{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T14:27:03Z","timestamp":1779892023460,"version":"3.53.1"},"reference-count":58,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T00:00:00Z","timestamp":1725408000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R01ES023423"],"award-info":[{"award-number":["R01ES023423"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R21ES019949"],"award-info":[{"award-number":["R21ES019949"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000066","name":"National Institute of Environmental Health Sciences","doi-asserted-by":"publisher","award":["R21ES16523"],"award-info":[{"award-number":["R21ES16523"]}],"id":[{"id":"10.13039\/100000066","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosglobalpublichealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Glob Public Health"],"abstract":"<jats:p>Predicting childhood blood lead levels (BLLs) has had mixed success, and it is unclear if individual- or neighborhood-level variables are most predictive. An ensemble machine learning (ML) approach to identify the most relevant predictors of BLL \u22652\u03bcg\/dL in urban children was implemented. A cross-sectional sample of 603 children (~7 years of age) recruited between 2009\u20132019 from Montevideo, Uruguay participated in the study. 77 individual- and 32 neighborhood-level variables were used to predict BLLs \u22652\u03bcg\/dL. Three ensemble learners were created: one with individual-level predictors (Ensemble-I), one with neighborhood-level predictors (Ensemble-N), and one with both (Ensemble-All). Each ensemble learner comprised four base classifiers with 50% training, 25% validation, and 25% test datasets. Predictive performance of the three ensemble models was compared using area under the curve (AUC) for the receiver operating characteristic (ROC), precision, sensitivity, and specificity on the test dataset. Ensemble-I (AUC: 0.75, precision: 0.56, sensitivity: 0.79, specificity: 0.65) performed similarly to Ensemble-All (AUC: 0.75, precision: 0.63, sensitivity: 0.79, specificity: 0.69). Ensemble-N (AUC: 0.51, precision: 0.0, sensitivity: 0.0, specificity: 0.50) severely underperformed. Year of enrollment was most important in Ensemble-I and Ensemble-All, followed by household water Pb. Three neighborhood-level variables were among the top 10 important predictors in Ensemble-All (density of bus routes, dwellings with stream\/other water source and distance to nearest river). The individual-level only model performed best, although precision was improved when both neighborhood and individual-level variables were included. Future predictive models of lead exposure should consider proximal predictors (i.e., household characteristics).<\/jats:p>","DOI":"10.1371\/journal.pgph.0003607","type":"journal-article","created":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T17:43:59Z","timestamp":1725471839000},"page":"e0003607","update-policy":"https:\/\/doi.org\/10.1371\/journal.pgph.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting blood lead in Uruguayan children: Individual- vs neighborhood-level ensemble learners"],"prefix":"10.1371","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2049-2204","authenticated-orcid":true,"given":"Seth","family":"Frndak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena I.","family":"Queirolo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nelly","family":"Ma\u00f1ay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zia","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0222-1301","authenticated-orcid":true,"given":"Gabriel","family":"Barg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Craig","family":"Colder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarzyna","family":"Kordas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,9,4]]},"reference":[{"issue":"10","key":"pgph.0003607.ref001","doi-asserted-by":"crossref","first-page":"e831","DOI":"10.1016\/S2542-5196(23)00166-3","article-title":"Global health burden and cost of lead exposure in children and adults: a health impact and economic modelling analysis","volume":"7","author":"B Larsen","year":"2023","journal-title":"The Lancet Planetary Health"},{"issue":"4","key":"pgph.0003607.ref002","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1001\/jama.1994.03520040046039","article-title":"The decline in blood lead levels in the United States: the National Health and Nutrition Examination Surveys (NHANES).","volume":"272","author":"JL Pirkle","year":"1994","journal-title":"Jama"},{"issue":"13","key":"pgph.0003607.ref003","first-page":"245","article-title":"Blood lead levels in children aged 1\u20135 years\u2014United States, 1999\u20132010","volume":"62","author":"W Wheeler","year":"2013","journal-title":"MMWR Morbidity and mortality weekly report"},{"issue":"3","key":"pgph.0003607.ref004","doi-asserted-by":"crossref","first-page":"037003","DOI":"10.1289\/EHP7932","article-title":"Blood Lead Levels in US Children Ages 1\u201311 Years, 1976\u20132016","volume":"129","author":"KB Egan","year":"2021","journal-title":"Environmental health perspectives"},{"key":"pgph.0003607.ref005","volume-title":"The toxic truth: children\u2019s exposure to lead pollution undermines a generation of future potential.","author":"N Rees","year":"2020"},{"issue":"16","key":"pgph.0003607.ref006","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1056\/NEJMoa022848","article-title":"Intellectual impairment in children with blood lead concentrations below 10 \u03bcg per deciliter.","volume":"348","author":"RL Canfield","year":"2003","journal-title":"New England journal of medicine."