1st Edition

Geospatial Health Data Modeling and Visualization with R-INLA and Shiny

By Paula Moraga Copyright 2020
    294 Pages
    by Chapman & Hall

    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

    Biography

    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.

    "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