Using self-organizing maps to develop ambient air quality classifications: a time series example

Patterns of infant fecal metabolite concentrations and social behavioral development in toddlers

BACKGROUND

Gut-derived metabolites, products of microbial and host co-metabolism, may inform mechanisms underlying children's neurodevelopment. We investigated whether infant fecal metabolites were related to toddler social behavior.

METHODS

Stool samples collected from 6-week-olds (n = 86) and 1-year-olds (n = 209) in the New Hampshire Birth Cohort Study (NHBCS) were analyzed using nuclear magnetic resonance spectroscopy metabolomics. Autism-related behavior in 3-year-olds was assessed by caregivers using the Social Responsiveness Scale (SRS-2). To assess the association between metabolites and SRS-2 scores, we used a traditional single-metabolite approach, quantitative metabolite set enrichment (QEA), and self-organizing maps (SOMs).

RESULTS

Using a single-metabolite approach and QEA, no individual fecal metabolite or metabolite set at either age was associated with SRS-2 scores. Using the SOM method, fecal metabolites of six-week-olds organized into four profiles, which were unrelated to SRS-2 scores. In 1-year-olds, one of twelve fecal metabolite profiles was associated with fewer autism-related behaviors, with SRS-2 scores 3.4 (95%CI: -7, 0.2) points lower than the referent group. This profile had higher concentrations of lactate and lower concentrations of short chain fatty acids than the reference.

CONCLUSIONS

We uncovered metabolic profiles in infant stool associated with subsequent social behavior, highlighting one potential mechanism by which gut bacteria may influence neurobehavior.

IMPACT

Differences in host and microbial metabolism may explain variability in neurobehavioral phenotypes, but prior studies do not have consistent results. We applied three statistical techniques to explore fecal metabolite differences related to social behavior, including self-organizing maps (SOMs), a novel machine learning algorithm. A 1-year-old fecal metabolite pattern characterized by high lactate and low short-chain fatty acid concentrations, identified using SOMs, was associated with social behavior less indicative of autism spectrum disorder. Our findings suggest that social behavior may be related to metabolite profiles and that future studies may uncover novel findings by applying the SOM algorithm.

Heterogeneous associations of multiplexed environmental factors and multidimensional aging metrics

Complicated associations between multiplexed environmental factors and aging are poorly understood. We manipulated aging using multidimensional metrics such as phenotypic age, brain age, and brain volumes in the UK Biobank. Weighted quantile sum regression was used to examine the relative individual contributions of multiplexed environmental factors to aging, and self-organizing maps (SOMs) were used to examine joint effects. Air pollution presented a relatively large contribution in most cases. We also found fair heterogeneities in which the same environmental factor contributed inconsistently to different aging metrics. Particulate matter contributed the most to variance in aging, while noise and green space showed considerable contribution to brain volumes. SOM identified five subpopulations with distinct environmental exposure patterns and the air pollution subpopulation had the worst aging status. This study reveals the heterogeneous associations of multiplexed environmental factors with multidimensional aging metrics and serves as a proof of concept when analyzing multifactors and multiple outcomes.

Joint effects of air pollution and neighborhood socioeconomic status on cognitive decline - Mediation by depression, high cholesterol levels, and high blood pressure