},{"issue":"7","key":"pgph.0003607.ref007","doi-asserted-by":"crossref","first-page":"894","DOI":"10.1289\/ehp.7688","article-title":"Low-level environmental lead exposure and children\u2019s intellectual function: an international pooled analysis","volume":"113","author":"BP Lanphear","year":"2005","journal-title":"Environ Health Perspect"},{"key":"pgph.0003607.ref008","unstructured":"Prevention CfDCa. CDC Updates Blood Lead Reference Value for Children 2021 [cited 2021. Available from: https:\/\/www.cdc.gov\/media\/releases\/2021\/p1028-blood-lead.html."},{"key":"pgph.0003607.ref009","doi-asserted-by":"crossref","first-page":"113862","DOI":"10.1016\/j.ijheh.2021.113862","article-title":"Predicting childhood lead exposure at an aggregated level using machine learning","volume":"238","author":"GP Lobo","year":"2021","journal-title":"International Journal of Hygiene and Environmental Health"},{"issue":"5","key":"pgph.0003607.ref010","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph20054477","article-title":"Predicting Low-Level Childhood Lead Exposure in Metro Atlanta Using Ensemble Machine Learning of High-Resolution Raster Cells.","volume":"20","author":"S Frndak","year":"2023","journal-title":"Int J Environ Res Public Health"},{"key":"pgph.0003607.ref011","article-title":"Identification of high lead exposure locations in Ohio at the census tract scale using a generalizable geospatial hotspot approach","author":"LW Stanek","year":"2024","journal-title":"Journal of Exposure Science & Environmental Epidemiology"},{"issue":"11","key":"pgph.0003607.ref012","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.3390\/ijerph15112351","article-title":"Lead Exposure in Low and Middle-Income Countries: Perspectives and Lessons on Patterns, Injustices, Economics, and Politics.","volume":"15","author":"K Kordas","year":"2018","journal-title":"International journal of environmental research and public health."},{"issue":"15","key":"pgph.0003607.ref013","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1001\/jama.2019.1004","article-title":"Screening for elevated blood lead levels in childhood and pregnancy: updated evidence report and systematic review for the US Preventive Services Task Force","volume":"321","author":"AG Cantor","year":"2019","journal-title":"Jama"},{"issue":"9","key":"pgph.0003607.ref014","doi-asserted-by":"crossref","first-page":"e2012734","DOI":"10.1001\/jamanetworkopen.2020.12734","article-title":"Validation of a Machine Learning Model to Predict Childhood Lead Poisoning","volume":"3","author":"E Potash","year":"2020","journal-title":"JAMA network open"},{"key":"pgph.0003607.ref015","article-title":"Novel Application of Machine Learning Algorithms and Model-Agnostic Methods to Identify Factors Influencing Childhood Blood Lead Levels.","author":"X Liu","year":"2021","journal-title":"Environmental Science & Technology"},{"key":"pgph.0003607.ref016","doi-asserted-by":"crossref","first-page":"109357","DOI":"10.1016\/j.envres.2020.109357","article-title":"A 25-year record of childhood blood lead exposure and its relationship to environmental sources","volume":"186","author":"C Dong","year":"2020","journal-title":"Environmental Research"},{"key":"pgph.0003607.ref017","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.envres.2015.03.001","article-title":"Association of blood lead levels with urinary F2-8\u03b1 isoprostane and 8-hydroxy-2-deoxy-guanosine concentrations in first-grade Uruguayan children","volume":"140","author":"A Roy","year":"2015","journal-title":"Environmental research"},{"key":"pgph.0003607.ref018","doi-asserted-by":"crossref","first-page":"123160","DOI":"10.1016\/j.envpol.2023.123160","article-title":"Secular trends in blood lead concentrations of school-age children in Montevideo, Uruguay from 2009 to 2019","volume":"343","author":"EI Queirolo","year":"2024","journal-title":"Environ Pollut"},{"key":"pgph.0003607.ref019","article-title":"The lead laboratory.","author":"PJ Parsons","year":"1997","journal-title":"Screening Young Children for Lead Poisoning: Guidance for State and Local Health Officials"},{"key":"pgph.0003607.ref020","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1016\/j.chemosphere.2018.07.154","article-title":"Drinking water lead, iron and zinc concentrations as predictors of blood lead levels and urinary lead excretion in school children from Montevideo, Uruguay.","volume":"212","author":"J Ravenscroft","year":"2018","journal-title":"Chemosphere"},{"key":"pgph.0003607.ref021","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.envint.2017.11.013","article-title":"Nutritional status and diet as predictors of children\u2019s lead concentrations in blood and urine","volume":"111","author":"Burganowski Kordas","year":"2018","journal-title":"Environment International"},{"issue":"3","key":"pgph.0003607.ref022","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/S0885-2006(03)00041-3","article-title":"The Child Care HOME Inventories: Assessing the quality of family child care homes.","volume":"18","author":"RH Bradley","year":"2003","journal-title":"Early Childhood Research Quarterly."