Cargando…

Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020

OBJECTIVE: Heavy metals are present in many environmental pollutants, and have cumulative effects on the human body through water or food, which can lead to several diseases, including osteoarthritis (OA). In this research, we aimed to explore the association between heavy metals and OA. METHODS: We...

Descripción completa

Detalles Bibliográficos
Autores principales: Xia, Fang, Li, Qingwen, Luo, Xin, Wu, Jinyi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9376265/
https://www.ncbi.nlm.nih.gov/pubmed/35979456
http://dx.doi.org/10.3389/fpubh.2022.906774
_version_ 1784768127719964672
author Xia, Fang
Li, Qingwen
Luo, Xin
Wu, Jinyi
author_facet Xia, Fang
Li, Qingwen
Luo, Xin
Wu, Jinyi
author_sort Xia, Fang
collection PubMed
description OBJECTIVE: Heavy metals are present in many environmental pollutants, and have cumulative effects on the human body through water or food, which can lead to several diseases, including osteoarthritis (OA). In this research, we aimed to explore the association between heavy metals and OA. METHODS: We extracted 18 variables including age, gender, race, education level, marital status, smoking status, body mass index (BMI), physical activity, diabetes mellitus, hypertension, poverty level index (PLI), Lead (Pb), cadmium (Cd), mercury (Hg), selenium (Se), manganese (Mn), and OA status from National Health and Nutrition Examination Survey (NHANES) 2011-2020 datasets. RESULTS: In the baseline data, the t test and Chi-square test were conducted. For heavy metals, quartile description and limit of detection (LOD) were adopted. To analyze the association between heavy metals and OA among elderly subjects, multivariable logistic regression was conducted and subgroup logistic by gender was also carried out. Furthermore, to make predictions based on heavy metals for OA, we compared eight machine learning algorithms, and XGBoost (AUC of 0.8, accuracy value of 0.773, and kappa value of 0.358) was the best machine learning model for prediction. For interactive use, a shiny application was made (https://alanwu.shinyapps.io/NHANES-OA/). CONCLUSION: The overall and gender subgroup logistic regressions all showed that Pb and Cd promoted the prevalence of OA while Mn could be a protective factor of OA prevalence among the elderly population of the United States. Furthermore, XGBoost model was trained for OA prediction.
format Online
Article
Text
id pubmed-9376265
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-93762652022-08-16 Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020 Xia, Fang Li, Qingwen Luo, Xin Wu, Jinyi Front Public Health Public Health OBJECTIVE: Heavy metals are present in many environmental pollutants, and have cumulative effects on the human body through water or food, which can lead to several diseases, including osteoarthritis (OA). In this research, we aimed to explore the association between heavy metals and OA. METHODS: We extracted 18 variables including age, gender, race, education level, marital status, smoking status, body mass index (BMI), physical activity, diabetes mellitus, hypertension, poverty level index (PLI), Lead (Pb), cadmium (Cd), mercury (Hg), selenium (Se), manganese (Mn), and OA status from National Health and Nutrition Examination Survey (NHANES) 2011-2020 datasets. RESULTS: In the baseline data, the t test and Chi-square test were conducted. For heavy metals, quartile description and limit of detection (LOD) were adopted. To analyze the association between heavy metals and OA among elderly subjects, multivariable logistic regression was conducted and subgroup logistic by gender was also carried out. Furthermore, to make predictions based on heavy metals for OA, we compared eight machine learning algorithms, and XGBoost (AUC of 0.8, accuracy value of 0.773, and kappa value of 0.358) was the best machine learning model for prediction. For interactive use, a shiny application was made (https://alanwu.shinyapps.io/NHANES-OA/). CONCLUSION: The overall and gender subgroup logistic regressions all showed that Pb and Cd promoted the prevalence of OA while Mn could be a protective factor of OA prevalence among the elderly population of the United States. Furthermore, XGBoost model was trained for OA prediction. Frontiers Media S.A. 2022-08-01 /pmc/articles/PMC9376265/ /pubmed/35979456 http://dx.doi.org/10.3389/fpubh.2022.906774 Text en Copyright © 2022 Xia, Li, Luo and Wu. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Public Health
Xia, Fang
Li, Qingwen
Luo, Xin
Wu, Jinyi
Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title_full Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title_fullStr Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title_full_unstemmed Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title_short Identification for heavy metals exposure on osteoarthritis among aging people and Machine learning for prediction: A study based on NHANES 2011-2020
title_sort identification for heavy metals exposure on osteoarthritis among aging people and machine learning for prediction: a study based on nhanes 2011-2020
topic Public Health
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9376265/
https://www.ncbi.nlm.nih.gov/pubmed/35979456
http://dx.doi.org/10.3389/fpubh.2022.906774
work_keys_str_mv AT xiafang identificationforheavymetalsexposureonosteoarthritisamongagingpeopleandmachinelearningforpredictionastudybasedonnhanes20112020
AT liqingwen identificationforheavymetalsexposureonosteoarthritisamongagingpeopleandmachinelearningforpredictionastudybasedonnhanes20112020
AT luoxin identificationforheavymetalsexposureonosteoarthritisamongagingpeopleandmachinelearningforpredictionastudybasedonnhanes20112020
AT wujinyi identificationforheavymetalsexposureonosteoarthritisamongagingpeopleandmachinelearningforpredictionastudybasedonnhanes20112020