Basic (GEE)

# Load necessary libraries
library(NBDCtools)    # ABCD data access helper
library(arrow)        # Read Parquet files
library(tidyverse)    # Data wrangling & visualization
library(gtsummary)    # Summary tables
library(rstatix)      # Statistical tests in tidy format
library(geepack)      # Generalized Estimating Equations (GEE) analysis
library(ggeffects)    # Extract & visualize model predictions
library(broom)      # Organizing model outputs

### Load harmonized ABCD data required for this analysis
requested_vars <- c(
    "ab_g_dyn__design_site",
    "ab_g_stc__design_id__fam",
    "ph_p_sds__dims_001"
)

data_dir <- Sys.getenv("ABCD_DATA_PATH", "/path/to/abcd/6_0/phenotype")

abcd_data <- create_dataset(
  dir_data = data_dir,
  study = "abcd",
  vars = requested_vars,
  release = "6.0",
  format = "parquet",
  categ_to_factor = TRUE,   # Convert categorical variables to factors
  value_to_na = TRUE,        # Convert missing codes (222, 333, etc.) to NA
  add_labels = TRUE          # Add variable and value labels
)

# Data wrangling: clean, restructure, and recode sleep variable
df_long <- abcd_data %>%
  filter(session_id %in% c("ses-00A", "ses-01A", "ses-02A", "ses-03A")) %>%  # Keep Baseline - Year 3
  arrange(participant_id, session_id) %>%
   mutate(
    participant_id = factor(participant_id), # Convert participant_id to a factor
    session_id = factor(session_id,
                        levels = c("ses-00A", "ses-01A", "ses-02A", "ses-03A"),
                        labels = c("Baseline", "Year_1", "Year_2", "Year_3")),  # Label sessions

    ab_g_dyn__design_site = factor(ab_g_dyn__design_site),  # Convert site to a factor
    ab_g_stc__design_id__fam = factor(ab_g_stc__design_id__fam), # Convert family id to a factor
    ph_p_sds__dims_001 = as.numeric(ph_p_sds__dims_001)  # Convert to numeric
  ) %>%
  filter(ph_p_sds__dims_001 != 999) %>%  # Remove "Don't know" responses
  mutate(
    # Original coding: 1=9-11hrs (sufficient), 2=<9hrs, 3=>11hrs (both insufficient)
    sleep_binary = ifelse(ph_p_sds__dims_001 == 1, 1, 0)  # Recode: 9-11 hrs = 1, others = 0
  ) %>%
  rename(  # Rename for simplicity
    site = ab_g_dyn__design_site,
    family_id = ab_g_stc__design_id__fam,
  ) %>%
  drop_na()  # Remove missing values

# Summarize 'sleep_binary' across session_ids
descriptives_table <- df_long %>%
    select(session_id, sleep_binary) %>%
    tbl_summary(
        by = session_id,
        missing = "no",
        label = list(sleep_binary ~ "Sufficient Sleep (9-11 hrs)"),
        statistic = list(
            all_categorical() ~ "{n} ({p}%)"  # Count & percentage
        )
    ) %>%
    modify_header(all_stat_cols() ~ "**{level}**<br>N = {n}") %>%
    modify_spanning_header(all_stat_cols() ~ "**Assessment Wave**") %>%
    bold_labels() %>%
    italicize_levels()

### Apply compact styling
theme_gtsummary_compact()

descriptives_table <- as_gt(descriptives_table)

### Save the table as HTML
gt::gtsave(descriptives_table, filename = "descriptives_table.html")

### Print the table
descriptives_table

# Fit GEE model: Predicting sufficient sleep over time
# Site is included to adjust for potential clustering and recruitment differences across ABCD study sites
model <- geeglm(sleep_binary ~ session_id + site,
  id = participant_id,
  data = df_long,
  family = binomial(link = "logit"),
  corstr = "exchangeable"
)

# Generate summary table
model_summary_table <- gtsummary::tbl_regression(model,
  digits = 3,
  intercept = TRUE
) %>%
  gtsummary::as_gt()

model_summary_table

# Save as standalone HTML
gt::gtsave(
  data = model_summary_table,
  filename = "model_summary.html",
  inline_css = FALSE
)

# Create GEE diagnostics data
diagnostics_data <- data.frame(
  Characteristic = c(
    "Correlation Structure",
    "Correlation Parameter (α)",
    "Scale Parameter",
    "Number of Participants",
    "Total Observations"
  ),
  Value = c(
    model$corstr,
    round(model$geese$alpha, 3),
    round(summary(model)$dispersion$Estimate, 3),
    length(unique(df_long$participant_id)),
    nrow(df_long)
  )
)

# Format diagnostics table
diagnostics_table <- diagnostics_data %>%
  gt::gt() %>%
  gt::tab_header(title = "GEE Model Diagnostics")

diagnostics_table

# Save diagnostics table
gt::gtsave(diagnostics_table, filename = "model_diagnostics.html")

# Generate predicted probabilities from the GEE model
preds <- ggeffect(model, terms = "session_id")

# Plot predicted probabilities with confidence intervals
visualization <- ggplot(preds, aes(x = x, y = predicted)) +
  geom_point(size = 3, color = "blue") +
  geom_line(group = 1, color = "blue") +
  geom_errorbar(aes(ymin = conf.low, ymax = conf.high), width = 0.2) +
  labs(title = "Predicted Probability of 9-11 Hours of Sleep Over Time",
       x = "Assessment Wave",
       y = "Predicted Probability of Sufficient Sleep") +
  theme_minimal()

  ggsave(
  filename = "visualization.png",
  plot = visualization,
  width = 8, height = 6, dpi = 300
)