Subject disposition

inTextSummaryTable

 # data of interest
data_in <- dataAll$ADSL

varDMFL <- grep("FL$", colnames(data_in), value = TRUE)
varDMFLLabel <- sub(" Flag$", "", labelVars[varDMFL])

getSummaryStatisticsTable(
    data = data_in,
    var = varDMFL, varFlag = varDMFL, varGeneralLab = "Analysis Set, N", 
    varLab = varDMFLLabel,
    stats = getStats("n (%)"),
    colVar = "TRT01P",
    labelVars = labelVars,
    colTotalInclude = TRUE, colTotalLab = "All subjects",
    varInclude0 = TRUE,
    title = tools::toTitleCase("Table: subject disposition")
    # file = file.path("tables_CSR", "Table_subjectDisposition.docx")
)

Table: Subject Disposition
Analysis Set, N	Placebo (N=2)	Xanomeline High Dose (N=3)	Xanomeline Low Dose (N=2)	All subjects (N=7)
Safety Population	2 (100)	3 (100)	2 (100)	7 (100)
Intent-to-Treat Population	2 (100)	3 (100)	2 (100)	7 (100)
Efficacy Population	1 (50.0)	3 (100)	2 (100)	6 (85.7)
Completers of Week 8 Population	1 (50.0)	3 (100)	2 (100)	6 (85.7)
Completers of Week 16 Population	1 (50.0)	1 (33.3)	1 (50.0)	3 (42.9)
Completers of Week 24 Population	1 (50.0)	1 (33.3)	1 (50.0)	3 (42.9)
Did the Subject Discontinue the Study?	2 (100)	2 (66.7)	1 (50.0)	5 (71.4)
Discontinued due to AE?	0	1 (33.3)	0	1 (14.3)
Subject Died?	2 (100)	0	1 (50.0)	3 (42.9)

gtsummary

data_in <- dataAll$ADSL

# Identify flag variables ending in "FL"
varDMFL <- grep("FL$", colnames(data_in), value = TRUE)

# Get label replacements: named list of formulas
varDMFLLabel <- setNames(
  sub(" Flag$", "", labelVars[varDMFL]),
  varDMFL
)
label_list <- map2(varDMFL, varDMFLLabel, ~ as.formula(paste0(.x, ' ~ "', .y, '"')))

# Optional: Ensure all flag variables are factors
data_in[varDMFL] <- lapply(data_in[varDMFL], factor)

# Generate the table
data_in %>%
  select(TRT01P, all_of(varDMFL)) %>%
  tbl_summary(
    by = TRT01P,
    type = all_of(varDMFL) ~ "categorical",
    statistic = all_categorical() ~ "{n} ({p}%)",
    label = label_list,
    missing = "no"
  ) %>%
  add_overall(last = TRUE, col_label = "All subjects") %>%
  modify_caption("**Table: Subject Disposition**")

**Table: Subject Disposition**
Characteristic	Placebo N = 2¹	Xanomeline High Dose N = 3¹	Xanomeline Low Dose N = 2¹	All subjects¹
Safety Population
Y	2 (100%)	3 (100%)	2 (100%)	7 (100%)
Intent-to-Treat Population
Y	2 (100%)	3 (100%)	2 (100%)	7 (100%)
Efficacy Population
N	1 (50%)	0 (0%)	0 (0%)	1 (14%)
Y	1 (50%)	3 (100%)	2 (100%)	6 (86%)
Completers of Week 8 Population
N	1 (50%)	0 (0%)	0 (0%)	1 (14%)
Y	1 (50%)	3 (100%)	2 (100%)	6 (86%)
Completers of Week 16 Population
N	1 (50%)	2 (67%)	1 (50%)	4 (57%)
Y	1 (50%)	1 (33%)	1 (50%)	3 (43%)
Completers of Week 24 Population
N	1 (50%)	2 (67%)	1 (50%)	4 (57%)
Y	1 (50%)	1 (33%)	1 (50%)	3 (43%)
Did the Subject Discontinue the Study?
	0 (0%)	1 (33%)	1 (50%)	2 (29%)
Y	2 (100%)	2 (67%)	1 (50%)	5 (71%)
Discontinued due to AE?
	2 (100%)	2 (67%)	2 (100%)	6 (86%)
Y	0 (0%)	1 (33%)	0 (0%)	1 (14%)
Subject Died?
	0 (0%)	3 (100%)	1 (50%)	4 (57%)
Y	2 (100%)	0 (0%)	1 (50%)	3 (43%)
¹ n (%)

