Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

Potash, Eric; Ghani, Rayid; Walsh, Joe; Jorgensen, Emile; Lohff, Cortland; Prachand, Nik; Mansour, Raed

doi:10.1001/jamanetworkopen.2020.12734

Cited by 28 publications

(22 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We merge blood lead surveillance data, public school records, and criminal arrest records at the individual level to evaluate the long-term impact of elevated BLL interventions on school performance and adolescent behavior in Charlotte, North Carolina. 2 Similar to that of many other state and local health departments, the public health response in North Carolina is based on CDC guidelines. Two consecutive test results over an alert threshold of ten micrograms of lead per deciliter of blood ( μ g/dL) triggers an elevated BLL intervention.…”

mentioning

confidence: 99%

“…Early life lead exposure also impacts externalizing behaviors such as attention, impulsivity, and hyperactivity in young children (Froehlich et al 2009;Chen et al 2007); increased delinquent and antisocial activity and higher rates of arrest (Aizer and Currie 2017;Wright et al 2008;Fergusson, Boden, and Horwood 2008;Needleman et al 2002;Dietrich et al 2001;Needleman et al 1996). 2 Charlotte contains the eighteenth largest school district and is representative of other large urban areas in the United States. 3 We present results from several different regression discontinuity designs and provide plots of outcomes by BLL values in the online Appendix.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Life after Lead: Effects of Early Interventions for Children Exposed to Lead

Billings

Schnepel

2018

American Economic Journal: Applied Economics

View full text Add to dashboard Cite

Lead pollution is consistently linked to cognitive and behavioral impairments, yet little is known about the benefits of public health interventions for children exposed to lead. This paper estimates the long-term impacts of early life interventions (e.g., lead remediation, nutritional assessment, medical evaluation, developmental surveillance, and public assistance referrals) recommended for lead-poisoned children. Using linked administrative data from Charlotte, NC, we compare outcomes for children who are similar across observable characteristics but differ in eligibility for intervention due to blood lead test results. We find that the negative outcomes previously associated with early life exposure can largely be reversed by intervention. (JEL I12, I18, I21, J13, J24, Q51)

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Life after Lead: Effects of Early Interventions for Children Exposed to Lead

Billings

Schnepel

2018

American Economic Journal: Applied Economics

View full text Add to dashboard Cite

show abstract

“…However, choosing the most optimal ML model can be challenging and thus, the development of methods for identifying the best performing model has become an important area of research. Although ML modeling has demonstrable predictive capability and is increasingly popular in epidemiology and public health, − it is still considered a black box due to the complex inner structure of the model . Recent advances in “interpretable machine learning” have helped to unveil these black boxes increasing its attractiveness to decision makers.…”

Section: Introductionmentioning

confidence: 99%

Novel Application of Machine Learning Algorithms and Model-Agnostic Methods to Identify Factors Influencing Childhood Blood Lead Levels

Liu

Taylor

Aelion

et al. 2021

Environ. Sci. Technol.

View full text Add to dashboard Cite

Blood lead (Pb) poisoning remains a global concern, particularly for children in their early developmental years. Broken Hill is Australia’s oldest operating silver–zinc–lead mine. In this study, we utilized recent advances in machine learning to assess multiple algorithms and identify the most optimal model for predicting childhood blood Pb levels (BLL) using Broken Hill children’s (<5 years of age) data (n = 23,749) from 1991 to 2015, combined with demographic, socio-economic, and environmental influencing factors. We applied model-agnostic methods to interpret the most optimal model, investigating different environmental and human factors influencing childhood BLL. Algorithm assessment showed that stacked ensemble, a method for automatically and optimally combining multiple prediction algorithms, enhanced predictive performance by 1.1% with respect to mean absolute error (p < 0.01) and 2.6% for root-mean-squared error (p < 0.01) compared to the best performing constituent algorithm (random forest). By interpreting the model, the following information was acquired: children had higher BLL if they resided within 1.0 km to the central mine area or 1.37 km to the railroad; year of testing had the greatest interactive strength with all other factors; BLL increased faster in Aboriginal than in non-Aboriginal children at 9–10 and 12–18 months of age. This “stacked ensemble + model-agnostic interpretation” framework achieved both prediction accuracy and model interpretability, identifying previously unconnected variables associated with elevated childhood BLL, offering a marked advantage over previous works. Thus, this approach has a clear value and potential for application to other environmental health issues.

show abstract

“…Statistical profiling presents an increasingly important avenue for informing high-stakes policy decisions such as the allocation of scarce public resources in a variety of settings. Examples include the allocation of intervention and supervision resources in criminal justice (Howard and Dixon, 2012), the allocation of in-person investigations in the context of child protection services (Chouldechova et al, 2018), and the allocation of home inspections to identify and control health hazards (Potash et al, 2020). In these scenarios, statistical models are used to provide an initial risk assessment such that decisions can be made, for example, regarding the question which cases require special attention and should be prioritized.…”

Section: Introductionmentioning

confidence: 99%

Fairness in Algorithmic Profiling: A German Case Study

Kern,

Bach,

Mautner

et al. 2021

Preprint

View full text Add to dashboard Cite

Algorithmic profiling is increasingly used in the public sector as a means to allocate limited public resources effectively and objectively. One example is the prediction-based statistical profiling of job seekers to guide the allocation of support measures by public employment services. However, empirical evaluations of potential side-effects such as unintended discrimination and fairness concerns are rare. In this study, we compare and evaluate statistical models for predicting job seekers' risk of becoming long-term unemployed with respect to prediction performance, fairness metrics, and vulnerabilities to data analysis decisions. Focusing on Germany as a use case, we evaluate profiling models under realistic conditions by utilizing administrative data on job seekers' employment histories that are routinely collected by German public employment services. Besides showing that these data can be used to predict long-term unemployment with competitive levels of accuracy, we highlight that different classification policies have very different fairness implications. We therefore call for rigorous auditing processes before such models are put to practice.

show abstract

Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

Abstract: This prognostic study validates a machine learning (random forest) prediction model of elevated blood lead levels by comparing with a parsimonious logistic regression among children in a Women, Infants, and Children cohort.

Cited by 28 publications

References 27 publications

Life after Lead: Effects of Early Interventions for Children Exposed to Lead

Life after Lead: Effects of Early Interventions for Children Exposed to Lead

Novel Application of Machine Learning Algorithms and Model-Agnostic Methods to Identify Factors Influencing Childhood Blood Lead Levels

Fairness in Algorithmic Profiling: A German Case Study

Contact Info

Product

Resources

About