Load packages and data

library(inTextSummaryTable)
library(clinUtils)
library(pander)
library(tools) # toTitleCase

# load example data
data(dataADaMCDISCP01)

dataAll <- dataADaMCDISCP01
labelVars <- attr(dataAll, "labelVars")

This section creates example data sets used below.

dataAE <-  subset(dataAll$ADAE, SAFFL == "Y" & TRTEMFL == "Y")
dataAEInterest <- subset(dataAE, AESOC %in% c(
        "INFECTIONS AND INFESTATIONS",
        "GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS"
    )
)

# ensure that order of elements is the one specified in 
# the corresponding numeric variable
dataAEInterest$TRTA <- reorder(dataAEInterest$TRTA, dataAEInterest$TRTAN)
dataAEInterest$AESEV <- factor(dataAEInterest$AESEV, levels = c("MILD", "MODERATE"))

dataTotalAE <- subset(dataAll$ADSL, TRT01A != "Placebo")
# should contain columns specified in 'colVar'
dataTotalAE$TRTA <- dataTotalAE$TRT01A 

Output formats

The default exported format is flextable, which is suitable for Word/PowerPoint documents.

Alternatively, a table can be exported as datatable interactive table for html reports, or as a data frame in R.

The outputType parameter specifies the output format of the summary statistics table.

summaryTableFt <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects in the data; n = number of subjects with observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    outputType = "flextable"
)
class(summaryTableFt)

## [1] "flextable"

summaryTableFt

getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects with data; n = number of subjects with this observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)")
)

getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects with data; n = number of subjects with this observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    style = "presentation"
)

getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects in the data; n = number of subjects with observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    outputType = "DT",
    ## DT-specific options
    buttons = c() # remove all export buttons
)

summaryTable <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects in the data; n = number of subjects with observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    style = "presentation",
    outputType = "data.frame"
)
pander(summaryTable, split.table = Inf)

summaryTableAll <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term",
    footer = c(
        "N = number of subjects in the data; n = number of subjects with observation",
        paste("Denominator for percentage calculations is the total number of subjects",
            "per treatment group in the safety population"
        )
    ),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    style = "presentation",
    outputType = "data.frame-base"
)
pander(summaryTableAll, split.table = Inf)

Custom aesthetics

The inTextSummaryTable contains functionalities to set the aesthetics of the tables.

Those aesthetics are set through global options.

This has the main advantage that if you wish to change the default color scheme, it is possible to set your preferences only once at the beginning of the R script or Rmd document.

When loading the package, the global options for palettes get automatically defined into the R session. If you wish to change the default colors, you can apply your preferences by changing the global options.

The inTextSummaryTable package has the following options for table aesthetics:

• inTextSummaryTable.colors.table.presentation

• inTextSummaryTable.pageDim.presentation

The first option sets custom colors for a table in a presentation mode, the last one defines the page dimension of a Powerpoint when exporting a table.

Note that the options have to be defined after loading the package. This because when loading the package, the default global options for palettes will overwrite the custom palettes.

# create named vector
customColorTable <- c(
    # black text in the header
    'header' = "#000000",
    # green background in the header
    'headerBackground' = "#74D055FF",
    # black text in the body
    'body' = "#000000", 
    # yellow background for all rows
    'bodyBackground1' = "#FDE725FF",
    'bodyBackground2' = "#FDE725FF",
    # black footer
    'footer' = "#000000",
    # white footer background
    'footerBackground' = "#FFFFFF",
    # black line for footer
    'line' = "#000000"
)
# set options
options(inTextSummaryTable.colors.table.presentation = customColorTable)
# create the table on a dummy data set
getSummaryStatisticsTable(
    data = data.frame(USUBJID = c(1, 2)),
    style = "presentation" 
)

# set custom dimension of page for presentation
# in this example, the dimension is the widescreen size
pageDimCustom <- c(7.5, 13.32)
options(inTextSummaryTable.pageDim.presentation = pageDimCustom)
getOption("inTextSummaryTable.pageDim.presentation")

## [1]  7.50 13.32

vignette("inTextSummaryTable-aesthetics", "inTextSummaryTable")

options(inTextSummaryTable.colors.table.presentation = tableColorsPresentation)

Export table to a separated file

The table can be exported to a different file by specifying a file name in the file parameter.

Possible formats are:

• txt: the raw base table is exported to a text file. This format can be used e.g. to run quality checks with reference Table/Listings/Figures.
• docx: the formatted table is exported to a Word document. Such format is typically of interest to share the tables to medical writers, to be imported directly into a Statistical Analysis Plan (if style = 'report').
• html: an interactive table is exported to the specified html file

# export table to a Word document
summaryTableFt <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    file = file.path("tables_CSR", "summaryTable-AEs.docx")
)

# export interactive table to a html document
summaryTableFt <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    file = file.path("tables_CSR", "summaryTable-AEs.html")
)

# export table in raw format to a text file
summaryTableFt <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    file = file.path("tables_CSR", "summaryTable-AEs.txt")
)

# export to multiple formats at once
summaryTableFt <- getSummaryStatisticsTable(
    data = dataAEInterest,
    rowVar = c("AESOC", "AEDECOD"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    dataTotal = dataTotalAE,
    labelVars = labelVars,
    file = file.path("tables_CSR",
        c("summaryTable.txt", "summaryTable.docx", "summaryTable.html")
    )
)

Export table of pre-computed summary statistics

To create a table in a similar format as the in-text tables created by the package, from pre-computed summary statistics (e.g. from CRO or from a different software as SAS) the function exportSummaryStatisticsTable can be used.