Air pollution and neighborhood socioeconomic status (N-SES) are associated with adverse cardiovascular health and neuropsychiatric functioning in older adults. This study examines the degree to which the joint effects of air pollution and N-SES on the cognitive decline are mediated by high cholesterol levels, high blood pressure (HBP), and depression. In the Emory Healthy Aging Study, 14,390 participants aged 50+ years from Metro Atlanta, GA, were assessed for subjective cognitive decline using the cognitive function instrument (CFI). Information on the prior diagnosis of high cholesterol, HBP, and depression was collected through the Health History Questionnaire. Participants' census tracts were assigned 3-year average concentrations of 12 air pollutants and 16 N-SES characteristics. We used the unsupervised clustering algorithm Self-Organizing Maps (SOM) to create 6 exposure clusters based on the joint distribution of air pollution and N-SES in each census tract. Linear regression analysis was used to estimate the effects of the SOM cluster indicator on CFI, adjusting for age, race/ethnicity, education, and neighborhood residential stability. The proportion of the association mediated by high cholesterol levels, HBP, and depression was calculated by comparing the total and direct effects of SOM clusters on CFI. Depression mediated up to 87 % of the association between SOM clusters and CFI. For example, participants living in the high N-SES and high air pollution cluster had CFI scores 0.05 (95 %-CI:0.01,0.09) points higher on average compared to those from the high N-SES and low air pollution cluster; after adjusting for depression, this association was attenuated to 0.01 (95 %-CI:-0.04,0.05). HBP mediated up to 8 % of the association between SOM clusters and CFI and high cholesterol up to 5 %. Air pollution and N-SES associated cognitive decline was partially mediated by depression. Only a small portion (<10 %) of the association was mediated by HBP and high cholesterol.

Sensitive periods for exposure to indoor air pollutants and psychosocial factors in association with symptoms of psychopathology at school-age in a South African birth cohort

Background

Gestation and the first few months of life are important periods for brain development. During these periods, exposure to environmental toxicants and psychosocial stressors are particularly harmful and may impact brain development. Specifically, exposure to indoor air pollutants (IAP) and psychosocial factors (PF) during these sensitive periods has been shown to predict childhood psychopathology.

Objectives

This study aims to investigate sensitive periods for the individual and joint effects of IAP and PF on childhood psychopathology at 6.5 years.

Methods

We analyzed data from the Drakenstein Child Health Study (N=599), a South African birth cohort. Exposure to IAP and PF was measured during the second trimester of pregnancy and 4 months postpartum. The outcome of childhood psychopathology was assessed at 6.5 years old using the Childhood Behavior Checklist (CBCL). We investigated individual effects of either pre-or postnatal exposure to IAP and PF on CBCL scores using adjusted linear regression models, and joint effects of these exposures using quantile g-computation and self-organizing maps (SOM). To identify possible sensitive periods, we used a structured life course modeling approach (SLCMA) as well as exposure mixture methods (quantile g-computation and SOM).

Results

Prenatal exposure to IAP or PFs, as well as the total prenatal mixture assessed using quantile g-computation, were associated with increased psychopathology. SLCMA and SOM models also indicated that the prenatal period is a sensitive period for IAP exposure on childhood psychopathology. Depression and alcohol were associated in both the pre-and postnatal period, while CO was associated with the postnatal period.

Discussion

Pregnancy may be a sensitive period for the effect of indoor air pollution on childhood psychopathology. Exposure to maternal depression and alcohol in both periods was also associated with psychopathology. Determining sensitive periods of exposure is vital to ensure effective interventions to reduce childhood psychopathology.

Environmental, social and behavioral risk factors in association with spatial clustering of childhood cancer incidence

Childhood cancer incidence is known to vary by age, sex, and race/ethnicity, but evidence is limited regarding external risk factors. We aim to identify harmful combinations of air pollutants and other environmental and social risk factors in association with the incidence of childhood cancer based on 2003-2017 data from the Georgia Cancer Registry. We calculated the standardized incidence ratios (SIR) of Central Nervous System (CNS) tumors, leukemia and lymphomas based on age, gender and ethnic composition in each of the 159 counties in Georgia, USA. County-level information on air pollution, socioeconomic status (SES), tobacco smoking, alcohol drinking and obesity were derived from US EPA and other public data sources. We applied two unsupervised learning tools (self-organizing map [SOM] and exposure-continuum mapping [ECM]) to identify pertinent types of multi-exposure combinations. Spatial Bayesian Poisson models (Leroux-CAR) were fit with indicators for each multi-exposure category as exposure and SIR of childhood cancers as outcomes. We identified consistent associations of environmental (pesticide exposure) and social/behavioral stressors (low socioeconomic status, alcohol) with spatial clustering of pediatric cancer class II (lymphomas and reticuloendothelial neoplasms), but not for other cancer classes. More research is needed to identify the causal risk factors for these associations.

