Two Decades of TB Deaths: Diverging Trends

Proportional facet heights (ggh4x), rounded bars (ggchicklet), and smart labels (ggstream) applied to WHO tuberculosis mortality data.

#TidyTuesday
Author

Aditya Dahiya

Published

November 16, 2025

About the Data

This dataset contains global tuberculosis (TB) burden estimates from the World Health Organization (WHO), curated through the getTBinR R package by Sam Abbott. The data provides country-level indicators spanning multiple years, including TB incidence rates, mortality estimates (both overall and stratified by HIV status), case detection rates, and population figures. Each observation is identified by standardized ISO country codes and organized by WHO region. According to WHO estimates, tuberculosis remains one of the world’s deadliest infectious diseases, with 10.6 million people falling ill with TB in 2021 and 1.6 million deaths from the disease. This dataset was contributed by Darakhshan Nehal as part of the #TidyTuesday project, a weekly data visualization challenge organized by the R4DS Online Learning Community. The data enables researchers, public health professionals, and data enthusiasts to analyze TB burden patterns, track case detection rates, and understand the intersection of TB and HIV across different regions and time periods.

Figure 1: Annual tuberculosis mortality visualized through stacked rounded bars (ggchicklet), with fill colors distinguishing WHO regions. Facet panels use proportional heights (ggh4x::facet_grid2()) reflecting the stark difference between non-HIV (top) and HIV-related (bottom) death tolls. Dynamic labels (ggstream::geom_stream_label()) are sized by regional total deaths over the period. X-axis shows years (2000-2022), Y-axis represents absolute death counts. Data sourced from WHO via Sam Abbott’s getTBinR R package, demonstrating advanced ggplot2 techniques for multi-faceted temporal comparisons.

How I Made This Graphic

.

Loading required libraries

Code 
pacman::p_load(
  tidyverse, # All things tidy

  scales, # Nice Scales for ggplot2
  fontawesome, # Icons display in ggplot2
  ggtext, # Markdown text support for ggplot2
  showtext, # Display fonts in ggplot2
  colorspace, # Lighten and Darken colours

  patchwork,  # Composing Plots
  ggh4x,      # Proportional facets
  ggchicklet, # Rounded bars
  ggstream   # Labels in stacked bar chart
)

who_tb_data <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-11-11/who_tb_data.csv')

Visualization Parameters

Code 
# Font for titles
font_add_google("Saira",
  family = "title_font"
)

# Font for the caption
font_add_google("Saira Condensed",
  family = "body_font"
)

# Font for plot text
font_add_google("Saira Extra Condensed",
  family = "caption_font"
)

showtext_auto()

# A base Colour
bg_col <- "white"
seecolor::print_color(bg_col)

# Colour for highlighted text
text_hil <- "grey40"
seecolor::print_color(text_hil)

# Colour for the text
text_col <- "grey30"
seecolor::print_color(text_col)

line_col <- "grey30"

# Define Base Text Size
bts <- 80

mypal <- paletteer::paletteer_d("ggthemes::excel_Ion") |> 
  as.character() |> 
  str_sub(1, 7)

# Caption stuff for the plot
sysfonts::font_add(
  family = "Font Awesome 6 Brands",
  regular = here::here("docs", "Font Awesome 6 Brands-Regular-400.otf")
)
github <- "&#xf09b"
github_username <- "aditya-dahiya"
xtwitter <- "&#xe61b"
xtwitter_username <- "@adityadahiyaias"
social_caption_1 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{github};</span> <span style='color: {text_hil}'>{github_username}  </span>")
social_caption_2 <- glue::glue("<span style='font-family:\"Font Awesome 6 Brands\";'>{xtwitter};</span> <span style='color: {text_hil}'>{xtwitter_username}</span>")
plot_caption <- paste0(
  "**Data:**  World Health Organization, {getTBinR} by Sam Abbott",
  " |  **Code:** ",
  social_caption_1,
  " |  **Graphics:** ",
  social_caption_2
)
rm(
  github, github_username, xtwitter,
  xtwitter_username, social_caption_1,
  social_caption_2
)