This function takes as input a data.frame in long format that should contain the summary statistics.

The long format should be such that the

• statistic value (statsVar)
• statistic type (if multiple), grouping row and columns (rowVar and colVar)

are both stored as different columns in the data.frame.

If the column headers should contain total number of subjects, the corresponding counts should be stored in records with the column isTotal set to TRUE.

dataDIABP <- subset(
    dataAll$ADVS, 
    SAFFL == "Y" & ANL01FL == "Y" &
    PARAMCD == "DIABP" & 
    AVISIT %in% c("Baseline", "Week 6") &
    ATPT == "AFTER LYING DOWN FOR 5 MINUTES"
)

# create example of data.frame containing statistics of interest
statsEff <- sapply(c("AVAL", "CHG"), function(var) {
      
      getStats(
          type = c("n", "mean (se)", "median (range)"),
          x = dataDIABP[[var]]
      )
      
    }, simplify = FALSE)

summaryTable <- computeSummaryStatisticsTable(
    data = dataDIABP,
    colVar = c("TRTP", "AVISIT"),
    var = c("AVAL", "CHG"), varGeneralLab = "",
    stats = statsEff,
    labelVars = labelVars
)

# format df with statistics to in-text table format
export(
    summaryTable = summaryTable,
    statsVar = c("n", "Mean (SE)", "Median (range)"),
    rowVar = "variable", rowVarLab = "Statistic",
    colVar = c("TRTP", "AVISIT"),
    colHeaderTotalInclude = TRUE,
    labelVars = simpleCap(tolower(labelVars[c("AVAL", "CHG")])),
    title = toTitleCase(
        "Table: Diastolic Blood Pressure (mmHg) statistics"
    )
)

Text formatting

Specific formatted text can be specified for the flextable output type only.

dataSL <- subset(dataAll$ADSL, SAFFL == "Y")

varsSL <- c("AGE", "WEIGHTBL", "BMIBL")
labelVars[varsSL] <- c(
    "Age",
    "Weight_{t}",
    "BMI (kg/m^{2})"
)

getSummaryStatisticsTable(
    data = dataSL, 
    var = varsSL,  
    stats = getStats("n (%"),
    labelVars = labelVars,
    fontsize = 16,
    title = toTitleCase("Demographic data (Safety Analysis Set)")
)

getSummaryStatisticsTable(
    data = dataSL, 
    var = varsSL,  
    stats = list(
        expression(paste0(
            ifelse(statMean > statMedian, 
                paste0("bold{", roundHalfUpTextFormat(statMean, 1), "}"), 
                roundHalfUpTextFormat(statMean, 1)
            ), 
            "\n(", 
                roundHalfUpTextFormat(statSE, 2),")")
        )
    ),
    labelVars = labelVars,
    fontsize = 12,
    title = toTitleCase("Demographic data (Safety Analysis Set)")
)

Create multiple tables by a variable

Multiple tables can be created for each element of a variable in the dataset by specifying the name of the variable in the argument byVar.

A list of final summary table can be included into a rmarkdown document with the knitPrintListObjects.

Please note that the following chunk option should be used: results = 'asis'.

For example, AE tables are created for each treatment:

summaryTableList <- getSummaryStatisticsTable(
    data = subset(dataAE, TRTEMFL == "Y"),
    rowVar = c("AESOC", "AEDECOD"),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    colVar = "TRTA",
    byVar = "TRTA",
    stats = getStats("n (%)"),
    labelVars = labelVars,
    title = "Table: Treatment-Emergent adverse events"
)

# print the list of tables in the rmarkdown document
clinUtils::knitPrintListObjects(summaryTableList) 

Listing

Listing in a similar format as the in-text summary table is created via the getListing function.

varsListing <- c(
    "USUBJID", "AEBODSYS", "AEDECOD", "TRTA", 
    "AESEV", "AESER", "ASTDY", "AENDY"
)

dataListing <- subset(dataAE, TRTEMFL == "Y" & AESEV == "SEVERE")
dataListing <- dataListing[, varsListing]
colnames(dataListing) <- getLabelVar(var = varsListing, labelVars = labelVars)

getListing(
    data = dataListing, 
    title = "Listing of treatment-emergent severe adverse events",
    includeRownames = FALSE
)

Filter records in a table

If only a subset of the records should be displayed in the final table, a custom filtering functions is specified via the filterFct parameter.

library(plyr)