Assessment of trace elements directly from archived total suspended particulate filters by laser ablation ICP-MS: A case study of South Carolina

Background

Exposure to particulate air pollution is one of the greatest environmental risk factors for adverse human health outcomes. However, the constituents that may be responsible for such adverse health effects have not been fully studied.

Methods

Total suspended particulates filters collected every 6 days in 2011 from three South Carolina locations were used in this case study. An inductively coupled plasma mass spectrometer interfaced with a laser ablation system (LA-ICP-MS) was used to directly analyze 41 inorganic elemental species on air pollution filters. Then, machine learning and multivariate statistical methods was employed to identify combinatorial patterns in the data and classify sites based on their elemental composition.

Results

Forty-one elements were assessed and 33 were used in subsequent analysis. Correlations between United States Environmental Protection Agency (US EPA)'s chemical analysis dataset and data from the current study revealed significant associations between 7/15 elements with enough variation for comparison (r between 0.28 to 0.66, p<0.05). Subsequent multivariate analyses revealed four distinct patterns in the distribution of elements by sample location throughout the year.

Conclusion

The different airborne elements may need to be assessed to understand combinations of elements which occur together over space and/or time. Such information can be helpful in planning effective counter measures and strategies to control particulate air pollution.

The complex relationship of air pollution and neighborhood socioeconomic status and their association with cognitive decline

BACKGROUND

Air pollution and neighborhood socioeconomic status (nSES) have been shown to affect cognitive decline in older adults. In previous studies, nSES acts as both a confounder and an effect modifier between air pollution and cognitive decline.

OBJECTIVES

This study aims to examine the individual and joint effects of air pollution and nSES on cognitive decline on adults 50 years and older in Metro Atlanta, USA.

METHODS

Perceived memory and cognitive decline was assessed in 11,897 participants aged 50+ years from the Emory Healthy Aging Study (EHAS) using the cognitive function instrument (CFI). Three-year average air pollution concentrations for 12 pollutants and 16 nSES characteristics were matched to participants using census tracts. Individual exposure linear regression and LASSO models explore individual exposure effects. Environmental mixture modeling methods including, self-organizing maps (SOM), Bayesian kernel machine regression (BKMR), and quantile-based G-computation explore joint effects, and effect modification between air pollutants and nSES characteristics on cognitive decline.

RESULTS

Participants living in areas with higher air pollution concentrations and lower nSES experienced higher CFI scores (beta: 0.121; 95 % CI: 0.076, 0.167) compared to participants living in areas with low air pollution and high nSES. Additionally, the BKMR model showed a significant overall mixture effect on cognitive decline, suggesting synergy between air pollution and nSES. These joint effects explain protective effects observed in single-pollutant linear regression models, even after adjustment for confounding by nSES (e.g., an IQR increase in CO was associated with a 0.038-point lower (95 % CI: -0.06, -0.01) CFI score).

DISCUSSION

Observed protective effects of single air pollutants on cognitive decline can be explained by joint effects and effect modification of air pollutants and nSES. Researchers must consider nSES as an effect modifier if not a co-exposure to better understand the complex relationships between air pollution and nSES in urban settings.

A Multipollutant Approach to Estimating Causal Effects of Air Pollution Mixtures on Overall Mortality in a Large, Prospective Cohort

BACKGROUND

Several studies have confirmed associations between air pollution and overall mortality, but it is unclear to what extent these associations reflect causal relationships. Moreover, few studies to our knowledge have accounted for complex mixtures of air pollution. In this study, we evaluate the causal effects of a mixture of air pollutants on overall mortality in a large, prospective cohort of Dutch individuals.

