Loading…
The relationship between heavy metals and metabolic syndrome using machine learning
Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method. The data used in this stud...
Saved in:
Published in: | Frontiers in public health 2024-04, Vol.12, p.1378041 |
---|---|
Main Authors: | , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | cdi_FETCH-LOGICAL-c420t-d0b38c737aaeca6d30d9b56d479b1a432bd4322710b4b14507eca899557bfd423 |
container_end_page | |
container_issue | |
container_start_page | 1378041 |
container_title | Frontiers in public health |
container_volume | 12 |
creator | Yao, Jun Du, Zhilin Yang, Fuyue Duan, Ran Feng, Tong |
description | Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.
The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.
11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.
Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model. |
doi_str_mv | 10.3389/fpubh.2024.1378041 |
format | article |
fullrecord | <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_fd1760560664408b8e1431d313acd063</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_fd1760560664408b8e1431d313acd063</doaj_id><sourcerecordid>3049721464</sourcerecordid><originalsourceid>FETCH-LOGICAL-c420t-d0b38c737aaeca6d30d9b56d479b1a432bd4322710b4b14507eca899557bfd423</originalsourceid><addsrcrecordid>eNpVkU1r3DAQhk1paUKaP9BD8bGX3Y40smSfSgn9CARySHoW-hivFWxpK3lT9t_X2d2G5CINM-_7SMxbVR8ZrBHb7ku_3dlhzYGLNUPVgmBvqnPOO7nijWzevqjPqstSHgCAAQrg7H11hq1sJSCeV3f3A9WZRjOHFMsQtrWl-S9RrAcyj_t6otmMpTbRH0qbxuDqso8-p4nqXQlxU0_GDSFSPZLJcWl8qN71i4kuT_dF9fvH9_urX6ub25_XV99uVk5wmFceLLZOoTKGnJEewXe2kV6ozjIjkFu_HFwxsMIy0YBaZG3XNY2yvRccL6rrI9cn86C3OUwm73UyQR8aKW-0yXNwI-neMyWhkSClENDalphA5pGhcR4kLqyvR9ay1om8ozhnM76Cvp7EMOhNetSMQaOQdwvh84mQ058dlVlPoTgaRxMp7YpGEJ3iTEixSPlR6nIqJVP__A4D_ZSuPqSrn9LVp3QX06eXP3y2_M8S_wHWkqHN</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3049721464</pqid></control><display><type>article</type><title>The relationship between heavy metals and metabolic syndrome using machine learning</title><source>PubMed Central</source><creator>Yao, Jun ; Du, Zhilin ; Yang, Fuyue ; Duan, Ran ; Feng, Tong</creator><creatorcontrib>Yao, Jun ; Du, Zhilin ; Yang, Fuyue ; Duan, Ran ; Feng, Tong</creatorcontrib><description>Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.
The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.
11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.
Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.</description><identifier>ISSN: 2296-2565</identifier><identifier>EISSN: 2296-2565</identifier><identifier>DOI: 10.3389/fpubh.2024.1378041</identifier><identifier>PMID: 38686033</identifier><language>eng</language><publisher>Switzerland: Frontiers Media S.A</publisher><subject>Adult ; Aged ; Body Mass Index ; Environmental Exposure - adverse effects ; Female ; heavy metals ; Humans ; Machine Learning ; Male ; metabolic syndrome ; Metabolic Syndrome - chemically induced ; Metabolic Syndrome - epidemiology ; Metals, Heavy ; Middle Aged ; NHANES (National Health and Nutrition Examination Survey) ; Nutrition Surveys ; Public Health ; Risk Factors ; SHapley additive exPlanations (SHAP)</subject><ispartof>Frontiers in public health, 2024-04, Vol.12, p.1378041</ispartof><rights>Copyright © 2024 Yao, Du, Yang, Duan and Feng.</rights><rights>Copyright © 2024 Yao, Du, Yang, Duan and Feng. 2024 Yao, Du, Yang, Duan and Feng</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c420t-d0b38c737aaeca6d30d9b56d479b1a432bd4322710b4b14507eca899557bfd423</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11057329/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC11057329/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,27924,27925,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38686033$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yao, Jun</creatorcontrib><creatorcontrib>Du, Zhilin</creatorcontrib><creatorcontrib>Yang, Fuyue</creatorcontrib><creatorcontrib>Duan, Ran</creatorcontrib><creatorcontrib>Feng, Tong</creatorcontrib><title>The relationship between heavy metals and metabolic syndrome using machine learning</title><title>Frontiers in public health</title><addtitle>Front Public Health</addtitle><description>Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.
