Explore the vast range of titles available.

Geospatial health data are essential to inform public health and policy. These data can be used to quantify disease burden, understand geographic and temporal patterns, identify risk factors, and measure inequalities. Geospatial Health Data: Modeling and Visualization with R-INLA and Shiny describes spatial and spatio-temporal statistical methods and visualization techniques to analyze georeferenced health data in R. The book covers the following topics: Manipulating and transforming point, areal, and raster data, Bayesian hierarchical models for disease mapping using areal and geostatistical data, Fitting and interpreting spatial and spatio-temporal models with the integrated nested Laplace approximation (INLA) and the stochastic partial differential equation (SPDE) approaches, Creating interactive and static visualizations such as disease maps and time plots, Reproducible R Markdown reports, interactive dashboards, and Shiny web applications that facilitate the communication of insights to collaborators and policymakers. The book features fully reproducible examples of several disease and environmental applications using real-world data such as malaria in The Gambia, cancer in Scotland and USA, and air pollution in Spain. Examples in the book focus on health applications, but the approaches covered are also applicable to other fields that use georeferenced data including epidemiology, ecology, demography or criminology. The book provides clear descriptions of the R code for data importing, manipulation, modelling, and visualization, as well as the interpretation of the results. This ensures contents are fully reproducible and accessible for students, researchers and practitioners. I Geospatial health data and INLA 1. Geospatial health Geospatial health data Disease mapping Communication of results 2. Spatial data and R packages for mapping Types of spatial data Areal data Geostatistical data Point patterns Coordinate Reference Systems (CRS) Geographic coordinate systems Projected coordinate systems Setting Coordinate Reference Systems in R Shapefiles Making maps with R ggplot2 leaflet mapview tmap 3. Bayesian inference and INLA Bayesian inference Integrated Nested Laplace Approximations (INLA) 4. The R-INLA package Linear predictor The inla() function Priors specification Example Data Model Results Control variables to compute approximations II Modeling and visualization 5. Areal data Spatial neighborhood matrices Standardized Incidence Ratio (SIR) Spatial small area disease risk estimation Spatial modeling of lung cancer in Pennsylvania Spatio-temporal small area disease risk estimation Issues with areal data 6. Spatial modeling of areal data. Lip cancer in Scotland Data and map Data preparation Adding data to map Mapping SIRs Modeling Model Neighborhood matrix Inference using INLA Results Mapping relative risks Exceedance probabilities 7. Spatio-temporal modeling of areal data. Lung cancer in Ohio Data and map Data preparation Observed cases Expected cases SIRs Adding data to map Mapping SIRs Time plots of SIRs Modeling Model Neighborhood matrix Inference using INLA Mapping relative risks 8. Geostatistical data Gaussian random fields Stochastic Partial Differential Equation approach (SPDE) Spatial modeling of rainfall in Paraná, Brazil Model Mesh construction Building the SPDE model on the mesh Index set Projection matrix Prediction data Stack with data for estimation and prediction Model formula inla() call Results Projecting the spatial field Disease mapping with geostatistical data 9. Spatial modeling of geostatistical data. Malaria in The Gambia Data Data preparation Prevalence Transforming coordinates Mapping prevalence Environmental covariates Modeling Model Mesh construction Building the SPDE model on the mesh Index set Projection matrix Prediction data Stack with data for estimation and prediction Model formula inla() call Mapping malaria prevalence Mapping exceedance probabilities 10. Spatio-temporal modeling of geostatistical data. Air pollution in Spain Map Data Modeling Model Mesh construction Building the SPDE model on the mesh Index set Projection matrix Prediction data Stack with data for estimation and prediction Model formula inla() call Results Mapping air pollution predictions III Communication of results 11. Introduction to R Markdown R Markdown YAML Markdown syntax R code chunks Figures Tables Example 12. Building a dashboard to visualize spatial data with flexdashboard The R package flexdashboard R Markdown Layout Dashboard components A dashboard to visualize global air pollution Data Table using DT Map using leaflet Histogram using ggplot2 R Markdown structure. YAML header and layout R code to obtain the data and create the visualizations 13. Introduction to Shiny Examples of Shiny apps Structure of a Shiny app Inputs Outputs Inputs, outputs and reactivity Examples of Shiny apps Example 1 Example 2 HTML Content Layouts Sharing Shiny apps 14. Interactive dashboards with flexdashboard and Shiny An interactive dashboard to visualize global air pollution 15. Building a Shiny app to upload and visualize spatio-temporal data Shiny Setup Structure of app.R Layout HTML content Read data Adding outputs Table using DT Time plot using dygraphs Map using leaflet Adding reactivity Reactivity in dygraphs Reactivity in leaflet Uploading data Inputs in ui to upload a CSV file and a shapefile Uploading CSV file in server() Uploading shapefile in server() Accessing the data and the map Handling missing inputs Requiring input files to be available using req() Checking data are uploaded before creating the map Conclusion 16. Disease surveillance with SpatialEpiApp Installation Use of SpatialEpiApp ‘Inputs’ page ‘Analysis’ page ‘Help’ page Appendix A R installation and packages used in the book A.1 Installing R and RStudio A.2 Installing R packages A.3 Packages used in the book \" The stress is on practical usage of INLA modelling in a spatial context and hence the author shows the full code for several carefully selected examples. Essentially all the steps from the beginning (necessary data manipulation and preparation) via INLA analysis itself (often in several alternatives) to the results (plots and maps) are explained carefully and commented. This is very useful for anybody who wants to start with the powerful INLA but did not dare to go through the very powerful but notalways- fully-documented environment.\" ~Marek Brabec, ISCB News Paula Moraga is a Lecturer in the Department of Mathematical Sciences at the University of Bath. She received her Master’s in Biostatistics from Harvard University and her Ph.D. in Statistics from the University of Valencia. Dr. Moraga develops innovative statistical methods and open-source software for disease surveillance including R packages for spatio-temporal modeling, detection of clusters, and travel-related spread of disease. Her work has directly informed strategic policy in reducing the burden of diseases such as malaria and cancer in several countries.

