Creation of standard in-text tables with the inTextSummaryTable package

1 Introduction

    library(clinUtils)
    library(tools)# toTitleCase
    library(plyr) # for ddply, rbind.fill
    library(pander) # for session info
    library(inTextSummaryTable)

1.1 Data format

The package is demonstrated with a subset of the ADaM datasets from the CDISC Pilot 01 dataset, available in the clinUtils package.

    # load example data
    library(clinUtils)

    # load example data
    data(dataADaMCDISCP01)

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

Typical in-text table for the CSR are included in the following sections.

Please note that the table content e.g. variables, statistics of interest depends strongly on the study at hand and personal preferences.

2 Subject information

2.1 Subject disposition

    # data of interest
    dataDM <- dataAll$ADSL
    
    varDMFL <- grep("FL$", colnames(dataDM), value = TRUE)
    varDMFLLabel <- sub(" Flag$", "", labelVars[varDMFL])
    
    getSummaryStatisticsTable(
        data = dataDM,
        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 = 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)

2.2 Demographics

    # data of interest
    dataDM <- 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
    dataDM$AGEGR1 <- with(dataDM, reorder(AGEGR1, AGEGR1N))
    dataDM$RACE <- with(dataDM, reorder(RACE, RACEN))
    dataDM$TRT01P <- with(dataDM, reorder(TRT01P, TRT01PN))
    
    ## Define set of statistics of interest:
    statsDM <- getStatsData(
        data = dataDM, var = varsDM,
        # different for continuous and categorical variable
        type = c(cont = "median (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 = dataDM, 
        # 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 = 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
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
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)
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)
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)
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-<30	0	1 (50.0)	2 (66.7)	3 (42.9)
<25	2 (100)	1 (50.0)	1 (33.3)	4 (57.1)

2.3 Baseline disease characteristics

Please note that the content of the table strongly depends on the study.

    # data of interest
    dataBDC <- subset(dataAll$ADSL, SAFFL == "Y")
    
    # create table
    getSummaryStatisticsTable(
        data = dataBDC,
        var = c("DURDIS", "EDUCLVL"), varGeneralLab = "Parameter", 
        colVar = "TRT01P", colTotalInclude = TRUE, colTotalLab = "All subjects",
        stats = getStats("median\n(range)"), statsGeneralLab = "",
        rowAutoMerge = FALSE,
        labelVars = labelVars,
        title = 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)

2.4 Medical History and Concomitant Diseases

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

    # sort variable according to corresponding numeric variables
    dataCM$TRTA <- with(dataCM, reorder(TRTA, TRTAN))
    
    # Terms should be in lower-case
    dataCM$CMDECOD <- simpleCap(tolower(dataCM$CMDECOD))
    dataCM$CMCLAS <- simpleCap(tolower(dataCM$CMCLAS))
            
    getSummaryStatisticsTable(
        data = dataCM,
        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 = 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
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)

3 Efficacy Analyses

The example dataset has has two primary endpoints:

• ADAS-Cog (11), a.k.a Alzheimer’s Disease Assessment Scale - Cognitive Subscale a metric containing 11 items, available in the ADQSADAS dataset
• CIBIC+ score a.k.a Video-referenced Clinician’s Interview-based Impression of Change available in the ADQSCIBC dataset

    dataAdasCog11 <- subset(dataAll$ADQSADAS, PARAMCD == "ACTOT")
    dataCIBIC <- subset(dataAll$ADQSCIBC, PARAMCD == "CIBICVAL")
    
    dataEfficacy <- plyr::rbind.fill(dataAdasCog11, dataCIBIC)
    
    dataEfficacy$TRTP <- with(dataEfficacy, reorder(TRTP, TRTPN))
    dataEfficacy$AVISIT <- with(dataEfficacy, reorder(AVISIT, AVISITN))
    
    stats <- getStatsData(
        data = dataEfficacy, 
        var = c("AVAL", "CHG"), 
        type = c("n", "mean (se)", "median (range)")
    )
    
    getSummaryStatisticsTable(
        data = dataEfficacy,
        rowVar = "PARAM",
        colVar = c("TRTP", "AVISIT"),
        var = c("AVAL", "CHG"), 
        stats = stats,
        labelVars = labelVars,
        title = paste("Table: efficacy endpoints", 
            toTitleCase("actual value and changes from baseline per time point"             
        )),
        file = file.path("tables_CSR", "Table_efficacy.docx")
    )