},{"key":"pgph.0003607.ref023","author":"R Bivand","year":"2017","journal-title":"Package \u2018rgeos\u2019. The Comprehensive R Archive Network (CRAN)."},{"key":"pgph.0003607.ref024","author":"R Bivand","year":"2015","journal-title":"Package \u2018rgdal\u2019. Bindings for the Geospatial Data Abstraction Library"},{"key":"pgph.0003607.ref025","author":"E Pebesma","year":"2012","journal-title":"Package \u2018sp\u2019. The Comprehensive R Archive Network"},{"key":"pgph.0003607.ref026","author":"B Leutner","year":"2017","journal-title":"Package \u2018RStoolbox\u2019. R Foundation for Statistical Computing, Version 01."},{"key":"pgph.0003607.ref027","volume":"734","author":"RJ Hijmans","year":"2015","journal-title":"Package \u2018raster\u2019. R package"},{"key":"pgph.0003607.ref028","unstructured":"Municipality of Montevideo Geographic Services. Sistema de Informaci\u00f3n Geogr\u00e1fica 2020 [Available from: http:\/\/sig.montevideo.gub.uy\/."},{"key":"pgph.0003607.ref029","doi-asserted-by":"crossref","first-page":"113753","DOI":"10.1016\/j.ijheh.2021.113753","article-title":"A mixed methods study examining neighborhood disadvantage and childhood behavior problems in Montevideo, Uruguay","volume":"235","author":"S Frndak","year":"2021","journal-title":"International Journal of Hygiene and Environmental Health"},{"key":"pgph.0003607.ref030","volume-title":"Planet Imagery Product Specifications","author":"S. Marta","year":"2018"},{"key":"pgph.0003607.ref031","author":"DJ Stekhoven","year":"2012","journal-title":"Package \u2018missForest\u2019"},{"key":"pgph.0003607.ref032","first-page":"1","author":"DJ Stekhoven","year":"2011","journal-title":"Using the missForest package. R package."},{"issue":"6","key":"pgph.0003607.ref033","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1002\/sam.11348","article-title":"Random Forest Missing Data Algorithms.","volume":"10","author":"F Tang","year":"2017","journal-title":"Stat Anal Data Min."},{"key":"pgph.0003607.ref034","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An introduction to statistical learning","author":"G James","year":"2013"},{"issue":"1","key":"pgph.0003607.ref035","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests.","volume":"45","author":"L. Breiman","year":"2001","journal-title":"Machine learning."},{"key":"pgph.0003607.ref036","first-page":"1189","article-title":"Greedy function approximation: a gradient boosting machine","author":"JH Friedman","year":"2001","journal-title":"Annals of statistics"},{"issue":"2","key":"pgph.0003607.ref037","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.4249\/scholarpedia.1883","article-title":"K-nearest neighbor.","volume":"4","author":"LE Peterson","year":"2009","journal-title":"Scholarpedia"},{"issue":"7553","key":"pgph.0003607.ref038","first-page":"436","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Deep learning. nature"},{"issue":"1","key":"pgph.0003607.ref039","doi-asserted-by":"crossref","first-page":"24090","DOI":"10.1038\/s41598-021-03198-8","article-title":"Explainable artificial intelligence (XAI) for exploring spatial variability of lung and bronchus cancer (LBC) mortality rates in the contiguous USA.","volume":"11","author":"ZU Ahmed","year":"2021","journal-title":"Scientific Reports."},{"issue":"1","key":"pgph.0003607.ref040","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/widm.1143","article-title":"Generating ensembles of heterogeneous classifiers using stacked generalization. Wiley Interdisciplinary Reviews","volume":"5","author":"MP Sesmero","year":"2015","journal-title":"Data Mining and Knowledge Discovery"},{"key":"pgph.0003607.ref041","first-page":"1","volume-title":"Deep learning with H2O","author":"A Candel","year":"2016"},{"issue":"1","key":"pgph.0003607.ref042","first-page":"3245","volume":"19","author":"P. Biecek","year":"2018","journal-title":"DALEX: explainers for complex predictive models in R. The Journal of Machine Learning Research"},{"key":"pgph.0003607.ref043","unstructured":"CEIC. Uruguay Exchange Rate against USD 2021 [Available from: https:\/\/www.ceicdata.com\/en\/indicator\/uruguay\/exchange-rate-against-usd."