The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.
11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.
Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.</description><subject>Adult</subject><subject>Aged</subject><subject>Body Mass Index</subject><subject>Environmental Exposure - adverse effects</subject><subject>Female</subject><subject>heavy metals</subject><subject>Humans</subject><subject>Machine Learning</subject><subject>Male</subject><subject>metabolic syndrome</subject><subject>Metabolic Syndrome - chemically induced</subject><subject>Metabolic Syndrome - epidemiology</subject><subject>Metals, Heavy</subject><subject>Middle Aged</subject><subject>NHANES (National Health and Nutrition Examination Survey)</subject><subject>Nutrition Surveys</subject><subject>Public Health</subject><subject>Risk Factors</subject><subject>SHapley additive exPlanations (SHAP)</subject><issn>2296-2565</issn><issn>2296-2565</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpVkU1r3DAQhk1paUKaP9BD8bGX3Y40smSfSgn9CARySHoW-hivFWxpK3lT9t_X2d2G5CINM-_7SMxbVR8ZrBHb7ku_3dlhzYGLNUPVgmBvqnPOO7nijWzevqjPqstSHgCAAQrg7H11hq1sJSCeV3f3A9WZRjOHFMsQtrWl-S9RrAcyj_t6otmMpTbRH0qbxuDqso8-p4nqXQlxU0_GDSFSPZLJcWl8qN71i4kuT_dF9fvH9_urX6ub25_XV99uVk5wmFceLLZOoTKGnJEewXe2kV6ozjIjkFu_HFwxsMIy0YBaZG3XNY2yvRccL6rrI9cn86C3OUwm73UyQR8aKW-0yXNwI-neMyWhkSClENDalphA5pGhcR4kLqyvR9ay1om8ozhnM76Cvp7EMOhNetSMQaOQdwvh84mQ058dlVlPoTgaRxMp7YpGEJ3iTEixSPlR6nIqJVP__A4D_ZSuPqSrn9LVp3QX06eXP3y2_M8S_wHWkqHN</recordid><startdate>20240415</startdate><enddate>20240415</enddate><creator>Yao, Jun</creator><creator>Du, Zhilin</creator><creator>Yang, Fuyue</creator><creator>Duan, Ran</creator><creator>Feng, Tong</creator><general>Frontiers Media S.A</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope></search><sort><creationdate>20240415</creationdate><title>The relationship between heavy metals and metabolic syndrome using machine learning</title><author>Yao, Jun ; Du, Zhilin ; Yang, Fuyue ; Duan, Ran ; Feng, Tong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c420t-d0b38c737aaeca6d30d9b56d479b1a432bd4322710b4b14507eca899557bfd423</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Body Mass Index</topic><topic>Environmental Exposure - adverse effects</topic><topic>Female</topic><topic>heavy metals</topic><topic>Humans</topic><topic>Machine Learning</topic><topic>Male</topic><topic>metabolic syndrome</topic><topic>Metabolic Syndrome - chemically induced</topic><topic>Metabolic Syndrome - epidemiology</topic><topic>Metals, Heavy</topic><topic>Middle Aged</topic><topic>NHANES (National Health and Nutrition Examination Survey)</topic><topic>Nutrition Surveys</topic><topic>Public Health</topic><topic>Risk Factors</topic><topic>SHapley additive exPlanations (SHAP)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yao, Jun</creatorcontrib><creatorcontrib>Du, Zhilin</creatorcontrib><creatorcontrib>Yang, Fuyue</creatorcontrib><creatorcontrib>Duan, Ran</creatorcontrib><creatorcontrib>Feng, Tong</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Frontiers in public health</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yao, Jun</au><au>Du, Zhilin</au><au>Yang, Fuyue</au><au>Duan, Ran</au><au>Feng, Tong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>The relationship between heavy metals and metabolic syndrome using machine learning</atitle><jtitle>Frontiers in public health</jtitle><addtitle>Front Public Health</addtitle><date>2024-04-15</date><risdate>2024</risdate><volume>12</volume><spage>1378041</spage><pages>1378041-</pages><issn>2296-2565</issn><eissn>2296-2565</eissn><abstract>Exposure to high levels of heavy metals has been widely recognized as an important risk factor for metabolic syndrome (MetS). The main purpose of this study is to assess the associations between the level of heavy metal exposure and Mets using machine learning (ML) method.