Demographics

inTextSummaryTable

# data of interest
data_in <- subset(dataAll$ADSL, SAFFL == "Y")

# variables of interest
# Note: if available: ethnicity is included
varsDM <- c(
  "SEX", "AGE", "AGEGR1",
  "RACE", "ETHNIC",
  "HEIGHTBL", "WEIGHTBL", 
  "BMIBL", "BMIBLGR1"
)

# Sort variables according to corresponding numeric variable
data_in$AGEGR1 <- with(data_in, reorder(AGEGR1, AGEGR1N))
data_in$RACE <- with(data_in, reorder(RACE, RACEN))
data_in$TRT01P <- with(data_in, reorder(TRT01P, TRT01PN))

## Define set of statistics of interest:
statsDM <- getStatsData(
  data = data_in, var = varsDM,
  # different for continuous and categorical variable
  # type = c(cont = "median (range)", cat = "n (%)"),
  type = c(cont = "n", cont = "mean (sd)",cont = "median\n(range)", 
         cat = "n (%)"),
  # for categorical variable, statistic name (here: 'n (%)')
  # should not be included in the table
  args = list(cat = list(includeName = FALSE))
)

## create the table:

getSummaryStatisticsTable(
  data = data_in, 
  # variables to summarize
  var = varsDM, 
  varGeneralLab = "Parameter",
  # column
  colVar = "TRT01P", colTotalInclude = TRUE, colTotalLab = "All subjects",
  # statistics
  stats = statsDM,
  statsGeneralLab = "",
  labelVars = labelVars,
  # if only one category, should be included in separated row (e.g. RACE: White)
  rowAutoMerge = FALSE,
  rowInclude0 = FALSE, emptyValue = 0,
  title = tools::toTitleCase("Table: Demographic Data (safety Analysis Set)")
  # file = file.path("tables_CSR", "Table_demographicData.docx")
)

Table: Demographic Data (Safety Analysis Set)
Parameter	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)	All subjects (N=7)
Variable group	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)	All subjects (N=7)
Sex
F	1 (50.0)	2 (100)	2 (66.7)	5 (71.4)
M	1 (50.0)	0	1 (33.3)	2 (28.6)
Age
n	2	2	3	7
Mean (SD)	82.0 (9.9)	78.0 (2.8)	66.7 (8.7)	74.3 (9.8)
Median (range)	82.0 (75,89)	78.0 (76,80)	69.0 (57,74)	75.0 (57,89)
Pooled Age Group 1
<65	0	0	1 (33.3)	1 (14.3)
65-80	1 (50.0)	2 (100)	2 (66.7)	5 (71.4)
>80	1 (50.0)	0	0	1 (14.3)
Race
WHITE	2 (100)	2 (100)	2 (66.7)	6 (85.7)
BLACK OR AFRICAN AMERICAN	0	0	1 (33.3)	1 (14.3)
Ethnicity
NOT HISPANIC OR LATINO	2 (100)	2 (100)	3 (100)	7 (100)
Baseline Height (cm)
n	2	2	3	7
Mean (SD)	167.65 (14.35)	155.55 (6.29)	163.00 (10.83)	162.20 (10.25)
Median (range)	167.65 (157.5,177.8)	155.55 (151.1,160.0)	158.80 (154.9,175.3)	158.80 (151.1,177.8)
Baseline Weight (kg)
n	2	2	3	7
Mean (SD)	59.65 (17.61)	54.45 (12.80)	68.50 (17.77)	61.96 (15.04)
Median (range)	59.65 (47.2,72.1)	54.45 (45.4,63.5)	66.70 (51.7,87.1)	63.50 (45.4,87.1)
Baseline BMI (kg/m^2)
n	2	2	3	7
Mean (SD)	20.90 (2.69)	22.75 (7.14)	25.53 (4.37)	23.41 (4.53)
Median (range)	20.90 (19.0,22.8)	22.75 (17.7,27.8)	27.80 (20.5,28.3)	22.80 (17.7,28.3)
Pooled Baseline BMI Group 1
<25	2 (100)	1 (50.0)	1 (33.3)	4 (57.1)
25-<30	0	1 (50.0)	2 (66.7)	3 (42.9)

gtsummary

# Subset Safety Analysis Set
data_in <- subset(dataAll$ADSL, SAFFL == "Y")

# Variables of interest
varsDM <- c(
  "SEX", "AGE", "AGEGR1",
  "RACE", "ETHNIC",
  "HEIGHTBL", "WEIGHTBL", 
  "BMIBL", "BMIBLGR1"
)

# Reorder factor levels
data_in <- data_in %>%
  mutate(
    AGEGR1 = fct_reorder(AGEGR1, AGEGR1N),
    RACE = fct_reorder(RACE, RACEN),
    TRT01P = fct_reorder(TRT01P, TRT01PN)
  )