METHODS

We evaluated 86,882 individuals from the LIFEWORK study, assessing overall mortality between 2013 and 2017 through national registry linkage. We predicted outdoor concentration of five air pollutants (PM2.5, PM10, NO2, PM2.5 absorbance, and oxidative potential) with land-use regression. We used logistic regression and mixture modeling (weighted quantile sum and boosted regression tree models) to identify potential confounders, assess pollutants' relevance in the mixture-outcome association, and investigate interactions and nonlinearities. Based on these results, we built a multivariate generalized propensity score model to estimate the causal effects of pollutant mixtures.

RESULTS

Regression model results were influenced by multicollinearity. Weighted quantile sum and boosted regression tree models indicated that all components contributed to a positive linear association with the outcome, with PM2.5 being the most relevant contributor. In the multivariate propensity score model, PM2.5 (OR=1.18, 95% CI: 1.08-1.29) and PM10 (OR=1.02, 95% CI: 0.91-1.14) were associated with increased odds of mortality per interquartile range increase.

CONCLUSION

Using novel methods for causal inference and mixture modeling in a large prospective cohort, this study strengthened the causal interpretation of air pollution effects on overall mortality, emphasizing the primary role of PM2.5 within the pollutant mixture.

KERNEL MACHINE AND DISTRIBUTED LAG MODELS FOR ASSESSING WINDOWS OF SUSCEPTIBILITY TO ENVIRONMENTAL MIXTURES IN CHILDREN'S HEALTH STUDIES

Exposures to environmental chemicals during gestation can alter health status later in life. Most studies of maternal exposure to chemicals during pregnancy have focused on a single chemical exposure observed at high temporal resolution. Recent research has turned to focus on exposure to mixtures of multiple chemicals, generally observed at a single time point. We consider statistical methods for analyzing data on chemical mixtures that are observed at a high temporal resolution. As motivation, we analyze the association between exposure to four ambient air pollutants observed weekly throughout gestation and birth weight in a Boston-area prospective birth cohort. To explore patterns in the data, we first apply methods for analyzing data on (1) a single chemical observed at high temporal resolution, and (2) a mixture measured at a single point in time. We highlight the shortcomings of these approaches for temporally-resolved data on exposure to chemical mixtures. Second, we propose a novel method, a Bayesian kernel machine regression distributed lag model (BKMR-DLM), that simultaneously accounts for nonlinear associations and interactions among time-varying measures of exposure to mixtures. BKMR-DLM uses a functional weight for each exposure that parameterizes the window of susceptibility corresponding to that exposure within a kernel machine framework that captures non-linear and interaction effects of the multivariate exposure on the outcome. In a simulation study, we show that the proposed method can better estimate the exposure-response function and, in high signal settings, can identify critical windows in time during which exposure has an increased association with the outcome. Applying the proposed method to the Boston birth cohort data, we find evidence of a negative association between organic carbon and birth weight and that nitrate modifies the organic carbon, elemental carbon, and sulfate exposure-response functions.

Persistent organic pollutants (POPs) - QSPR classification models by means of Machine learning strategies

Persistent Organic pollutants (POPs) are toxic chemicals with a shallow degradation rate and global negative impact. Their physicochemical is combined with the complex effects of long-term POPs accumulation in the environment and transport function through the food chain. That is why POPs have been linked to adverse effects on human health and animals. They circulate globally via different environmental pathways, and could be detected in regions far from their source of origin. The primary goal of the present study is to carry out classification of various representatives of POPs using different theoretical descriptors (molecular, structural) to develop quantitative structure-properties relationship (QSPR) models for predicting important properties POPs. Multivariate statistical methods such as hierarchical cluster analysis, principal components analysis and self-organizing maps were applied to reach excellent partitioning of 149 representatives of POPs into 4 classes using ten most appropriate descriptors (out of 63) defined by variable reduction procedure. The predictive capabilities of the defined classes could be applied as a pattern recognition for new and unidentified POPs, based only on structural properties that similar molecules may have. The additional self-organizing maps technique made it possible to visualize the feature-space and investigate possible patterns and similarities between POPs molecules. It contributes to confirmation of the proper classification into four classes. Based on SOM results, the effect of each variable and pattern formation has been presented.