Table: efficacy endpoints Actual Value and Changes from Baseline per Time Point
Parameter	Placebo				Xanomeline Low Dose				Xanomeline High Dose
Variable
Statistic	Baseline (N=2)	Week 8 (N=2)	Week 16 (N=2)	Week 24 (N=2)	Baseline (N=2)	Week 8 (N=2)	Week 16 (N=2)	Week 24 (N=2)	Baseline (N=3)	Week 8 (N=3)	Week 16 (N=3)	Week 24 (N=3)
Adas-Cog(11) Subscore
Analysis Value
n	2	2	2	2	2	2	2	2	3	3	3	3
Mean (SE)	14.0 (6.00)	16.5 (3.50)	17.5 (2.50)	17.5 (2.50)	32.0 (23.00)	37.0 (25.00)	38.5 (23.50)	37.0 (25.00)	15.7 (6.36)	16.7 (6.36)	15.3 (5.21)	17.7 (5.36)
Median (range)	14.0 (8,20)	16.5 (13,20)	17.5 (15,20)	17.5 (15,20)	32.0 (9,55)	37.0 (12,62)	38.5 (15,62)	37.0 (12,62)	15.0 (5,27)	16.0 (6,28)	16.0 (6,24)	22.0 (7,24)
Change from Baseline
n	-	2	2	2	-	2	2	2	-	3	3	3
Mean (SE)	-	2.5 (2.50)	3.5 (3.50)	3.5 (3.50)	-	5.0 (2.00)	6.5 (0.50)	5.0 (2.00)	-	1.0 (0.00)	-0.3 (1.33)	2.0 (2.89)
Median (range)	-	2.5 (0,5)	3.5 (0,7)	3.5 (0,7)	-	5.0 (3,7)	6.5 (6,7)	5.0 (3,7)	-	1.0 (1,1)	1.0 (-3,1)	2.0 (-3,7)
CIBIC Score
Analysis Value
n	-	1	1	1	-	2	2	2	-	2	3	3
Mean (SE)	-	6.0 ( NA)	5.0 ( NA)	5.0 ( NA)	-	5.0 (0.00)	4.5 (0.50)	4.5 (0.50)	-	4.5 (0.50)	4.0 (0.00)	4.3 (0.33)
Median (range)	-	6.0 (6,6)	5.0 (5,5)	5.0 (5,5)	-	5.0 (5,5)	4.5 (4,5)	4.5 (4,5)	-	4.5 (4,5)	4.0 (4,4)	4.0 (4,5)

4 Safety Analyses

4.1 Adverse Events

4.1.1 Treatment-emergent summary table

    ## data of interest: safety analysis set and treatment-emergent
    dataTEAE <- subset(dataAll$ADAE, SAFFL == "Y" & TRTEMFL == "Y")
    
    # order treatment and severity categories
    dataTEAE$TRTA <- with(dataTEAE, reorder(TRTA, TRTAN))
    
    ## data considered for the total
    dataTotalAE <- subset(dataAll$ADSL, SAFFL == "Y")
    dataTotalAE$TRTA <- with(dataTotalAE, reorder(TRT01A, TRT01AN))
    
    # TEAE with worst intensity
    # build worst-case scenario
    dataTEAE$AESEV <- factor(dataTEAE$AESEV, levels = c("MILD", "MODERATE", "SEVERE"))
    dataTEAE$AESEVN <- as.numeric(dataTEAE$AESEV)
    dataTEAE <- ddply(dataTEAE, c("USUBJID", "TRTA"), function(x)
        cbind.data.frame(x, 
            WORSTINT = with(x, ifelse(AESEVN == max(AESEVN), as.character(AESEV), NA_character_))
    ))
    dataTEAE$WORSTINT <- factor(dataTEAE$WORSTINT, levels = levels(dataTEAE$AESEV))
    
    ## specify labels for each variable:
    varsAE <- c("TRTEMFL", "AESER", "AESDTH", "AEREL")
    
    # create the table
    getSummaryStatisticsTable(
        data = dataTEAE,
        colVar = "TRTA",
        # define variables to compute statistics on
        var = c("TRTEMFL", "AESER", "WORSTINT", "AESDTH", "AEREL"), 
        varFlag = c("TRTEMFL", "AESER", "AESDTH"),
        varLab = c(TRTEMFL = "Treatment-Emergent", WORSTINT = "Worst-case severity:"),
        varGeneralLab = "Subjects with, n(%):",
        # force the inclusion of lines for variable without count:
        varInclude0 = TRUE,
        # include the total for the worst-case scenario
        varTotalInclude = "WORSTINT",
        # statistics:
        stats = getStats('n (%)'),
        emptyValue = "0",
        labelVars = labelVars,
        # dataset used for the total in the header column (and for percentage as default)
        dataTotal = dataTotalAE,
        # title/export
        title = toTitleCase("Table: Summary Table of Treatment-emergent Adverse Events (safety analysis set)"),
        file = file.path("tables_CSR", "Table_TEAE_summary.docx")
    )

Table: Summary Table of Treatment-Emergent Adverse Events (Safety Analysis Set)
Subjects with, n(%):	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)
Variable group
Treatment-Emergent	2 (100)	2 (100)	3 (100)
Serious Event	0	0	1 (33.3)
Worst-case severity:	2 (100)	2 (100)	3 (100)
MILD	0	0	0
MODERATE	0	1 (50.0)	1 (33.3)
SEVERE	2 (100)	1 (50.0)	2 (66.7)
Results in Death	2 (100)	1 (50.0)	0
Causality
NONE	1 (50.0)	2 (100)	3 (100)
POSSIBLE	1 (50.0)	1 (50.0)	2 (66.7)
PROBABLE	0	1 (50.0)	3 (100)
REMOTE	0	0	1 (33.3)