# Add text to plot-------------------------------------------------
plot_title <- "HIV-TB Deaths Plummet, Non-HIV Cases Persist"

plot_subtitle <- "Between 2000 and 2022, global tuberculosis mortality declined substantially, with HIV-related TB deaths falling dramatically from 800,000 to under 200,000 annually. However, non-HIV TB deaths decreased more gradually from 1.9 million to 1.1 million. Africa and South-East Asia shoulder the greatest burden, particularly for HIV-associated cases. While medical advances have transformed HIV-TB outcomes, persistent non-HIV mortality signals ongoing public health challenges requiring sustained intervention." |> str_wrap(120)

plot_subtitle |> str_view()

Exploratory Data Analysis and Wrangling

Code 
# pacman::p_load(summarytools)
# 
# who_tb_data |> 
#   dfSummary() |> 
#   view()
# 
# pacman::p_unload(summarytools)

# Create df1 with selected columns
# df1 <- who_tb_data |> 
#   select(
#     country,
#     year,
#     iso2,
#     g_whoregion,
#     pop = e_pop_num,
#     tb_deaths_total = e_mort_num,
#     tb_deaths_hiv = e_mort_tbhiv_num,
#     tb_deaths_non_hiv = e_mort_exc_tbhiv_num
#   )
# Check if the numbers add up
# df1 |> 
#   mutate(
#     calculated_total = tb_deaths_hiv + tb_deaths_non_hiv,
#     difference = tb_deaths_total - calculated_total,
#     # Check if difference is less than 100 (for rounding and estimation errors)
#     matches = abs(difference) < 100 
#   ) |> 
#   count(matches)

# Seems okay for estimation

# Create df1 and pivot longer
df1_long <- who_tb_data |>
  select(
    country,
    year,
    region = g_whoregion,
    tb_deaths_hiv = e_mort_tbhiv_num,
    tb_deaths_non_hiv = e_mort_exc_tbhiv_num
  ) |>
  pivot_longer(
    cols = c(tb_deaths_hiv, tb_deaths_non_hiv),
    names_to = "death_type",
    values_to = "cases"
  ) |>
  mutate(
    death_type_label = if_else(death_type == "tb_deaths_hiv", 
                                "HIV-related TB Deaths", 
                                "Non-HIV TB Deaths"),
    death_type_label = factor(death_type_label, 
                              levels = c("Non-HIV TB Deaths", "HIV-related TB Deaths"))
  ) |>
  filter(!is.na(cases)) |>
  group_by(year, region, death_type_label) |>
  summarise(cases = sum(cases, na.rm = TRUE), .groups = "drop")

# Calculate total cases by region for label sizing
region_totals <- df1_long |>
  group_by(region, death_type_label) |>
  summarise(total_cases = sum(cases, na.rm = TRUE), .groups = "drop")

# Add region totals to df1_long
df1_long <- df1_long |>
  left_join(region_totals)



# -------------------------------------------------------------------------------------------------
library(ggh4x)  # install with: install.packages("ggh4x")

# Create labels data for facet titles inside plot
facet_labels <- df1_long |>
  group_by(year, death_type_label) |> 
  summarise(
    cases = sum(cases, na.rm = TRUE)
  ) |> 
  group_by(death_type_label) |> 
  summarise(
    x = max(year, na.rm = TRUE),
    y = max(cases, na.rm = TRUE) * 0.95,  # 95% of max y value
    .groups = "drop"
  )

The Plot

Code 
g <- ggplot(df1_long, aes(x = year, y = cases)) +
  ggchicklet::geom_chicklet(
    mapping = aes(fill = region),
    position = "stack",
    alpha = 0.5
  ) +
  ggstream::geom_stream_label(
    mapping = aes(
      label = region,
      size = total_cases,
      colour = region,
      fill = region
    ),
    type = "ridge",
    hjust = "inward",
    check_overlap = TRUE,
    family = "body_font",
    fontface = "bold"
  ) +
  scale_size_continuous(
    range = c(bts / 4, bts / 1.5)
  ) +
  scale_fill_manual(values = mypal) +
  scale_colour_manual(values = darken(mypal, 0.1)) +
  
  # Using facet_grid2 (for proportional heights of facets)
  ggh4x::facet_grid2(
    death_type_label ~ ., 
    scales = "free_y", 
    space = "free_y"
    ) +
  geom_text(
    data = facet_labels,
    mapping = aes(x = x, y = y, label = death_type_label),
    hjust = 1,
    vjust = 1,
    fontface = "bold",
    size = bts * 0.75,
    inherit.aes = FALSE,
    colour = text_hil
    ) +
  labs(
    title = plot_title,
    subtitle = plot_subtitle,
    caption = plot_caption,
    x = "Year",
    y = "Estimated Annual Tuberculosis Deaths (Absolute Count)",
    fill = "WHO Region"
  ) +
  scale_y_continuous(
    labels = scales::label_number(
      scale_cut = cut_short_scale(),
      big.mark = ","
    ),
    expand = expansion(0)
  ) +
  scale_x_continuous(
    expand = expansion(0.015)
  ) +
  coord_cartesian(
    clip = "off"
  ) +
  theme_minimal(
    base_family = "body_font",
    base_size = bts
  ) +
  theme(
    legend.position = "none",
    