Dengue is one of the major hurdles to the public health in Sri Lanka, causing high morbidity and mortality. The present study focuses on the use of geographical information systems (GIS) to map and evaluate the spatial and temporal distribution of dengue in Sri Lanka from 2009 to 2014 and to elucidate the association of climatic factors with dengue incidence. Epidemiological, population and meteorological data were collected from the Epidemiology Unit, Department of Census and Statistics and the Department of Meteorology of Sri Lanka. Data were analyzed using SPSS (Version 20, 2011) and R studio (2012) and the maps were generated using Arc GIS 10.2. The dengue incidence showed a significant positive correlation with rainfall (p<0.0001). No positive correlation was observed between dengue incidence and temperature (p = 0.107) or humidity (p = 0.084). Rainfall prior to 2 and 5 months and a rise in the temperature prior to 9 months positively correlated with dengue incidence as based on the auto-correlation values. A rise in humidity prior to 1 month had a mild positive correlation with dengue incidence. However, a rise in humidity prior to 9 months had a significant negative correlation with dengue incidence based on the auto-correlation values. Remote sensing and GIS technologies give near real time utility of climatic data together with the past dengue incidence for the prediction of dengue outbreaks. In that regard, GIS will be applicable in outbreak predictions including prompt identification of locations with dengue incidence and forecasting future risks and thus direct control measures to minimize major outbreaks.

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.

