Into the Black Box: What Can Machine Learning Offer Environmental Health Research?

Schmidt, Charles W.

doi:10.1289/ehp5878

Cited by 15 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical ML modeling is considered a “black-box” approach; however, interpretable ML provides a framework that can help explain the reasoning of the “learning system” to improve prediction credibility. ,− Previous studies have produced predictions with very fine resolutions, ranging from 1 km to 100 m for certain areas, but the quality of these fine-scale predictions is unknown. In the estimation and evaluation of subgrid gradients, the following five issues matter: (1) availability of local spatiotemporal information (e.g., microscale measures) to support the finer scale considered, (2) targeted validations to reflect not only interpolation but also extrapolation capability for substantial distances, (3) specialized interpretation tools to measure the contributions of local variations, (4) locally dense monitoring networks (that benefit from advanced measurement and sensing techniques , ) for direct evaluation, and (5) applicability to exposure and health studies and environmental justice assessments. − …”

Section: Discussionmentioning

confidence: 99%

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations

Ren

Cai

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

3D-grid-based chemical transport models, such as the Community Multiscale Air Quality (CMAQ) modeling system, have been widely used for predicting concentrations of ambient air pollutants. However, typical horizontal resolutions of nationwide CMAQ simulations (12 × 12 km2) cannot capture local-scale gradients for accurately assessing human exposures and environmental justice disparities. In this study, a Bayesian ensemble machine learning (BEML) framework, which integrates 13 learning algorithms, was developed for downscaling CMAQ estimates of ozone daily maximum 8 h averages to the census tract level, across the contiguous US, and was demonstrated for 2011. Three-stage hyperparameter tuning and targeted validations were designed to ensure the ensemble model’s ability to interpolate, extrapolate, and capture concentration peaks. The Shapley value metric from coalitional game theory was applied to interpret the drivers of subgrid gradients. The flexibility (transferability) of the 2011-trained BEML model was further tested by evaluating its ability to estimate fine-scale concentrations for other years (2012–2017) without retraining. To demonstrate the feasibility of using the BEML approach to strictly “data-limited” situations, the model was applied to downscale CMAQ outputs for a future-year scenario-based simulation that considers effects of variations in meteorology associated with climate change.

show abstract

Section: Discussionmentioning

confidence: 99%

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations

Ren

Cai

et al. 2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…28 Environmental health AI can help elucidate how environmental toxin exposures contribute to the development of disease and promote preventive policy and infrastructural changes. 29,30 Applications focused on primary care settings seemed to have lower translatability. One such application in diabetes was a proposal to generate policy recommendations that reduce preventive care disparities in patients with diabetes using Medicare claims data and Markov decision process analysis (eTable 5 in the Supplement, detecting, understanding, and reducing diabetes belt preventive care disparities).…”

Section: Discussionmentioning

confidence: 99%

Translatability Analysis of National Institutes of Health–Funded Biomedical Research That Applies Artificial Intelligence

et al. 2022

View full text Add to dashboard Cite

Key Points Question Which applications of artificial intelligence (AI) in biomedical research could generate the most translational value (ie, ability to lead to development that has measurable value for human health)? Findings In this cohort study using bibliometric analysis, 2 citation-based metrics were used as proxies for translational impact, and 75 unique medical applications of AI were identified from a set of 16 629 National Institutes of Health awards related to AI, using natural language processing. Varied applications were found to have high translatability, but bias against applications in basic biochemical analysis was evident. Meaning These findings suggest that National Institutes of Health award data applications of AI in biomedical research are not equivalent: some demonstrate greater potential for translational impact than others.

show abstract

“…Machine Learning (ML) has been gaining popularity in environmental health sciences [ 28 ]. However, most ML applications are pursued for prediction rather than for association inference [ 29 ].…”

Section: Introductionmentioning

confidence: 99%

Socioexposomics of COVID-19 across New Jersey: a comparison of geostatistical and machine learning approaches

Ren

Georgopoulos

2023

J Expo Sci Environ Epidemiol

View full text Add to dashboard Cite

Background Disparities in adverse COVID-19 health outcomes have been associated with multiple social and environmental stressors. However, research is needed to evaluate the consistency and efficiency of methods for studying these associations at local scales. Objective To assess socioexposomic associations with COVID-19 outcomes across New Jersey and evaluate consistency of findings from multiple modeling approaches. Methods We retrieved data for COVID-19 cases and deaths for the 565 municipalities of New Jersey up to the end of the first phase of the pandemic, and calculated mortality rates with and without long-term-care (LTC) facility deaths. We considered 84 spatially heterogeneous environmental, demographic and socioeconomic factors from publicly available databases, including air pollution, proximity to industrial sites/facilities, transportation-related noise, occupation and commuting, neighborhood and housing characteristics, age structure, racial/ethnic composition, poverty, etc. Six geostatistical models (Poisson/Negative-Binomial regression, Poison/Negative-Binomial mixed effect model, Poisson/Negative-Binomial Bersag-York-Mollie spatial model) and two Machine Learning (ML) methods (Random Forest, Extreme Gradient Boosting) were implemented to assess association patterns. The Shapley effects plot was established for explainable ML and change of support validation was introduced to compare performances of different approaches. Results We found robust positive associations of COVID-19 mortality with historic exposures to NO2, population density, percentage of minority and below high school education, and other social and environmental factors. Exclusion of LTC deaths does not significantly affect correlations for most factors but findings can be substantially influenced by model structures and assumptions. The best performing geostatistical models involved flexible structures representing data variations. ML methods captured association patterns consistent with the best performing geostatistical models, and furthermore detected consistent nonlinear associations not captured by geostatistical models. Significance The findings of this work improve the understanding of how social and environmental disparities impacted COVID-19 outcomes across New Jersey.

show abstract

Into the Black Box: What Can Machine Learning Offer Environmental Health Research?

Cited by 15 publications

References 10 publications

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations

Flexible Bayesian Ensemble Machine Learning Framework for Predicting Local Ozone Concentrations

Translatability Analysis of National Institutes of Health–Funded Biomedical Research That Applies Artificial Intelligence

Socioexposomics of COVID-19 across New Jersey: a comparison of geostatistical and machine learning approaches

Contact Info

Product

Resources

About