A novel method to evaluate the community built environment using photographs--Environmental Profile of a Community Health (EPOCH) photo neighbourhood evaluation tool

Cultural Sets Shape Adult Conceptualizations and Relationships to Nature

The variability of nature and the nature construct have complicated interpretations of empirical evidence from nature-based health studies. The challenge of defining nature exposure for purposes of methodological standardization may encompass constructs beyond vegetated landcover. This study offers a new construct for defining 'nature exposure' that considers cultural sets and nature familiarity. Focus group discussions across the United States (N = 126) explored the concept of what constitutes the relationship to nature. The participant diversity included regions, cultural demographics, cumulative nature experience, and everyday nature exposure. Mixed methods of semi-structured discussion and a photo exercise that prompted nature connectedness allowed for data triangulation and the detection of contradictions between approaches. Individuals conceptualized nature in ways reflecting highly personal and differentiated experiences, which defied consensus toward a single nature construct. The group scoring of photo imagery showed consistent high and low levels of nature connectedness with respect to wildness and outdoor urban venues, respectively, but diverged in the assessment of nature within the built environment. Everyday nature exposure significantly differentiated how groups conceptualized and related to nature imagery. This result may indicate an unmet biophilic need among groups with low backgrounds of nature exposure. The contrasts between the discussion content and the observed reactions to nature imagery showed the value of using mixed methods in qualitative research.

Exploring convolutional neural networks and spatial video for on-the-ground mapping in informal settlements

BACKGROUND

The health burden in developing world informal settlements often coincides with a lack of spatial data that could be used to guide intervention strategies. Spatial video (SV) has proven to be a useful tool to collect environmental and social data at a granular scale, though the effort required to turn these spatially encoded video frames into maps limits sustainability and scalability. In this paper we explore the use of convolution neural networks (CNN) to solve this problem by automatically identifying disease related environmental risks in a series of SV collected from Haiti. Our objective is to determine the potential of machine learning in health risk mapping for these environments by assessing the challenges faced in adequately training the required classification models.

RESULTS

We show that SV can be a suitable source for automatically identifying and extracting health risk features using machine learning. While well-defined objects such as drains, buckets, tires and animals can be efficiently classified, more amorphous masses such as trash or standing water are difficult to classify. Our results further show that variations in the number of image frames selected, the image resolution, and combinations of these can be used to improve the overall model performance.

CONCLUSION

Machine learning in combination with spatial video can be used to automatically identify environmental risks associated with common health problems in informal settlements, though there are likely to be variations in the type of data needed for training based on location. Success based on the risk type being identified are also likely to vary geographically. However, we are confident in identifying a series of best practices for data collection, model training and performance in these settings. We also discuss the next step of testing these findings in other environments, and how adding in the simultaneously collected geographic data could be used to create an automatic health risk mapping tool.

Small-Area Factors and Their Impact on Low Birth Weight-Results of a Birth Cohort Study in Bielefeld, Germany

Introduction: The location of residence is a factor possibly contributing to social inequalities and emerging evidence indicates that it already affects perinatal development. The underlying pathways remain unknown; theory-based and hypothesis-driven analyses are lacking. To address these challenges, we aim to establish to what extent small-area characteristics contribute to low birth weight (LBW), independently of individual characteristics. First, we select small-area characteristics based on a conceptual model and measure them. Then, we empirically analyse the impact of these characteristics on LBW. Material and methods: Individual data were provided by the birth cohort study "Health of infants and children in Bielefeld/Germany." The sample consists of 892 eligible women and their infants distributed over 80 statistical districts in Bielefeld. Small-area data were obtained from local noise maps, emission inventory, Google Street View and civil registries. A linear multilevel analysis with a two-level structure (individuals nested within statistical districts) was conducted. Results: The effects of the selected small-area characteristics on LBW are small to non-existent, no significant effects are detected. The differences in proportion of LBW based on marginal effects are small, ranging from zero to 1.1%. Newborns from less aesthetic and subjectively perceived unsafe neighbourhoods tend to have higher proportions of LBW. Discussion: We could not find evidence for negative effects of small-area factors on LBW, but our study confirms that obtaining adequate sample size, reliable measure of exposure and using available data for operationalisation of the small-area context represent the core challenges in this field of research.

