Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China

ObjectivesThis study investigated association between long-term PM2.5 exposure and lung cancer incidence, focusing on Jiangsu Province, China. We aimed to explore the effects of historical PM2.5 with time lags and build a prediction model using machine learning methods.Study designAn ecological epid...

Full description

Saved in:
Bibliographic Details
Main Authors: Feiran Wei, Shijun Yang, Huiying Wang, Meng Zhao, Jinyi Zhou, Xiaobing Shen, Renqiang Han, Gaoqiang Fei
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1536509/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850184148759609344
author Feiran Wei
Shijun Yang
Huiying Wang
Meng Zhao
Meng Zhao
Jinyi Zhou
Xiaobing Shen
Xiaobing Shen
Renqiang Han
Renqiang Han
Gaoqiang Fei
author_facet Feiran Wei
Shijun Yang
Huiying Wang
Meng Zhao
Meng Zhao
Jinyi Zhou
Xiaobing Shen
Xiaobing Shen
Renqiang Han
Renqiang Han
Gaoqiang Fei
author_sort Feiran Wei
collection DOAJ
description ObjectivesThis study investigated association between long-term PM2.5 exposure and lung cancer incidence, focusing on Jiangsu Province, China. We aimed to explore the effects of historical PM2.5 with time lags and build a prediction model using machine learning methods.Study designAn ecological epidemiology study.MethodsLung cancer incidence data from Jiangsu Province (2014–2018) were combined with annual PM2.5 concentration data from satellite sources for the previous 10 years (lag 0 to lag 9). Correlation and grey correlation analyses were performed to evaluate the lagged relationship between PM2.5 exposure and lung cancer incidence. To address the multicollinearity problem in the data, ridge regression, support vector regression, and back propagation artificial neural network were employed. The combined prediction model was constructed using the optimal weighting method.ResultsThe incidence of lung cancer was significantly correlated with PM2.5 concentration at different historical time points, with the strongest correlation at lag 9. The combined prediction model that integrates multiple prediction methods showed higher accuracy and reliability in predicting lung cancer incidence than a single model.ConclusionLong-term exposure to PM2.5, especially exposure with a long lag time, is closely related to lung cancer incidence. The integrated machine learning prediction model can be used as a reliable tool to assess the health risks of air pollution.
format Article
id doaj-art-a1c5b3f32e884bbfb8792e2c95006991
institution OA Journals
issn 2296-2565
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-a1c5b3f32e884bbfb8792e2c950069912025-08-20T02:17:08ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-05-011310.3389/fpubh.2025.15365091536509Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in ChinaFeiran Wei0Shijun Yang1Huiying Wang2Meng Zhao3Meng Zhao4Jinyi Zhou5Xiaobing Shen6Xiaobing Shen7Renqiang Han8Renqiang Han9Gaoqiang Fei10Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, ChinaGuangxi Meteorological Observatory, Nanjing, ChinaLianyungang Meteorological Bureau, Lianyungang, ChinaKey Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, ChinaDepartment of Epidemiology and Biostatistics, School of Public Health, Southeast University, Nanjing, ChinaJiangsu Provincial Center for Disease Control and Prevention (Jiangsu Provincial Academy of Preventive Medicine), Nanjing, ChinaKey Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, ChinaDepartment of Epidemiology and Biostatistics, School of Public Health, Southeast University, Nanjing, ChinaJiangsu Provincial Center for Disease Control and Prevention (Jiangsu Provincial Academy of Preventive Medicine), Nanjing, ChinaDepartment of Public Health, Jiangsu Cancer Hospital, The Affiliated Cancer Hospital of Nanjing Medical University, Jiangsu Institute of Cancer Research, Nanjing, ChinaDepartment of Public Health, Jiangsu Cancer Hospital, The Affiliated Cancer Hospital of Nanjing Medical University, Jiangsu Institute of Cancer Research, Nanjing, ChinaObjectivesThis study investigated association between long-term PM2.5 exposure and lung cancer incidence, focusing on Jiangsu Province, China. We aimed to explore the effects of historical PM2.5 with time lags and build a prediction model using machine learning methods.Study designAn ecological epidemiology study.MethodsLung cancer incidence data from Jiangsu Province (2014–2018) were combined with annual PM2.5 concentration data from satellite sources for the previous 10 years (lag 0 to lag 9). Correlation and grey correlation analyses were performed to evaluate the lagged relationship between PM2.5 exposure and lung cancer incidence. To address the multicollinearity problem in the data, ridge regression, support vector regression, and back propagation artificial neural network were employed. The combined prediction model was constructed using the optimal weighting method.ResultsThe incidence of lung cancer was significantly correlated with PM2.5 concentration at different historical time points, with the strongest correlation at lag 9. The combined prediction model that integrates multiple prediction methods showed higher accuracy and reliability in predicting lung cancer incidence than a single model.ConclusionLong-term exposure to PM2.5, especially exposure with a long lag time, is closely related to lung cancer incidence. The integrated machine learning prediction model can be used as a reliable tool to assess the health risks of air pollution.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1536509/fullPM2.5lung cancerlong-term exposuremachine learningprediction modelpublic health
spellingShingle Feiran Wei
Shijun Yang
Huiying Wang
Meng Zhao
Meng Zhao
Jinyi Zhou
Xiaobing Shen
Xiaobing Shen
Renqiang Han
Renqiang Han
Gaoqiang Fei
Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
Frontiers in Public Health
PM2.5
lung cancer
long-term exposure
machine learning
prediction model
public health
title Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
title_full Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
title_fullStr Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
title_full_unstemmed Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
title_short Epidemiological association and machine learning-based prediction of lung cancer risk linked to long-term lagged satellite-derived PM2.5 in China
title_sort epidemiological association and machine learning based prediction of lung cancer risk linked to long term lagged satellite derived pm2 5 in china
topic PM2.5
lung cancer
long-term exposure
machine learning
prediction model
public health
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1536509/full
work_keys_str_mv AT feiranwei epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT shijunyang epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT huiyingwang epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT mengzhao epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT mengzhao epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT jinyizhou epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT xiaobingshen epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT xiaobingshen epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT renqianghan epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT renqianghan epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina
AT gaoqiangfei epidemiologicalassociationandmachinelearningbasedpredictionoflungcancerrisklinkedtolongtermlaggedsatellitederivedpm25inchina