human health impact of airborne particulate matter. Environ Int 74: 136-143, 2015. https://doi.org/10.1016/j.envint.2014.10.005
  6. Li Y, Ma Z, Zheng C, Shang Y: Ambient temperature enhanced acute cardiovascular-respiratory mortality effects of PM2.5 in Beijing, China. Int J Biometeorol 59: 1761-1770, 2015. https://doi.org/10.1007/s00484-015-0984-z
  7. Orellano P, Reynoso J, Quaranta N: Short-term exposure to sulphur dioxide (SO2) and all-cause and respiratory mortality: a systematic review and meta-analysis. Environ Int 150: 106434, 2021. https://doi.org/10.1016/j.envint.2021.106434
  8. Chen RJ, Lee YH, Chen TH, et al.: Carbon monoxide-triggered health effects: the important role of the inflammasome and its possible crosstalk with autophagy and exosomes. Arch Toxicol 95: 1141-1159, 2021. https://doi.org/10.1007/s00204-021-02976-7
  9. Meng X, Liu C, Chen R, et al.: Short term associations of ambient nitrogen dioxide with daily total, cardiovascular, and respiratory mortality: multilocation analysis in 398 cities. BMJ 372: n534, 2021. https://doi.org/10.1136/bmj.n534
  10. Holm SM, Balmes JR: Systematic review of ozone effects on human lung function, 2013 through 2020. Chest 161: 190-201, 2022. https://doi.org/10.1016/j.chest.2021.07.2170
  11. Vo TTT, Wu CZ, Lee IT: Potential effects of noxious chemical-containing fine particulate matter on oral health through reactive oxygen species-mediated oxidative stress: promising clues. Biochem Pharmacol 182: 114286, 2020. https://doi.org/10.1016/j.bcp.2020.114286
  12. Marruganti C, Shin HS, Sim SJ, Grandini S, Lafori A, Romandini M: Air pollution as a risk indicator for periodontitis. Biomedicines 11: 443, 2023. https://doi.org/10.3390/biomedicines11020443
  13. Lin HJ, Tsai SCS, Lin FCF, et al.: Prolonged exposure to air pollution increases periodontal disease risk: a nationwide, population-based, cohort study. Atmosphere 12: 1668, 2021. https://doi.org/10.3390/atmos12121668
  14. Xiong K, Yang P, Cui Y, Li J, Li Y, Tang B: Research on the association between periodontitis and COPD. Int J Chron Obstruct Pulmon Dis 18: 1937-1948, 2023. https://doi.org/10.2147/copd.s425172
  15. Slots J: Periodontitis: facts, fallacies and the future. Periodontol 2000 75: 7-23, 2017. https://doi.org/10.1111/prd.12221
  16. Larsson L: Current concepts of epigenetics and its role in periodontitis. Curr Oral Health Rep 4: 286-293, 2017. https://doi.org/10.1007/s40496-017-0156-9
  17. LeCun Y, Bengio Y, Hinton G: Deep learning. Nature 521: 436-444, 2015. https://doi.org/10.1038/nature14539
  18. Kim OJ, Lee SH, Kang SH, Kim SY: Incident cardiovascular disease and particulate matter air pollution in South Korea using a population-based and nationwide cohort of 0.2 million adults. Environ Health 19: 113, 2020. https://doi.org/10.1186/s12940-020-00671-1
  19. Hwang J, Bae H, Choi S, Yi H, Ko B, Kim N: Impact of air pollution on breast cancer incidence and mortality: a nationwide analysis in South Korea. Sci Rep 10: 5392, 2020. https://doi.org/10.1038/s41598-020-62200-x
  20. Oh HR, Ho CH, Koo YS, et al.: Impact of Chinese air pollutants on a record-breaking PMs episode in the Republic of Korea for 11-15 January 2019. Atmos Environ 223: 117262, 2020. https://doi.org/10.1016/j.atmosenv.2020.117262
  21. Min KD, Yi SJ, Kim HC, et al.: Association between exposure to traffic-related air pollution and pediatric allergic diseases based on modeled air pollution concentrations and traffic measures in Seoul, Korea: a comparative analysis. Environ Health 19: 6, 2020. https://doi.org/10.1186/s12940-020-0563-6
  22. Lewis CD: Industrial and business forecasting methods: a practical guide to exponential smoothing and curve fitting. Butterworth Scientific, London, 1982.
  23. Yang TH, Masumi S, Weng SP, Chen HW, Chuang HC, Chuang KJ: Personal exposure to particulate matter and inflammation among patients with periodontal disease. Sci Total Environ 502: 585-589, 2015. https://doi.org/10.1016/j.scitotenv.2014.09.081
  24. Huang K, Feng LF, Liu ZY, et al.: The modification of meteorological factors on the relationship between air pollution and periodontal diseases: an exploration based on different interaction strategies. Environ Geochem Health 45: 8187-8202, 2023. https://doi.org/10.1007/s10653-023-01705-6
  25. Seo JH, Kim JS, Yang J, et al.: Changes in air quality during the COVID-19 pandemic and associated health benefits in Korea. Appl Sci 10: 8720, 2020a. https://doi.org/10.3390/app10238720
  26. Seo JH, Jeon HW, Sung UJ, Sohn JR: Impact of the COVID-19 outbreak on air quality in Korea. Atmosphere 11: 1137, 2020b. https://doi.org/10.3390/atmos11101137
  27. Kyung SY, Jeong SH: Particulate-matter related respiratory diseases. Tuberc Respir Dis (Seoul) 83: 116-121, 2020. https://doi.org/10.4046/trd.2019.0025
  28. D'Ercole S, Parisi P, D'Arcangelo S, et al.: Correlation between use of different type protective facemasks and the oral ecosystem. BMC Public Health 23: 1992, 2023. https://doi.org/10.1186/s12889-023-16936-6
  29. Hung M, Voss MW, Rosales MN, et al.: Application of machine learning for diagnostic prediction of root caries. Gerodontology 36: 395-404, 2019. https://doi.org/10.1111/ger.12432
  30. Kang IA, Ngnamsie Njimbouom S, Lee KO, Kim JD: DCP: prediction of dental caries using machine learning in personalized medicine. Appl Sci 12: 3043, 2022. https://doi.org/10.3390/app12063043