# SOC with AE terms with at least 2 subjects
getSummaryStatisticsTable(
    data = subset(dataAE, TRTEMFL == "Y"),
    rowVar = c("AESOC", "AEDECOD"),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    filterFct = function(x)
      ddply(x, "AESOC", function(y)
            if(any(y$statN >= 2))   y           
      ),
    labelVars = labelVars,
    title = paste(
        "Table: Adverse Events by System Organ Class and",
        "Preferred Term with at least 2 patients in System Organ Class"
    )
)

# AE term with at least one term with more than 70% in the treatment
getSummaryStatisticsTable(
    data = subset(dataAE, TRTEMFL == "Y"),
    rowVar = c("AESOC", "AEDECOD"),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    filterFct = function(x)
      ddply(x, "AEDECOD", function(xTerm) {
            if(any(xTerm$statPercN >= 70))  xTerm       
          }),
    labelVars = labelVars,
    title = "Table: Adverse Events by System Organ Class and Preferred Term with at least 70% patients"
)

Note: to help the creation of this filtering function, the displaying data could be extracted first via the computeSummaryStatisticsTable function (instead of creating directly the in-text table via the getSummaryStatisticsTable), and then used to define the filterFct parameter.

x <- computeSummaryStatisticsTable(
    data = subset(dataAE, TRTEMFL == "Y"),
    rowVar = c("AESOC", "AEDECOD"),
    rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term\nn (%)"),
    colVar = "TRTA",
    stats = getStats("n (%)"),
    labelVars = labelVars
)
head(x)

##                                                  AESOC                     AEDECOD    TRTA isTotal statN statm statPercTotalN statPercN    n (%)
## 1                                    CARDIAC DISORDERS       MYOCARDIAL INFARCTION Placebo   FALSE     1     1              2        50 1 (50.0)
## 2                           GASTROINTESTINAL DISORDERS                      NAUSEA Placebo   FALSE     0     0              2         0        0
## 3 GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS APPLICATION SITE DERMATITIS Placebo   FALSE     0     0              2         0        0
## 4 GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS   APPLICATION SITE ERYTHEMA Placebo   FALSE     0     0              2         0        0
## 5 GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS APPLICATION SITE IRRITATION Placebo   FALSE     0     0              2         0        0
## 6 GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS   APPLICATION SITE PRURITUS Placebo   FALSE     0     0              2         0        0

# for specific AEDECOD
xTerm <- subset(x, AEDECOD == "MYOCARDIAL INFARCTION")
# identify the record for treated patient:
subset(xTerm, grepl("Placebo", TRTA))

##               AESOC               AEDECOD    TRTA isTotal statN statm statPercTotalN statPercN    n (%)
## 1 CARDIAC DISORDERS MYOCARDIAL INFARCTION Placebo   FALSE     1     1              2        50 1 (50.0)

# keep all records (placebo + treatment) if percentage if higher than 20%:
# if no 'else' condition, nothing (NULL) is returned:
if(subset(xTerm, grepl("Placebo", TRTA))$statPercN >= 20)   xTerm

##                AESOC               AEDECOD                 TRTA isTotal statN statm statPercTotalN statPercN    n (%)
## 1  CARDIAC DISORDERS MYOCARDIAL INFARCTION              Placebo   FALSE     1     1              2        50 1 (50.0)
## 33 CARDIAC DISORDERS MYOCARDIAL INFARCTION Xanomeline High Dose   FALSE     0     0              3         0        0
## 65 CARDIAC DISORDERS MYOCARDIAL INFARCTION  Xanomeline Low Dose   FALSE     0     0              2         0        0

# across all AE terms:
ddply(x, "AEDECOD", function(xTerm)
      if(subset(xTerm, grepl("Placebo", TRTA))$statPercN >= 20) xTerm
)

##                   AESOC               AEDECOD                 TRTA isTotal statN statm statPercTotalN statPercN    n (%)
## 1 PSYCHIATRIC DISORDERS     COMPLETED SUICIDE              Placebo   FALSE     1     1              2        50 1 (50.0)
## 2 PSYCHIATRIC DISORDERS     COMPLETED SUICIDE Xanomeline High Dose   FALSE     0     0              3         0        0
## 3 PSYCHIATRIC DISORDERS     COMPLETED SUICIDE  Xanomeline Low Dose   FALSE     0     0              2         0        0
## 4     CARDIAC DISORDERS MYOCARDIAL INFARCTION              Placebo   FALSE     1     1              2        50 1 (50.0)
## 5     CARDIAC DISORDERS MYOCARDIAL INFARCTION Xanomeline High Dose   FALSE     0     0              3         0        0
## 6     CARDIAC DISORDERS MYOCARDIAL INFARCTION  Xanomeline Low Dose   FALSE     0     0              2         0        0
## 7                  <NA>                  <NA>              Placebo    TRUE     2     2              2       100  2 (100)
## 8                  <NA>                  <NA> Xanomeline High Dose    TRUE     3    30              3       100  3 (100)
## 9                  <NA>                  <NA>  Xanomeline Low Dose    TRUE     2    22              2       100  2 (100)

# format it as a function and pass it to the 'filterFct' parameter

Appendix