Using dynamic time warping self-organizing maps to characterize diurnal patterns in environmental exposures

Advances in measurement technology are producing increasingly time-resolved environmental exposure data. We aim to gain new insights into exposures and their potential health impacts by moving beyond simple summary statistics (e.g., means, maxima) to characterize more detailed features of high-frequency time series data. This study proposes a novel variant of the Self-Organizing Map (SOM) algorithm called Dynamic Time Warping Self-Organizing Map (DTW-SOM) for unsupervised pattern discovery in time series. This algorithm uses DTW, a similarity measure that optimally aligns interior patterns of sequential data, both as the similarity measure and training guide of the neural network. We applied DTW-SOM to a panel study monitoring indoor and outdoor residential temperature and particulate matter air pollution (PM_2.5) for 10 patients with asthma from 7 households near Salt Lake City, UT; the patients were followed for up to 373 days each. Compared to previous SOM algorithms using timestamp alignment on time series data, the DTW-SOM algorithm produced fewer quantization errors and more detailed diurnal patterns. DTW-SOM identified the expected typical diurnal patterns in outdoor temperature which varied by season, as well diurnal patterns in PM_2.5 which may be related to daily asthma outcomes. In summary, DTW-SOM is an innovative feature engineering method that can be applied to highly time-resolved environmental exposures assessed by sensors to identify typical diurnal (or hourly or monthly) patterns and provide new insights into the health effects of environmental exposures.

Multi-Level Socioenvironmental Contributors to Childhood Asthma in New York City: a Cluster Analysis

Childhood asthma exacerbation remains the leading cause of pediatric emergency department visits and hospitalizations and disproportionately affects Latinx and Black children, compared to non-Latinx White children in NYC. Environmental exposures and socioeconomic factors may jointly contribute to childhood asthma exacerbations; however, they are often studied separately. To better investigate the multiple contributors to disparities in childhood asthma, we compiled data on various individual and neighborhood level socioeconomic and environmental factors, including education, race/ethnicity, income disparities, gentrification, housing characteristics, built environment, and structural racism, from the NYC Department of Health's KIDS 2017 survey and the US Census' American Community Survey. We applied cluster analysis and logistic regression to first identify the predominant patterns of social and environmental factors experienced by children in NYC and then estimate whether children experiencing specific patterns are more likely to experience asthma exacerbations. We found that housing and built environment characteristics, such as density and age of buildings, were the predominant features to differentiate the socio-environmental patterns observed in New York City. Children living in neighborhoods with greater proportions of rental housing, high-density buildings, and older buildings were more likely to experience asthma exacerbations than other children. These findings add to the literature about childhood asthma in urban environments, and can assist efforts to target actionable policies and practices that promote health equity related to childhood asthma.

Model choice for estimating the association between exposure to chemical mixtures and health outcomes: A simulation study

Challenges arise in researching health effects associated with chemical mixtures. Several methods have recently been proposed for estimating the association between health outcomes and exposure to chemical mixtures, but a formal simulation study comparing broad-ranging methods is lacking. We select five recently developed methods and evaluate their performance in estimating the exposure-response function, identifying active mixture components, and identifying interactions in a simulation study. Bayesian kernel machine regression (BKMR) and nonparametric Bayes shrinkage (NPB) were top-performing methods in our simulation study. BKMR and NPB outperformed other contemporary methods and traditional linear models in estimating the exposure-response function and identifying active mixture components. BKMR and NPB produced similar results in a data analysis of the effects of multipollutant exposure on lung function in children with asthma.