# Identify variable types
cont_vars <- varsDM[sapply(data_in[varsDM], is.numeric)]
cat_vars  <- setdiff(varsDM, cont_vars)

# Format type list
type_list <- c(
  lapply(cont_vars, function(x) as.formula(paste0(x, " ~ 'continuous2'"))),
  lapply(cat_vars,  function(x) as.formula(paste0(x, " ~ 'categorical'")))
)

# Format label list
label_list <- lapply(varsDM, function(x) {
  lbl <- labelVars[[x]]
  if (is.null(lbl)) lbl <- x
  as.formula(paste0(x, " ~ '", lbl, "'"))
})

# Build table
tbl <- data_in %>%
  select(all_of(c("TRT01P", varsDM))) %>%
  tbl_summary(
    by = TRT01P,
    type = type_list,
    statistic = list(
      all_continuous2() ~ c("Mean (SD)" = "{mean} ({sd})",
                            "Median" = "{median} ",
                            "(Min - Max)" = "({min} - {max})"),
      all_categorical() ~ "{n} ({p}%)"
    ),
    label = label_list,
    missing = "no"
  ) %>%
  add_overall(last = TRUE, col_label = "All subjects") %>%
  modify_caption("**Table: Demographic Data (Safety Analysis Set)**") %>%
  bold_labels()

tbl

**Table: Demographic Data (Safety Analysis Set)**
Characteristic	Placebo N = 2¹	Xanomeline Low Dose N = 2¹	Xanomeline High Dose N = 3¹	All subjects¹
Sex
F	1 (50%)	2 (100%)	2 (67%)	5 (71%)
M	1 (50%)	0 (0%)	1 (33%)	2 (29%)
Age
Mean (SD)	82 (10)	78 (3)	67 (9)	74 (10)
Median	82	78	69	75
(Min - Max)	(75 - 89)	(76 - 80)	(57 - 74)	(57 - 89)
Pooled Age Group 1
<65	0 (0%)	0 (0%)	1 (33%)	1 (14%)
65-80	1 (50%)	2 (100%)	2 (67%)	5 (71%)
>80	1 (50%)	0 (0%)	0 (0%)	1 (14%)
Race
WHITE	2 (100%)	2 (100%)	2 (67%)	6 (86%)
BLACK OR AFRICAN AMERICAN	0 (0%)	0 (0%)	1 (33%)	1 (14%)
Ethnicity
NOT HISPANIC OR LATINO	2 (100%)	2 (100%)	3 (100%)	7 (100%)
Baseline Height (cm)
Mean (SD)	168 (14)	156 (6)	163 (11)	162 (10)
Median	168	156	159	159
(Min - Max)	(158 - 178)	(151 - 160)	(155 - 175)	(151 - 178)
Baseline Weight (kg)
Mean (SD)	60 (18)	54 (13)	69 (18)	62 (15)
Median	60	54	67	64
(Min - Max)	(47 - 72)	(45 - 64)	(52 - 87)	(45 - 87)
Baseline BMI (kg/m^2)
Mean (SD)	20.9 (2.7)	22.8 (7.1)	25.5 (4.4)	23.4 (4.5)
Median	20.9	22.8	27.8	22.8
(Min - Max)	(19.0 - 22.8)	(17.7 - 27.8)	(20.5 - 28.3)	(17.7 - 28.3)
Pooled Baseline BMI Group 1
<25	2 (100%)	1 (50%)	1 (33%)	4 (57%)
25-<30	0 (0%)	1 (50%)	2 (67%)	3 (43%)
¹ n (%)

Baseline disease characteristics

inTextSummaryTable

# data of interest
data_in <- subset(dataAll$ADSL, SAFFL == "Y")

# create table
getSummaryStatisticsTable(
    data = data_in,
    var = c("DURDIS", "EDUCLVL"), varGeneralLab = "Parameter", 
    colVar = "TRT01P", colTotalInclude = TRUE, colTotalLab = "All subjects",
    stats = getStats("median\n(range)"), statsGeneralLab = "",
    rowAutoMerge = FALSE,
    labelVars = labelVars,
    title = tools::toTitleCase("Table: Baseline Disease Characteristics (safety analysis set)")
    # file = file.path("tables_CSR", "Table_BaselineCharacteristics.docx")
)