Background Community- associated methicillin resistant Staphylococcus aureus (CA-MRSA) cause serious infections and rates continue to rise worldwide. Use of geocoded electronic health record (EHR) data to prevent spread of disease is limited in health service research. We demonstrate how geocoded EHR and spatial analyses can be used to identify risks for CA-MRSA in children, which are tied to place-based determinants and would not be uncovered using traditional EHR data analyses. Methods An epidemiology study was conducted on children from January 1, 2002 through December 31, 2010 who were treated for Staphylococcus aureus infections. A generalized estimated equations (GEE) model was developed and crude and adjusted odds ratios were based on S. aureus risks. We measured the risk of S. aureus as standardized incidence ratios (SIR) calculated within aggregated US 2010 Census tracts called spatially adaptive filters, and then created maps that differentiate the geographic patterns of antibiotic resistant and non-resistant forms of S. aureus . Results CA-MRSA rates increased at higher rates compared to non-resistant forms, p  = 0.01. Children with no or public health insurance had higher odds of CA-MRSA infection. Black children were almost 1.5 times as likely as white children to have CA-MRSA infections (aOR 95% CI 1.44,1.75, p  < 0.0001); this finding persisted at the block group level ( p  < 0.001) along with household crowding (p < 0.001). The youngest category of age (< 4 years) also had increased risk for CA-MRSA (aOR 1.65, 95%CI 1.48, 1.83, p < 0.0001). CA-MRSA encompasses larger areas with higher SIRs compared to non-resistant forms and were found in block groups with higher proportion of blacks ( r  = 0.517, p < 0.001), younger age ( r  = 0.137, p < 0.001), and crowding ( r  = 0.320, p < 0.001). Conclusions In the Atlanta MSA, the risk for CA-MRSA is associated with neighborhood-level measures of racial composition, household crowding, and age of children. Neighborhoods which have higher proportion of blacks, household crowding, and children < 4 years of age are at greatest risk. Understanding spatial relationship at a community level and how it relates to risks for antibiotic resistant infections is important to combat the growing numbers and spread of such infections like CA-MRSA.

We implement a high-resolution visualization of the medical knowledge domain using the self-organizing map (SOM) method, based on a corpus of over two million publications. While self-organizing maps have been used for document visualization for some time, (1) little is known about how to deal with truly large document collections in conjunction with a large number of SOM neurons, (2) post-training geometric and semiotic transformations of the SOM tend to be limited, and (3) no user studies have been conducted with domain experts to validate the utility and readability of the resulting visualizations. Our study makes key contributions to all of these issues. Documents extracted from Medline and Scopus are analyzed on the basis of indexer-assigned MeSH terms. Initial dimensionality is reduced to include only the top 10% most frequent terms and the resulting document vectors are then used to train a large SOM consisting of over 75,000 neurons. The resulting two-dimensional model of the high-dimensional input space is then transformed into a large-format map by using geographic information system (GIS) techniques and cartographic design principles. This map is then annotated and evaluated by ten experts stemming from the biomedical and other domains. Study results demonstrate that it is possible to transform a very large document corpus into a map that is visually engaging and conceptually stimulating to subject experts from both inside and outside of the particular knowledge domain. The challenges of dealing with a truly large corpus come to the fore and require embracing parallelization and use of supercomputing resources to solve otherwise intractable computational tasks. Among the envisaged future efforts are the creation of a highly interactive interface and the elaboration of the notion of this map of medicine acting as a base map, onto which other knowledge artifacts could be overlaid.

China is the largest developing country with a relatively developed public health system. To further prevent and eliminate the spread of infectious diseases, China has listed 39 notifiable infectious diseases characterized by wide prevalence or great harm, and classified them into classes A, B, and C, with severity decreasing across classes. Class A diseases have been almost eradicated in China, thus making class B diseases a priority in infectious disease prevention and control. In this retrospective study, we analyze the spatial distribution patterns of 12 class B notifiable infectious diseases that remain active all over China. Global and local Moran's I and corresponding graphic tools are adopted to explore and visualize the global and local spatial distribution of the incidence of the selected epidemics, respectively. Inter-correlations of clustering patterns of each pair of diseases and a cumulative summary of the high/low cluster frequency of the provincial units are also provided by means of figures and maps. Of the 12 most commonly notifiable class B infectious diseases, viral hepatitis and tuberculosis show high incidence rates and account for more than half of the reported cases. Almost all the diseases, except pertussis, exhibit positive spatial autocorrelation at the provincial level. All diseases feature varying spatial concentrations. Nevertheless, associations exist between spatial distribution patterns, with some provincial units displaying the same type of cluster features for two or more infectious diseases. Overall, high-low (unit with high incidence surrounded by units with high incidence, the same below) and high-high spatial cluster areas tend to be prevalent in the provincial units located in western and southwest China, whereas low-low and low-high spatial cluster areas abound in provincial units in north and east China. Despite the various distribution patterns of 12 class B notifiable infectious diseases, certain similarities between their spatial distributions are present. Substantial evidence is available to support disease-specific, location-specific, and disease-combined interventions. Regarding provinces that show high-high/high-low patterns of multiple diseases, comprehensive interventions targeting different diseases should be established. As to the adjacent provincial units revealing similar patterns, coordinated actions need to be taken across borders.