Chemometrics for environmental monitoring: a review

Environmental monitoring is necessary to ensure the overall health and conservation of an ecosystem. However, ecosystems (e.g. air, water, soil), are complex, involving numerous processes (both native and external), inputs, contaminants, and living organisms. As such, monitoring an environmental system is not a trivial task. The data obtained from natural systems is often multifaceted and convoluted, as a multitude of inputs can be intertwined within the matrix of the information obtained as part of a study. This means that trends and important results can be easily overlooked by conventional and single dimensional data analysis protocols. Recently, chemometric methods have emerged as a powerful method for maximizing the details contained within a chemical data set. Specifically, chemometrics refers to the use of mathematical and statistical analysis methods to evaluate chemical data, beyond univariant analysis. This type of analysis can provide a quantitative description of environmental measurements, while also having the capacity to reveal previously overlooked trends in data sets. Applying chemometrics to environmental data allows us to identify and describe the inter-relationship of environmental drivers, sources of contamination, and their potential impact upon the environment. This review aims to provide a detailed understanding of chemometric techniques, how they are currently used in environmental monitoring, and how these techniques can be used to improve current practices. An enhanced ability to monitor environmental conditions and to predict trends would be greatly beneficial to government and research agencies in their ability to develop environmental policies and analytical procedures.

Assessment of Multipollutant Exposures During Pregnancy Using Silicone Wristbands

Silicone wristbands can assess multipollutant exposures in a non-invasive and minimally burdensome manner, which may be suitable for use among pregnant women. We investigated silicone wristbands as passive environmental samplers in the New Hampshire Birth Cohort Study, a prospective pregnancy cohort. We used wristbands to assess exposure to a broad range of organic chemicals, identified multipollutant exposure profiles using self-organizing maps (SOMs), and assessed temporal consistency and determinants of exposures during pregnancy. Participants (n = 255) wore wristbands for 1 week at 12 gestational weeks. Of 1,530 chemicals assayed, 199 were detected in at least one wristband and 16 were detected in >60% of wristbands. A median of 23 (range: 12,37) chemicals were detected in each wristband, and chemicals in commerce and personal care products were most frequently detected. A subset of participants (n=20) wore a second wristband at 24 gestational weeks, and concentrations of frequently detected chemicals were moderately correlated between time points (median intraclass correlation: 0.22; range: 0.00,0.69). Women with higher educational attainment had fewer chemicals detected in their wristbands and the total number of chemicals detected varied seasonally. Triphenyl phosphate concentrations were positively associated with nail polish use, and benzophenone concentrations were highest in summer. No clear associations were observed with other a priori relations, including certain behaviors, season, and socioeconomic factors. SOM analyses revealed 12 profiles, ranging from 2 to 149 participants, captured multipollutant exposure profiles observed in this cohort. The most common profile (n = 149) indicated that 58% of participants experienced relatively low exposures to frequently detected chemicals. Less common (n ≥ 10) and rare (n < 10) profiles were characterized by low to moderate exposures to most chemicals and very high and/or very low exposure to a subset of chemicals. Certain covariates varied across SOM profile membership; for example, relative to women in the most common profile who had low exposures to most chemicals, women in the profile with elevated exposure to galaxolide and benzyl benzoate were younger, more likely to be single, and more likely to report nail polish use. Our study illustrates the utility of silicone wristbands for measurement of multipollutant exposures in sensitive populations, including pregnant women.

Dynamics of plant responses to combinations of air pollutants

The focus of this review is on how plants respond to combinations of multiple air pollutants. Global pollution trends, plant physiological responses and ecological perspectives in natural and agricultural systems are all discussed. In particular, we highlight the importance of studying sequential or simultaneous exposure of plants to pollutants, rather than exposure to individual pollutants in isolation, and explore how these responses may interfere with the way plants interact with their biotic community. Air pollutants can alter the normal physiology and metabolic functioning of plants. Here we describe how the phenotypic and molecular changes in response to multiple pollutants can differ compared to those elicited by single pollutants, and how different responses have been observed between plants in the field and in controlled laboratory conditions and between trees and crop plants. From an ecological perspective, we discuss how air pollution can result in greater susceptibility to biotic stressors and in direct or indirect effects on interactions with organisms that occupy higher trophic levels. Finally, we provide an overview of the potential uses of plants to mitigate air pollution, exploring the feasibility for pollution removal via the processes of bio-accumulation and phytoremediation. We conclude by proposing some new directions for future research in the field.