Extending Data for Urban Health Decision-Making: a Menu of New and Potential Neighborhood-Level Health Determinants Datasets in LMICs

Area-level indicators of the determinants of health are vital to plan and monitor progress toward targets such as the Sustainable Development Goals (SDGs). Tools such as the Urban Health Equity Assessment and Response Tool (Urban HEART) and UN-Habitat Urban Inequities Surveys identify dozens of area-level health determinant indicators that decision-makers can use to track and attempt to address population health burdens and inequalities. However, questions remain as to how such indicators can be measured in a cost-effective way. Area-level health determinants reflect the physical, ecological, and social environments that influence health outcomes at community and societal levels, and include, among others, access to quality health facilities, safe parks, and other urban services, traffic density, level of informality, level of air pollution, degree of social exclusion, and extent of social networks. The identification and disaggregation of indicators is necessarily constrained by which datasets are available. Typically, these include household- and individual-level survey, census, administrative, and health system data. However, continued advancements in earth observation (EO), geographical information system (GIS), and mobile technologies mean that new sources of area-level health determinant indicators derived from satellite imagery, aggregated anonymized mobile phone data, and other sources are also becoming available at granular geographic scale. Not only can these data be used to directly calculate neighborhood- and city-level indicators, they can be combined with survey, census, administrative and health system data to model household- and individual-level outcomes (e.g., population density, household wealth) with tremendous detail and accuracy. WorldPop and the Demographic and Health Surveys (DHS) have already modeled dozens of household survey indicators at country or continental scales at resolutions of 1 × 1 km or even smaller. This paper aims to broaden perceptions about which types of datasets are available for health and development decision-making. For data scientists, we flag area-level indicators at city and sub-city scales identified by health decision-makers in the SDGs, Urban HEART, and other initiatives. For local health decision-makers, we summarize a menu of new datasets that can be feasibly generated from EO, mobile phone, and other spatial data-ideally to be made free and publicly available-and offer lay descriptions of some of the difficulties in generating such data products.

Beyond Nutrient Intake: Use of Digital Food Photography Methodology to Examine Family Dinnertime

OBJECTIVE

To explore the feasibility of using an image-based food photography methodology (Remote Food Photography Method) in a rural, low-resource audience and use the photos to examine the context of family dinner.

DESIGN

Parents used the SmartIntake app on study-issued tablets to take before and after photos of their and their child's dinner for about 7 nights and participated in a mini-focus group to discuss their experience with the Remote Food Photography Method.

SETTING

Six Head Start/preschool centers in rural Colorado.

PARTICIPANTS

Mother-child dyads (n = 31).

VARIABLES MEASURED

Number and quality of photos received, participant feedback, meal timing, concordance, location, preparation, and quality.

ANALYSIS

The researchers assessed feasibility via practicality (percent photos received) and acceptability (general inductive approach used to analyze mini-focus group transcripts for participant feedback); time stamps, meal quality, and food preparation scales were used to analyze dinner photos.

RESULTS

The majority of photographs (738 of 864) were received. Participants reacted favorably to the methodology; for some, it led to greater self-reflection about mealtime. Mother-child dyads usually ate dinner at the same time and often ate the same food. Children were frequently served protein and refined grains and were rarely served whole grains or fruit. Many families relied on convenience foods.

CONCLUSIONS AND IMPLICATIONS

Digital food photography was feasible in this audience. Photos yielded a holistic picture of family dinnertime: meal timing, location, concordance in parent-child meals, level of preparation, and meal quality.

A picture tells a thousand…exposures: Opportunities and challenges of deep learning image analyses in exposure science and environmental epidemiology

BACKGROUND

Artificial intelligence (AI) is revolutionizing our world, with applications ranging from medicine to engineering.