Table: Baseline Disease Characteristics (Safety Analysis Set)
Parameter	Placebo (N=2)	Xanomeline High Dose (N=3)	Xanomeline Low Dose (N=2)	All subjects (N=7)
Duration of Disease (Months)	20.65 (17.6,23.7)	31.4 (2.2,32.1)	35.6 (31.4,39.8)	31.4 (2.2,39.8)
Years of Education	13 (12,14)	15 (10,16)	12 (12,12)	12 (10,16)

gtsummary

# Subset data
data_in <- subset(dataAll$ADSL, SAFFL == "Y")

# Variables of interest
vars <- c("DURDIS", "EDUCLVL")

# Identify variable types
cont_vars <- vars[sapply(data_in[vars], is.numeric)]
cat_vars <- setdiff(vars, cont_vars)

# Set types: "continuous2" for median + range on separate row
type_list <- c(
  lapply(cont_vars, function(x) as.formula(paste0(x, " ~ 'continuous2'"))),
  lapply(cat_vars, function(x) as.formula(paste0(x, " ~ 'categorical'")))
)

# Set labels
label_list <- lapply(vars, function(x) {
  lbl <- labelVars[[x]]
  if (is.null(lbl)) lbl <- x
  as.formula(paste0(x, " ~ '", lbl, "'"))
})

# Create table
tbl <- data_in %>%
  select(all_of(c("TRT01P", vars))) %>%
  tbl_summary(
    by = TRT01P,
    type = type_list,
    statistic = list(
      all_continuous2() ~ c("Mean (SD)" = "{mean} ({sd})",
                            "Median" = "{median} ",
                            "(Min - Max)" = "({min} - {max})"),
      all_categorical() ~ "{n} ({p}%)"
    ),
    label = label_list,
    missing = "no"
  ) %>%
  add_overall(last = TRUE, col_label = "All subjects") %>%
  modify_caption("**Table: Baseline Disease Characteristics (Safety Analysis Set)**") %>%
  bold_labels()

# View the table
tbl

**Table: Baseline Disease Characteristics (Safety Analysis Set)**
Characteristic	Placebo N = 2	Xanomeline High Dose N = 3	Xanomeline Low Dose N = 2	All subjects
Duration of Disease (Months)
Mean (SD)	21 (4)	22 (17)	36 (6)	25 (12)
Median	21	31	36	31
(Min - Max)	(18 - 24)	(2 - 32)	(31 - 40)	(2 - 40)
Years of Education
Mean (SD)	13.00 (1.41)	13.67 (3.21)	12.00 (0.00)	13.00 (2.08)
Median	13.00	15.00	12.00	12.00
(Min - Max)	(12.00 - 14.00)	(10.00 - 16.00)	(12.00 - 12.00)	(10.00 - 16.00)

Medical History and Concomitant Diseases

inTextSummaryTable

data_in <- subset(dataAll$ADCM, SAFFL == "Y")

# sort variable according to corresponding numeric variables
data_in$TRTA <- with(data_in, reorder(TRTA, TRTAN))

# Terms should be in lower-case
data_in$CMDECOD <- simpleCap(tolower(data_in$CMDECOD))
data_in$CMCLAS <- simpleCap(tolower(data_in$CMCLAS))
        
getSummaryStatisticsTable(
    data = data_in,
    colVar = "TRTA", colTotalInclude = TRUE, colTotalLab = "All subjects",
    rowVar = c("CMCLAS", "CMDECOD"), 
    # include total across generic terms and across ATC4 classes
    rowVarTotalInclude = c("CMCLAS", "CMDECOD"), 
    rowTotalLab = "Any prior and concomitant medication",
    stats = getStats("n (%)"),
    # sort rows based on counts of subjects in the total column 
    rowOrder = "total",
    labelVars = labelVars,
    emptyValue = 0,
    title = tools::toTitleCase(paste("Prior and concomitant therapies",
        "by medication class and generic term (safety analyis set)"
    ))
    # file = file.path("tables_CSR", "Table_CM.docx")
)

Prior and Concomitant Therapies by Medication Class and Generic Term (Safety Analyis Set)
Medication Class	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=1)	All subjects (N=3)
Standardized Medication Name	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=1)	All subjects (N=3)
Any prior and concomitant medication	2 (100)	1 (100)	3 (100)
Systemic hormonal preparations, excl.	2 (100)	1 (100)	3 (100)
Hydrocortisone	2 (100)	1 (100)	3 (100)
Uncoded	2 (100)	1 (100)	3 (100)
Uncoded	2 (100)	1 (100)	3 (100)
Respiratory system	1 (50.0)	0	1 (33.3)
Salbutamol sulfate	1 (50.0)	0	1 (33.3)

Reference

inTextSummaryTable: Creation of in-Text Summary Table

Disposition and Baseline

Subject disposition

inTextSummaryTable

gtsummary

Demographics

inTextSummaryTable

gtsummary

Baseline disease characteristics

inTextSummaryTable

gtsummary

Medical History and Concomitant Diseases

inTextSummaryTable

Reference