Perspectivas do uso de mineração de dados e aprendizado de máquina em saúde e segurança no trabalho

Resumo Introdução: a variedade, volume e velocidade de geração de dados (big data) possibilitam novas e mais complexas análises. Objetivo: discutir e apresentar técnicas de mineração de dados (data mining) e de aprendizado de máquina (machine learning) para auxiliar pesquisadores de Saúde e Segurança no Trabalho (SST) na escolha da técnica adequada para lidar com big data. Métodos: revisão bibliográfica com foco em data mining e no uso de análises preditivas com machine learning e suas aplicações para auxiliar diagnósticos e predição de riscos em SST. Resultados: a literatura indica que aplicações de data mining com algoritmos de machine learning para análises preditivas em saúde pública e em SST apresentam melhor desempenho em comparação com análises tradicionais. São sugeridas técnicas de acordo com o tipo de pesquisa almejada. Discussão: data mining tem se tornado uma alternativa cada vez mais comum para lidar com bancos de dados de saúde pública, possibilitando analisar grandes volumes de dados de morbidade e mortalidade. Tais técnicas não visam substituir o fator humano, mas auxiliar em processos de tomada de decisão, servir de ferramenta para a análise estatística e gerar conhecimento para subsidiar ações que possam melhorar a qualidade de vida do trabalhador.

Associations between multipollutant day types and select cardiorespiratory outcomes in Columbia, South Carolina, 2002 to 2013

Background

Health studies of air pollution are increasingly aiming to study associations between air pollutant mixtures and health.

Objective

Estimate associations between observed combinations of ambient air pollutants and select cardiorespiratory outcomes in Columbia, SC during 2002 to 2013.

Methods

We estimate associations using a two-stage approach. First, we identified a collection of observed pollutant combinations, which we define as multipollutant day types (MDTs), by applying a self-organizing map (SOM) to daily measures of nitrogen dioxide (NO₂), sulfur dioxide (SO₂), ozone (O₃), and particulate matter ≤ 2.5 microns (PM_2.5). Then, overdispersed Poisson time-series models were used to estimate associations between MDTs and each outcome using a 'clean' MDT referent and controlling for long-term, seasonal, and day-of-the-week trends and meteorology. Outcomes included daily emergency department visits for asthma and upper respiratory infection (URI), and hospital admissions for congestive heart failure (CHF) and ischemic heart disease (IHD).

Results

We found that a number of MDTs were significantly and positively associated (point estimates ranged from~2-5%) with cardiorespiratory outcomes in Columbia when compared to days with low pollution. Estimated associations revealed that outcomes for asthma, URIs, and IHD increased 2-4% on warm, dry days experiencing elevated levels of O₃ and PM_2.5. We also found that cooler days with higher NO₂ pollution associated with increased asthma, CHF, and IHD outcomes (2-5%).

Conclusion

Our analysis continues support for using self-organizing maps to develop multipollutant exposure metrics and further illustrates how such metrics can be applied to explore associations between pertinent pollutant combinations and health.

Using self-organizing map for coastal water quality classification: Towards a better understanding of patterns and processes

Self-organizing map (SOM) was used to explore the spatial characteristics of water quality in the middle and southern Fujian coastal area. Nineteen water quality variables (temperature, salinity, pH, dissolved oxygen, alkalinity, chemical oxygen demand, nutrients NH₄-N, H₂SiO₃, PO₄^-, NO₂^-, and NO₃^-, heavy metals/metalloid Cu, Zn, As, Cd, Pb, Hg, and Cr⁶⁺, and oil) were measured in the surface, middle, and bottom water layers at 94 different sampling sites. Patterns of water quality variables were visualized by the SOM planes, and similar patterns were observed for those variables that correlated with each other, indicating a common source. pH, COD, As, Hg, Pb, and Cr⁶⁺ likely originated from industries, while nutrients NH₄-N, NO₂^-, NO₃^-, and PO₄^3- were mainly attributed to agriculture and aquaculture. The k-means clustering in the SOM grouped the water quality data into nine clusters, which revealed three representative water types, ranging from low salinity to high salinity with different levels of heavy metal/metalloid pollution and nutrient pollution. Spatial changes in water quality reflected the impacts of natural factors (riverine outflows, tides, and alongshore currents), as well as anthropogenic activities (mariculture, industrial and urban discharges, and agricultural effluents). Principal component analysis (PCA) confirmed the clustering results obtained by SOM, while the latter provides a more detailed classification and additional information about the dominant variables governing the classification processes. The results of this study suggest that SOM is an effective tool for a better understanding of patterns and processes driving water quality.