The data used in this study are from the national health and nutrition examination survey 2003-2018. According to the demographic information and heavy metal exposure level of participants, a total of 22 variables were included. Lasso was used to screen out the key variables, and 9 commonly used ML models were selected to establish the associations with the 5-fold cross validation method. Finally, we choose the SHapley Additive exPlanations (SHAP) method to explain the prediction results of Adaboost model.
11,667 eligible individuals were randomly divided into two groups to train and verify the prediction model. Through lasso, characteristic variables were selected from 24 variables as predictors. The AUC (area under curve) of the models selected in this study were all greater than 0.7, and AdaBoost was the best model. The AUC value of AdaBoost was 0.807, the accuracy was 0.720, and the sensitivity was 0.792. It is noteworthy that higher levels of cadmium, body mass index, cesium, being female, and increasing age were associated with an increased probability of MetS. Conversely, lower levels of cobalt and molybdenum were linked to a decrease in the estimated probability of MetS.
Our study highlights the AdaBoost model proved to be highly effective, precise, and resilient in detecting a correlation between exposure to heavy metals and MetS. Through the use of interpretable methods, we identified cadmium, molybdenum, cobalt, cesium, uranium, and barium as prominent contributors within the predictive model.</abstract><cop>Switzerland</cop><pub>Frontiers Media S.A</pub><pmid>38686033</pmid><doi>10.3389/fpubh.2024.1378041</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2296-2565 |
ispartof | Frontiers in public health, 2024-04, Vol.12, p.1378041 |
issn | 2296-2565 2296-2565 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_fd1760560664408b8e1431d313acd063 |
source | PubMed Central |
subjects | Adult Aged Body Mass Index Environmental Exposure - adverse effects Female heavy metals Humans Machine Learning Male metabolic syndrome Metabolic Syndrome - chemically induced Metabolic Syndrome - epidemiology Metals, Heavy Middle Aged NHANES (National Health and Nutrition Examination Survey) Nutrition Surveys Public Health Risk Factors SHapley additive exPlanations (SHAP) |
title | The relationship between heavy metals and metabolic syndrome using machine learning |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A11%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=The%20relationship%20between%20heavy%20metals%20and%20metabolic%20syndrome%20using%20machine%20learning&rft.jtitle=Frontiers%20in%20public%20health&rft.au=Yao,%20Jun&rft.date=2024-04-15&rft.volume=12&rft.spage=1378041&rft.pages=1378041-&rft.issn=2296-2565&rft.eissn=2296-2565&rft_id=info:doi/10.3389/fpubh.2024.1378041&rft_dat=%3Cproquest_doaj_%3E3049721464%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c420t-d0b38c737aaeca6d30d9b56d479b1a432bd4322710b4b14507eca899557bfd423%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3049721464&rft_id=info:pmid/38686033&rfr_iscdi=true |