Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Mar 2;20(5):4477.
doi: 10.3390/ijerph20054477.

Predicting Low-Level Childhood Lead Exposure in Metro Atlanta Using Ensemble Machine Learning of High-Resolution Raster Cells

Seth Frndak  1 , Fengxia Yan  2 , Mike Edelson  3 , Lilly Cheng Immergluck  4 , Katarzyna Kordas  1 , Muhammed Y Idris  5 , Carmen M Dickinson-Copeland  4
Affiliations

Predicting Low-Level Childhood Lead Exposure in Metro Atlanta Using Ensemble Machine Learning of High-Resolution Raster Cells

Seth Frndak et al. Int J Environ Res Public Health. .

Abstract

Low-level lead exposure in children is a major public health issue. Higher-resolution spatial targeting would significantly improve county and state-wide policies and programs for lead exposure prevention that generally intervene across large geographic areas. We use stack-ensemble machine learning, including an elastic net generalized linear model, gradient-boosted machine, and deep neural network, to predict the number of children with venous blood lead levels (BLLs) ≥2 to <5 µg/dL and ≥5 µg/dL in ~1 km2 raster cells in the metro Atlanta region using a sample of 92,792 children ≤5 years old screened between 2010 and 2018. Permutation-based predictor importance and partial dependence plots were used for interpretation. Maps of predicted vs. observed values were generated to compare model performance. According to the EPA Toxic Release Inventory for air-based toxic release facility density, the percentage of the population below the poverty threshold, crime, and road network density was positively associated with the number of children with low-level lead exposure, whereas the percentage of the white population was inversely associated. While predictions generally matched observed values, cells with high counts of lead exposure were underestimated. High-resolution geographic prediction of lead-exposed children using ensemble machine learning is a promising approach to enhance lead prevention efforts.

Keywords: geographic prediction; lead exposure; machine learning; primary prevention.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.

Figures

Figure 1
Figure 1
Data processing and model building flow for the ensemble ML.
Figure 2
Figure 2
Predictor importance for ensemble learners predicting the number of children in a raster cell with BLLs ≥2–<5 µg/dL.
Figure 3
Figure 3
Partial dependence plots for top four ensemble predictors of the number of children in a raster cell with BLLs ≥2–<5 µg/dL.
Figure 4
Figure 4
Raster grid of predicted and observed number of BLLs≥2–<5 µg/dL in the Atlanta metro area.
Figure 5
Figure 5
Predictor importance for ensemble learners predicting the number of children in a raster cell with BLLs ≥ 5 µg/dL.
Figure 6
Figure 6
Partial dependence plots for top four ensemble predictors of the number of children in a raster cell with BLLs ≥ 5 µg/dL.
Figure 7
Figure 7
Raster grid of predicted and observed number of BLLs ≥ 5 µg/dL in the Atlanta metro area.
See this image and copyright information in PMC

References

    1. Nigg J.T., Knottnerus G.M., Martel M.M., Nikolas M., Cavanagh K., Karmaus W., Rappley M.D. Low Blood Lead Levels Associated with Clinically Diagnosed Attention-Deficit/Hyperactivity Disorder and Mediated by Weak Cognitive Control. Biol. Psychiatry. 2008;63:325–331. doi: 10.1016/j.biopsych.2007.07.013. - DOI - PMC - PubMed
    1. Lanphear B.P., Dietrich K., Auinger P., Cox C. Cognitive Deficits Associated with Blood Lead Concentrations <10 Microg/DL in US Children and Adolescents. Public Health Rep. 2000;115:521–529. doi: 10.1093/phr/115.6.521. - DOI - PMC - PubMed
    1. Surkan P.J., Zhang A., Trachtenberg F., Daniel D.B., McKinlay S., Bellinger D.C. Neuropsychological Function in Children with Blood Lead Levels <10 Microg/DL. Neurotoxicology. 2007;28:1170–1177. doi: 10.1016/j.neuro.2007.07.007. - DOI - PMC - PubMed
    1. Vorvolakos T., Arseniou S., Samakouri M. There is no safe threshold for lead exposure: A literature review. Psychiatriki. 2016;27:204–214. doi: 10.22365/jpsych.2016.273.204. - DOI - PubMed
    1. Gilbert S.G., Weiss B. A rationale for lowering the blood lead action level from 10 to 2 μg/dL. Neurotoxicology. 2006;27:693–701. doi: 10.1016/j.neuro.2006.06.008. - DOI - PMC - PubMed

Publication types