OBJECTIVES

Here we discuss the promise, challenges, and probable data sources needed to apply AI in the fields of exposure science and environmental health. In particular, we focus on the use of deep convolutional neural networks to estimate environmental exposures using images and other complementary data sources such as cell phone mobility and social media information.

DISCUSSION

Characterizing the health impacts of multiple spatially-correlated exposures remains a challenge in environmental epidemiology. A shift toward integrated measures that simultaneously capture multiple aspects of the urban built environment could improve efficiency and provide important insights into how our collective environments influence population health. The widespread adoption of AI in exposure science is on the frontier. This will likely result in new ways of understanding environmental impacts on health and may allow for analyses to be efficiently scaled for broad coverage. Image-based convolutional neural networks may also offer a cost-effective means of estimating local environmental exposures in low and middle-income countries where monitoring and surveillance infrastructure is limited. However, suitable databases must first be assembled to train and evaluate these models and these novel approaches should be complemented with traditional exposure metrics.

CONCLUSIONS

The promise of deep learning in environmental health is great and will complement existing measurements for data-rich settings and could enhance the resolution and accuracy of estimates in data poor scenarios. Interdisciplinary partnerships will be needed to fully realize this potential.

Urban Health Indicator Tools of the Physical Environment: a Systematic Review

Urban health indicator (UHI) tools provide evidence about the health impacts of the physical urban environment which can be used in built environment policy and decision-making. Where UHI tools provide data at the neighborhood (and lower) scale they can provide valuable information about health inequalities and environmental deprivation. This review performs a census of UHI tools and explores their nature and characteristics (including how they represent, simplify or address complex systems) to increase understanding of their potential use by municipal built environment policy and decision-makers. We searched seven bibliographic databases, four key journals and six practitioner websites and conducted Google searches between January 27, 2016 and February 24, 2016 for UHI tools. We extracted data from primary studies and online indicator systems. We included 198 documents which identified 145 UHI tools comprising 8006 indicators, from which we developed a taxonomy. Our taxonomy classifies the significant diversity of UHI tools with respect to topic, spatial scale, format, scope and purpose. The proportions of UHI tools which measure data at the neighborhood and lower scale, and present data via interactive maps, have both increased over time. This is particularly relevant to built environment policy and decision-makers, reflects growing analytical capability and offers the potential for improved understanding of the complexity of influences on urban health (an aspect noted as a particular challenge by some indicator producers). The relation between urban health indicators and health impacts attributable to modifiable environmental characteristics is often indirect. Furthermore, the use of UHI tools in policy and decision-making appears to be limited, thus raising questions about the continued development of such tools by multiple organisations duplicating scarce resources. Further research is needed to understand the requirements of built environment policy and decision-makers, public health professionals and local communities regarding the form and presentation of indicators which support their varied objectives.

The picture of health: examining school-based health environments through photographs

Health-promoting schools (HPS) is an effective approach to enhance the health and well-being of children and youth, but its measurement remains a challenge considering contextual differences across school environments. The purpose of this study was to qualitatively explore the physical features of the school environment through photographs of schools that had implemented an HPS approach compared with schools that had not. This study used a descriptive approach, wherein physical features of the school environment were distilled through visual images and qualitatively analyzed. School environment data were collected from 18 elementary schools (10 HPS, 8 comparison schools) from a school board in rural Nova Scotia (Canada). Evaluation assistants captured photographs of the physical school environment as part of a broader environment audit. Overarching themes included the promotion, access and availability of opportunities for healthy eating and physical activity, healthy school climate and safety and accessibility of the school. The photographs characterized diverse aspects of the school environment and revealed differences between schools that had implemented an HPS approach compared with schools that had not. There were increased visual cues to support healthy eating, physical activity and mental well-being, and indications of a holistic approach to health among schools that implemented an HPS approach. This research adds to understanding the environmental elements of HPS. The use of photographic data to understand school environments provided an innovative method to explore the physical features of schools that had implemented an HPS approach.