Prevention quality indicators (PQIs) constitute a set of measures that can be combined with hospital inpatient data to identify the quality of care for ambulatory care sensitive conditions (ACSC). Geographical information system (GIS) web mapping and applications contribute to a better representation of PQI spatial distribution. Unlike many countries in the world, in Portugal, this type of application remains underdeveloped. The main objective of this work was to facilitate the assessment of geographical patterns and trends of health data in Portugal. Therefore, two innovative open source applications were developed. Leaflet Javascript Library, PostGIS, and GeoServer were used to create a web map application prototype. Python language was used to develop the GIS application. The geospatial assessment of geographical patterns of health data in Portugal can be obtained through a GIS application and a web map application. Both tools proposed allowed for an easy and intuitive assessment of geographical patterns and time trends of PQI values in Portugal, alongside other relevant health data, i.e., the location of health care facilities, which, in turn, showed some association between the location of facilities and quality of health care. However, in the future, more research is still required to map other relevant data, for more in-depth analyses.

Despite availability of valuable ecological data in published thematic maps, manual methods to transfer published maps to a more accessible digital format are time-intensive. Application of object-based image analysis makes digitization faster. Using object-based image analysis followed by random forests classification, we rapidly digitized choropleth maps of white-tailed deer ( ) densities in the conterminous US during 1982 and 2001 to 2005 (hereafter, 2003), allowing access to deer density information stored in images. The digitization process took about one day each per deer density map, of which about two hours was computer processing time, which will differ due to factors such as resolution and number of objects. Deer were present in 4.75 million km (60% of the area) and 5.56 million km (70%) during 1982 and 2003, respectively. Population and density in areas with deer presence were 17.15 million and 3.6 deer/km during 1982 and 29.93 million and 5.4 deer/km during 2003. Greatest densities were 7.2 deer/km in Georgia during 1982 and 14.6 deer/km in Wisconsin during 2003. Six states had deer densities ≥9.8 deer/km during 2003. Colorado, Idaho, and Oregon had greatest increases in population and area of deer presence, and deer expansion is likely to continue into western states. Error in these estimates may be similar to error resulting from differential reporting by state agencies. Deer densities likely are within historical levels in most of the US. This method rapidly reclaimed informational value of deer density maps, enabling greater analysis, and similarly may be applied to digitize a variety of published maps to geographic information system layers, which permit greater analysis.

Landscape structure in the Eastern US experienced great changes in the last century with the expansion of forest cover into abandoned agricultural land and the clearing of secondary forest cover for urban development. In this paper, the spatial and temporal patterns of forest cover from 1914 to 2004 in the Gwynns Falls watershed in Baltimore, Maryland were quantified from historic maps and aerial photographs. Using a database of forest patches from six times—1914, 1938, 1957, 1971, 1999, and 2004—we found that forest cover changed, both temporally and spatially. While total forest area remained essentially constant, turnover in forest cover was very substantial. Less than 20% of initial forest cover remained unchanged. Forest cover became increasingly fragmented as the number, size, shape, and spatial distribution of forest patches within the watershed changed greatly. Forest patch change was also analyzed within 3-km distance bands extending from the urban core to the more suburban end of the watershed. This analysis showed that, over time, the location of high rates of forest cover change shifted from urban to suburban bands which coincides with the spatial shift of urbanization. Forest cover tended to be more stable in and near the urban center, whereas forest cover changed more in areas where urbanization was still in process. These results may have critical implications for the ecological functioning of forest patches and underscore the need to integrate multi-temporal data layers to investigate the spatial pattern of forest cover and the temporal variations of that spatial pattern.