    # Overall
    text = element_text(
      margin = margin(0, 0, 0, 0, "mm"),
      colour = text_col,
      lineheight = 0.3
    ),
    
    # Axes
    axis.text.x.bottom = element_text(
      margin = margin(4,0,0,0, "mm")
    ),
    axis.title.x.bottom = element_text(
      margin = margin(0,0,0,0, "mm")
    ),
    axis.text.y.left = element_text(
      size = bts,
      margin = margin(0,4,0,0, "mm")
    ),
    axis.title.y.left = element_text(
      margin = margin(0,0,0,0, "mm")
    ),
    axis.ticks.x.bottom = element_blank(),
    axis.ticks.length.x = unit(0, "mm"),
    axis.ticks.length.y.left = unit(0, "mm"),
    axis.line = element_line(
      arrow = arrow(
        length = unit(5, "mm")
      ),
      linewidth = 0.5,
      colour = text_col
    ),
    panel.grid = element_blank(),
    panel.grid.major.y = element_line(
      linetype = 3,
      linewidth = 0.6,
      colour = text_hil
    ),
    panel.grid.minor.y = element_line(
      linetype = 3,
      linewidth = 0.3,
      colour = text_hil
    ),
    strip.text = element_blank(),
    
    # Labels and Strip Text
    plot.title = element_text(
      margin = margin(5, 0, 5, 0, "mm"),
      hjust = 0.5,
      vjust = 0.5,
      colour = text_hil,
      size = 2.3 * bts,
      family = "body_font",
      face = "bold",
      lineheight = 0.25
    ),
    plot.subtitle = element_text(
      margin = margin(2, 0, 5, 0, "mm"),
      vjust = 0.5,
      colour = text_hil,
      size = bts,
      hjust = 0.5,
      family = "body_font",
      lineheight = 0.3
    ),
    plot.caption = element_markdown(
      family = "caption_font",
      hjust = 0.5,
      margin = margin(5,0,0,0, "mm"),
      colour = text_hil
    ),
    plot.caption.position = "plot",
    plot.title.position = "plot",
    plot.margin = margin(5, 5, 5, 5, "mm")
  )

ggsave(
  filename = here::here(
    "data_vizs",
    "tidy_who_tb_burden.png"
  ),
  plot = g,
  width = 400,
  height = 500,
  units = "mm",
  bg = bg_col
)

Savings the thumbnail for the webpage

Code 
# Saving a thumbnail

library(magick)

# Saving a thumbnail for the webpage
image_read(here::here(
  "data_vizs",
  "tidy_who_tb_burden.png"
)) |>
  image_resize(geometry = "x400") |>
  image_write(
    here::here(
      "data_vizs",
      "thumbnails",
      "tidy_who_tb_burden.png"
    )
  )

Session Info

Code 
pacman::p_load(
  tidyverse, # All things tidy

  scales, # Nice Scales for ggplot2
  fontawesome, # Icons display in ggplot2
  ggtext, # Markdown text support for ggplot2
  showtext, # Display fonts in ggplot2
  colorspace, # Lighten and Darken colours

  patchwork,  # Composing Plots
  ggh4x,      # Proportional facets
  ggchicklet, # Rounded bars
  ggstream   # Labels in stacked bar chart
)

sessioninfo::session_info()$packages |>
  as_tibble() |>
  
  # The attached column is TRUE for packages that were 
  # explicitly loaded with library()
  dplyr::filter(attached == TRUE) |>
  dplyr::select(package,
    version = loadedversion,
    date, source
  ) |>
  dplyr::arrange(package) |>
  janitor::clean_names(
    case = "title"
  ) |>
  gt::gt() |>
  gt::opt_interactive(
    use_search = TRUE
  ) |>
  gtExtras::gt_theme_espn()
Table 1: R Packages and their versions used in the creation of this page and graphics

Links