Characterizing the spatial distribution of multiple pollutants and populations at risk in Atlanta, Georgia

BACKGROUND

Exposure metrics that identify spatial contrasts in multipollutant air quality are needed to better understand multipollutant geographies and health effects from air pollution. Our aim is to improve understanding of: (1) long-term spatial distributions of multiple pollutants; and (2) demographic characteristics of populations residing within areas of differing air quality.

METHODS

We obtained average concentrations for ten air pollutants (p=10) across a 12 km grid (n=253) covering Atlanta, Georgia for 2002-2008. We apply a self-organizing map (SOM) to our data to derive multipollutant patterns observed across our grid and classify locations under their most similar pattern (i.e, multipollutant spatial type (MST)). Finally, we geographically map classifications to delineate regions of similar multipollutant characteristics and characterize associated demographics.

RESULTS

We found six MSTs well describe our data, with profiles highlighting a range of combinations, from locations experiencing generally clean air to locations experiencing conditions that were relatively dirty. Mapping MSTs highlighted that downtown areas were dominated by primary pollution and that suburban areas experienced relatively higher levels of secondary pollution. Demographics show the largest proportion of the overall population resided in downtown locations experiencing higher levels of primary pollution. Moreover, higher proportions of nonwhites and children in poverty reside in these areas when compared to suburban populations that resided in areas exhibiting relatively lower pollution.

CONCLUSION

Our approach reveals the nature and spatial distribution of differential pollutant combinations across urban environments and provides helpful insights for identifying spatial exposure and demographic contrasts for future health studies.

Exploring associations between multipollutant day types and asthma morbidity: epidemiologic applications of self-organizing map ambient air quality classifications

BACKGROUND

Recent interest in the health effects of air pollution focuses on identifying combinations of multiple pollutants that may be associated with adverse health risks.

OBJECTIVE

Present a methodology allowing health investigators to explore associations between categories of ambient air quality days (i.e., multipollutant day types) and adverse health.

METHODS

First, we applied a self-organizing map (SOM) to daily air quality data for 10 pollutants collected between January 1999 and December 2008 at a central monitoring location in Atlanta, Georgia to define a collection of multipollutant day types. Next, we conducted an epidemiologic analysis using our categories as a multipollutant metric of ambient air quality and daily counts of emergency department (ED) visits for asthma or wheeze among children aged 5 to 17 as the health endpoint. We estimated rate ratios (RR) for the association of multipollutant day types and pediatric asthma ED visits using a Poisson generalized linear model controlling for long-term, seasonal, and weekday trends and weather.

RESULTS

Using a low pollution day type as the reference level, we found significant associations of increased asthma morbidity in three of nine categories suggesting adverse effects when combinations of primary (CO, NO2, NOX, EC, and OC) and/or secondary (O3, NH4, SO4) pollutants exhibited elevated concentrations (typically, occurring on dry days with low wind speed). On days with only NO3 elevated (which tended to be relatively cool) and on days when only SO2 was elevated (which likely reflected plume touchdowns from coal combustion point sources), estimated associations were modestly positive but confidence intervals included the null.

CONCLUSIONS

We found that ED visits for pediatric asthma in Atlanta were more strongly associated with certain day types defined by multipollutant characteristics than days with low pollution levels; however, findings did not suggest that any specific combinations were more harmful than others. Relative to other health endpoints, asthma exacerbation may be driven more by total ambient pollutant exposure than by composition.