Predictive Modeling for Public Health

Potash, Eric; Brew, Joe; Loewi, Alexander; Majumdar, Subhabrata; Reece, Andrew; Walsh, Joe; Rozier, Eric W. D.; Jorgenson, Emile; Mansour, Raed; Ghani, Rayid

doi:10.1145/2783258.2788629

Cited by 28 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 31 Initial results suggested that alternative machine learning classifiers, such as a support vector machine, would perform similarly to the random forest model. 10 …”

Section: Discussionmentioning

confidence: 99%

“…In 2015, a random forest model was developed to predict EBLLs in Chicago children. 10 That model was updated with additional predictors for this study. The source code is publicly available ( https://github.com/chicago/lead-model ).…”

Section: Methodsmentioning

confidence: 99%

“…In 2015, a random forest model was developed to predict EBLLs in Chicago children. 10 These data were aggregated in various ways to create predictors for the machine learning model. For example, from the historical BLLs, we calculated the EBLL (both Ն6 and Ն10 μg/dL) counts and rates at various spatial levels (address, census block, and census tract) and time periods (1, 2, 3, 5, 10, and all available years).…”

Section: Random Forest Modelmentioning

confidence: 99%

See 2 more Smart Citations

Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“… 31 Initial results suggested that alternative machine learning classifiers, such as a support vector machine, would perform similarly to the random forest model. 10 …”

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Random Forest Modelmentioning

confidence: 99%

See 1 more Smart Citation

Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lead control interventions have focused on mitigating identified routes of exposure, primarily from lead-based paint in older housing (Carrel et al, 2017;Pirkle et al, 1998;Saegert et al, 2003). Through Pb-contaminated dust, present within housing structures, older residential dwellings are the primary route of exposure in children, and they disproportionally affect low-income, racial minorities (Gaitens et al, 2009;Jacobs, 2011;Jacobs et al, 2002;Lanphear et al, 1998bLanphear et al, , 1998aLanphear et al, , 1996Matte and Jacobs, 2000;Potash et al, 2015). In contrast, background routes of Pb-exposure represent sources that are harder to identify, typically because they are more difficult to measure and Pb is present at lower levels.…”

Section: Introductionmentioning

confidence: 99%

Variability in the spatial density of vacant properties contributes to background lead (Pb) exposure in children

Castro

Larsen

Hruska

et al. 2019

Environmental Research

View full text Add to dashboard Cite

Background: Heightened blood lead levels (BLL) are associated with cognitive deficiencies and adverse behavioral outcomes. Lead-contaminated house dust is the primary source of exposure in U.S. children, and evidence suggests that even background (low-level) exposure has negative consequences. Identifying sources of background exposure is of great public health significance because of the larger number of children that can be affected. Methods: Blood lead was assessed in a bi-racial sample of children from Syracuse, NY, aged 9-11, using established biomonitoring methods. The spatial density of vacant properties was modelled from publicly available georeferenced datasets. Further, regression models were used to measure the impact of this spatial density variable on children's BLL. Results: In a sample of 221 children, with a mean BLL of 1.06 µg/dL (SD = 0.68), results showed increases in spatial density of vacant properties predict increases in median blood-PB levels, b = 0.14 (0.06-0.21), p < .001. This association held true even after accounting for demographic covariates, and age of individual housing. Further analysis showed spatial

show abstract

“…Residual levels must be maintained such that biofilms and other residual reactants do not prematurely reduce a system's protection against pathogenic intrusion events. Reducing contaminants formed within distribution systems, such as disinfection byproducts (Boccelli et al 1998;USEPA 2002) and lead (Del Toral et al 2013;Lacey et al 1985;Levallois et al 2014;Potash et al 2015), also have been important goals for decades. As additional contaminants of concern have been identified, water age (i.e., the amount of time water spends in the distribution system moving from the point of treatment to point of consumption) has emerged as a general proxy for water quality (AWWA 2002;Machell and Boxall 2014).…”

Section: Introductionmentioning

confidence: 99%

Integrated Multiobjective Optimization and Simulation Model Applied to Drinking Water Treatment Placement in the Context of Existing Infrastructure

Schwetschenau

VanBriesen

Cohon

2019

J. Water Resour. Plann. Manage.

View full text Add to dashboard Cite

Drinking water systems provide consistent and safe supplies of water across urban areas through the use of treatment and distribution infrastructure. Design of drinking water infrastructure requires incorporation of multiple conflicting stakeholder goals, such as cost and water quality. This work expands on a previously developed integrated modeling framework that uses simulation and optimization models for long-term planning of treatment infrastructure in the context of existing distribution systems. The optimization model component is a multi-objective formulation. The expanded model framework is demonstrated on the USEPA Net3 treatment network. The multiobjective optimization includes three objectives-minimizing cost, maximizing systemwide chlorine residual, and minimizing the demand-weighted water age (a proxy for water quality)-to identify the optimal location and capacity of treatment plants. Results show the trade-offs between each pair of objectives. Of a maximum of five possible treatment locations, three treatment plants were optimal for the water quality objectives, whereas one treatment plant was optimal for the cost objective. The capacity allocation and sites selected for treatment differed between the two water quality objectives.

show abstract

Predictive Modeling for Public Health

Cited by 28 publications

References 11 publications

Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

Validation of a Machine Learning Model to Predict Childhood Lead Poisoning

Variability in the spatial density of vacant properties contributes to background lead (Pb) exposure in children

Integrated Multiobjective Optimization and Simulation Model Applied to Drinking Water Treatment Placement in the Context of Existing Infrastructure

Contact Info

Product

Resources

About