PSI Conference 2026 Presentation Code

Fast, Fresh & Interactive: R Dashboards for Statisticians in 30 Minutes or Less!
Conference
Author

PSI AIMS

Published

June 16, 2026

Setup

Package Installation

install.packages("tibble", type = "binary")
install.packages("dplyr", type = "binary")
install.packages("ggplot2", type = "binary")
install.packages("plotly", type = "binary")
install.packages("DT", type = "binary")
install.packages("htmlwidgets", type = "binary")
install.packages("pharmaverseadamjnj")

Package Load

library(dplyr)
library(ggplot2)
library(plotly)
library(DT)
library(htmlwidgets)
library(pharmaverseadamjnj)

Read in ADSL and carry out some data preparation

adsl <- pharmaverseadamjnj::adsl

adsl2 <- adsl %>%
  select(USUBJID, TRT01P, TRTDURD, WEIGHTBL, HEIGHTBL) %>%
  filter(!is.na(TRT01P) & !is.na(TRTDURD))

adsl3 <- adsl2 %>%
  mutate_if(is.character, as.factor)

tf_colors <- c(
  "Placebo" = "#0072B2",
  "Xanomeline High Dose" = "#D55E00",
  "Xanomeline Low Dose" = "#CC79A7"
)

Recipe 1: Make A Figure Interactive

Boxplot: Create The Static Figure

f1 <- ggplot(data = adsl3, aes(x = TRT01P, y = TRTDURD, fill = TRT01P)) +
  geom_boxplot() +
  scale_x_discrete(name = "Treatment Group") +
  scale_y_continuous(
    limits = c(0, 250),
    breaks = seq(0, 250, 50),
    expand = c(0.05, 0.05),
    name = "Treatment Duration (Days)"
  ) +
  scale_fill_manual(
    values = tf_colors,
    name = "Treatment Group"
  )

Boxplot: Make It Interactive

g1 <- ggplotly(f1)

saveWidget(g1, file.path("interactive-outputs", "boxplotly.html"), selfcontained = TRUE)

Open the interactive boxplot

Scatterplot: Create The Static Figure

f2 <- ggplot(data = adsl3, aes(x = HEIGHTBL, y = WEIGHTBL, shape = TRT01P, colour = TRT01P)) +
  geom_point() +
  scale_x_continuous(
    limits = c(0, 150),
    breaks = seq(0, 150, 10),
    name = "Baseline Height (cm)"
  ) +
  scale_y_continuous(
    limits = c(0, 150),
    breaks = seq(0, 150, 10),
    name = "Baseline Weight (kg)"
  ) +
  scale_shape_manual(
    values = c(16, 17, 15),
    name = "Treatment Group"
  ) +
  scale_colour_manual(
    values = tf_colors,
    name = "Treatment Group"
  )

Scatterplot: Make It Interactive

g2 <- ggplotly(f2)

saveWidget(g2, file.path("interactive-outputs", "scatterplotly.html"), selfcontained = TRUE)

Open the interactive scatterplot

Recipe 2: Make A Table Explorable

Prepare The Table

my_table <- adsl3

my_table_2 <- my_table %>%
  rename(
    "Unique Subject Identifier" = USUBJID,
    "Treatment Group" = TRT01P,
    "Total Treatment Duration (Days)" = TRTDURD,
    "Baseline Weight (kg)" = WEIGHTBL,
    "Baseline Height (cm)" = HEIGHTBL
  )

Make It Interactive

d <- datatable(
  my_table_2,
  extensions = c("ColReorder"),
  rownames = FALSE,
  filter = "top",
  class = "stripe hover compact",
  options = list(
    colReorder = TRUE,
    pageLength = 5,
    lengthMenu = c(5, 10, 12, 20, 50, 100)
  )
)

saveWidget(d, file.path("interactive-outputs", "datatable.html"), selfcontained = TRUE)

Open the interactive table

Recipe 3: Bring Outputs Together

Open the Quarto dashboard

Full Code

# PSI Conf 2026 interactivity recipes

install.packages("tibble", type = "binary")
install.packages("dplyr", type = "binary")
install.packages("ggplot2", type = "binary")
install.packages("plotly", type = "binary")
install.packages("DT", type = "binary")
install.packages("htmlwidgets", type = "binary")
install.packages("pharmaverseadamjnj")

library(dplyr)
library(ggplot2)
library(plotly)
library(DT)
library(htmlwidgets)
library(pharmaverseadamjnj)


# Data --------------------------------------------------------------------

adsl <- pharmaverseadamjnj::adsl

adsl2 <- adsl %>%
  select(USUBJID, TRT01P, TRTDURD, WEIGHTBL, HEIGHTBL) %>%
  filter(!is.na(TRT01P) & !is.na(TRTDURD))

adsl3 <- adsl2 %>%
  mutate_if(is.character, as.factor)

tf_colors <- c(
  "Placebo" = "#0072B2",
  "Xanomeline High Dose" = "#D55E00",
  "Xanomeline Low Dose" = "#CC79A7"
)


# Recipe 1: Make a figure interactive ------------------------------------

f1 <- ggplot(data = adsl3, aes(x = TRT01P, y = TRTDURD, fill = TRT01P)) +
  geom_boxplot() +
  scale_x_discrete(name = "Treatment Group") +
  scale_y_continuous(
    limits = c(0, 250),
    breaks = seq(0, 250, 50),
    expand = c(0.05, 0.05),
    name = "Treatment Duration (Days)"
  ) +
  scale_fill_manual(
    values = tf_colors,
    name = "Treatment Group"
  )

g1 <- ggplotly(f1)

saveWidget(g1, file.path("interactive-outputs", "boxplotly.html"), selfcontained = TRUE)


f2 <- ggplot(data = adsl3, aes(x = HEIGHTBL, y = WEIGHTBL, shape = TRT01P, colour = TRT01P)) +
  geom_point() +
  scale_x_continuous(
    limits = c(0, 150),
    breaks = seq(0, 150, 10),
    name = "Baseline Height (cm)"
  ) +
  scale_y_continuous(
    limits = c(0, 150),
    breaks = seq(0, 150, 10),
    name = "Baseline Weight (kg)"
  ) +
  scale_shape_manual(
    values = c(16, 17, 15),
    name = "Treatment Group"
  ) +
  scale_colour_manual(
    values = tf_colors,
    name = "Treatment Group"
  )

g2 <- ggplotly(f2)

saveWidget(g2, file.path("interactive-outputs", "scatterplotly.html"), selfcontained = TRUE)


# Recipe 2: Make a table explorable --------------------------------------

my_table <- adsl3

my_table_2 <- my_table %>%
  rename(
    "Unique Subject Identifier" = USUBJID,
    "Treatment Group" = TRT01P,
    "Total Treatment Duration (Days)" = TRTDURD,
    "Baseline Weight (kg)" = WEIGHTBL,
    "Baseline Height (cm)" = HEIGHTBL
  )

d <- datatable(
  my_table_2,
  extensions = c("ColReorder"),
  rownames = FALSE,
  filter = "top",
  class = "stripe hover compact",
  options = list(
    colReorder = TRUE,
    pageLength = 5,
    lengthMenu = c(5, 10, 12, 20, 50, 100)
  )
)

saveWidget(d, file.path("interactive-outputs", "datatable.html"), selfcontained = TRUE)