},{"key":"pgph.0003607.ref044","doi-asserted-by":"crossref","first-page":"113903","DOI":"10.1016\/j.ijheh.2021.113903","article-title":"A review of studies on blood lead concentrations of traditional Mexican potters","volume":"240","author":"JA Est\u00e9vez-Garc\u00eda","year":"2022","journal-title":"International Journal of Hygiene and Environmental Health"},{"key":"pgph.0003607.ref045","doi-asserted-by":"crossref","first-page":"114944","DOI":"10.1016\/j.envres.2022.114944","article-title":"Using exterior housing conditions to predict elevated pediatric blood lead levels","volume":"218","author":"NJ Wilson","year":"2023","journal-title":"Environmental Research"},{"key":"pgph.0003607.ref046","doi-asserted-by":"crossref","first-page":"112146","DOI":"10.1016\/j.envres.2021.112146","article-title":"A new approach to a legacy concern: Evaluating machine-learned Bayesian networks to predict childhood lead exposure risk from community water systems","volume":"204","author":"R Mulhern","year":"2022","journal-title":"Environmental Research"},{"key":"pgph.0003607.ref047","doi-asserted-by":"crossref","first-page":"113975","DOI":"10.1016\/j.jpeds.2024.113975","article-title":"Firearm-Related Lead Exposure and Child Lead Levels in the United States, 2012\u20132018","volume":"269","author":"C Hoover","year":"2024","journal-title":"The Journal of Pediatrics"},{"issue":"10","key":"pgph.0003607.ref048","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1056\/NEJM198209023071001","article-title":"National estimates of blood lead levels: United States, 1976\u20131980: association with selected demographic and socioeconomic factors.","volume":"307","author":"KR Mahaffey","year":"1982","journal-title":"New England Journal of Medicine."},{"issue":"5","key":"pgph.0003607.ref049","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1007\/s11524-016-0071-8","article-title":"The relationship of neighborhood socioeconomic differences and racial residential segregation to childhood blood lead levels in Metropolitan Detroit.","volume":"93","author":"HA Moody","year":"2016","journal-title":"Journal of Urban Health"},{"issue":"3","key":"pgph.0003607.ref050","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/j.acap.2020.06.009","article-title":"Examining Links Between Diet and Lead Exposure in Young Children: 2009 to 2014 National Health and Nutrition Examination Survey.","volume":"21","author":"G Desai","year":"2021","journal-title":"Acad Pediatr."},{"issue":"3","key":"pgph.0003607.ref051","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1111\/j.1753-4887.2000.tb01842.x","article-title":"Does vitamin C intake protect against lead toxicity?","volume":"58","author":"DK Houston","year":"2000","journal-title":"Nutrition reviews."},{"issue":"4","key":"pgph.0003607.ref052","first-page":"Bc08","article-title":"Effect of Vitamin C Supplementation on Blood Lead Level, Oxidative Stress and Antioxidant Status of Battery Manufacturing Workers of Western Maharashtra, India.","volume":"10","author":"G Ghanwat","year":"2016","journal-title":"J Clin Diagn Res."},{"issue":"3","key":"pgph.0003607.ref053","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.cpem.2017.07.010","article-title":"An update on childhood lead poisoning.","volume":"18","author":"M Hauptman","year":"2017","journal-title":"Clinical pediatric emergency medicine."},{"key":"pgph.0003607.ref054","doi-asserted-by":"crossref","first-page":"123160","DOI":"10.1016\/j.envpol.2023.123160","article-title":"Secular trends in blood lead concentrations of school-age children in Montevideo, Uruguay from 2009 to 2019","volume":"343","author":"EI Queirolo","year":"2024","journal-title":"Environmental Pollution"},{"issue":"1","key":"pgph.0003607.ref055","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1080\/10618600.2014.907095","article-title":"Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation","volume":"24","author":"A Goldstein","year":"2015","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"pgph.0003607.ref056","first-page":"1","article-title":"Visualizing Variable Importance and Variable Interaction Effects in Machine Learning Models","author":"A Inglis","year":"2022","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"1\u20133","key":"pgph.0003607.ref057","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.scitotenv.2007.08.012","article-title":"Nonlinear association between soil lead and blood lead of children in metropolitan New Orleans, Louisiana: 2000\u20132005","volume":"388","author":"HW Mielke","year":"2007","journal-title":"Science of the Total Environment"},{"issue":"5","key":"pgph.0003607.ref058","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph17051552","article-title":"Disparity in Risk Factor Severity for Early Childhood Blood Lead among Predominantly African-American Black Children: The 1999 to 2010 US NHANES.","volume":"17","author":"D Yeter","year":"2020","journal-title":"Int J Environ Res Public Health"}],"container-title":["PLOS Global Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0003607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:46:14Z","timestamp":1729878374000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pgph.0003607"}},"subtitle":[],"editor":[{"given":"Meghnath","family":"Dhimal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,9,4]]},"references-count":58,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9,4]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pgph.0003607","relation":{},"ISSN":["2767-3375"],"issn-type":[{"value":"2767-3375","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,4]]}}}