Predicting blood lead in Uruguayan children: Individual- vs neighborhood-level ensemble learners
Open Access
- 4 September 2024
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Global Public Health
- Vol. 4 (9) , e0003607
Abstract
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 ≥2μg/dL in urban children was implemented. A cross-sectional sample of 603 children (~7 years of age) recruited between 2009–2019 from Montevideo, Uruguay participated in the study. 77 individual- and 32 neighborhood-level variables were used to predict BLLs ≥2μg/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).Keywords
Funding Information
- National Institute of Environmental Health Sciences (R01ES023423)
- National Institute of Environmental Health Sciences (R21ES019949)
- National Institute of Environmental Health Sciences (R21ES16523)
This publication has 40 references indexed in Scilit:
- Examining Links Between Diet and Lead Exposure in Young Children: 2009 to 2014 National Health and Nutrition Examination SurveyAcademic Pediatrics, 2021
- Validation of a Machine Learning Model to Predict Childhood Lead PoisoningJAMA Network Open, 2020
- Screening for Elevated Blood Lead Levels in Childhood and PregnancyJAMA, 2019
- Drinking water lead, iron and zinc concentrations as predictors of blood lead levels and urinary lead excretion in school children from Montevideo, UruguayChemosphere, 2018
- An Update on Childhood Lead PoisoningClinical Pediatric Emergency Medicine, 2017
- Random forest missing data algorithmsStatistical Analysis and Data Mining: An ASA Data Science Journal, 2017
- The Relationship of Neighborhood Socioeconomic Differences and Racial Residential Segregation to Childhood Blood Lead Levels in Metropolitan DetroitJournal of Urban Health, 2016
- Generating ensembles of heterogeneous classifiers using Stacked GeneralizationWIREs Data Mining and Knowledge Discovery, 2015
- An Introduction to Statistical Learning2013
- The Decline in Blood Lead Levels in the United StatesJAMA, 1994