4.1.2 Treatment-emergent incidence table

4.1.2.1 Events occuring in at least one subject

    dataTEAE <- subset(dataAll$ADAE, SAFFL == "Y" & TRTEMFL == "Y")
    
    # order treatment and severity categories
    dataTEAE$TRTA <- with(dataTEAE, reorder(TRTA, TRTAN))
    
    ## data considered for the total
    dataTotalAE <- subset(dataAll$ADSL, SAFFL == "Y")
    dataTotalAE$TRTA <- with(dataTotalAE, reorder(TRT01A, TRT01AN))
    
    getSummaryStatisticsTable(
        data = dataTEAE,
        rowVar = c("AESOC", "AEDECOD"),
        colVar = "TRTA",
        ## total
        # data
        dataTotal = dataTotalAE,
        # row total
        rowVarTotalInclude = c("AESOC", "AEDECOD"), rowTotalLab = "Any TEAE",
        stats = getStats("n (%)"),
        labelVars = labelVars,
        rowVarLab = c('AESOC' = "TEAE by SOC and Preferred Term,\nn (%)"),
        # sort rows based on the total column:
        rowOrder = "total", 
        rowOrderTotalFilterFct = function(x) subset(x, TRTA == "Total"),
        title = paste("Table: Treatment-emergent Adverse Events by System Organ Class",
            "and Preferred Term (Safety Analysis Set)"
        ),
        file = file.path("tables_CSR", "Table_TEAE_SOCPT_atLeast1Subject.docx")
    )

Table: Treatment-emergent Adverse Events by System Organ Class and Preferred Term (Safety Analysis Set)
TEAE by SOC and Preferred Term, n (%)	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)
Dictionary-Derived Term
Any TEAE	2 (100)	2 (100)	3 (100)
GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS	0	2 (100)	3 (100)
APPLICATION SITE PRURITUS	0	2 (100)	2 (66.7)
APPLICATION SITE ERYTHEMA	0	2 (100)	1 (33.3)
APPLICATION SITE IRRITATION	0	1 (50.0)	1 (33.3)
APPLICATION SITE DERMATITIS	0	0	1 (33.3)
FATIGUE	0	0	1 (33.3)
SECRETION DISCHARGE	0	1 (50.0)	0
SUDDEN DEATH	0	1 (50.0)	0
MUSCULOSKELETAL AND CONNECTIVE TISSUE DISORDERS	0	2 (100)	2 (66.7)
BACK PAIN	0	0	1 (33.3)
FLANK PAIN	0	0	1 (33.3)
MUSCULAR WEAKNESS	0	1 (50.0)	0
SHOULDER PAIN	0	1 (50.0)	0
PSYCHIATRIC DISORDERS	1 (50.0)	1 (50.0)	1 (33.3)
COMPLETED SUICIDE	1 (50.0)	0	0
CONFUSIONAL STATE	0	1 (50.0)	0
HALLUCINATION, VISUAL	0	0	1 (33.3)
GASTROINTESTINAL DISORDERS	0	0	2 (66.7)
NAUSEA	0	0	2 (66.7)
INFECTIONS AND INFESTATIONS	0	1 (50.0)	1 (33.3)
LOWER RESPIRATORY TRACT INFECTION	0	0	1 (33.3)
PNEUMONIA	0	1 (50.0)	0
NERVOUS SYSTEM DISORDERS	0	0	2 (66.7)
AMNESIA	0	0	1 (33.3)
LETHARGY	0	0	1 (33.3)
PARTIAL SEIZURES WITH SECONDARY GENERALISATION	0	0	1 (33.3)
RENAL AND URINARY DISORDERS	0	1 (50.0)	1 (33.3)
CALCULUS URETHRAL	0	0	1 (33.3)
INCONTINENCE	0	1 (50.0)	0
RESPIRATORY, THORACIC AND MEDIASTINAL DISORDERS	0	1 (50.0)	1 (33.3)
DYSPNOEA	0	1 (50.0)	0
EPISTAXIS	0	0	1 (33.3)
SKIN AND SUBCUTANEOUS TISSUE DISORDERS	0	1 (50.0)	1 (33.3)
ACTINIC KERATOSIS	0	0	1 (33.3)
ERYTHEMA	0	1 (50.0)	0
CARDIAC DISORDERS	1 (50.0)	0	0
MYOCARDIAL INFARCTION	1 (50.0)	0	0
INJURY, POISONING AND PROCEDURAL COMPLICATIONS	0	1 (50.0)	0
JOINT DISLOCATION	0	1 (50.0)	0
SKIN LACERATION	0	1 (50.0)	0
INVESTIGATIONS	0	1 (50.0)	0
NASAL MUCOSA BIOPSY	0	1 (50.0)	0
METABOLISM AND NUTRITION DISORDERS	0	0	1 (33.3)
DECREASED APPETITE	0	0	1 (33.3)

4.1.2.2 Events occuring in at least 25% of all subjects

    getSummaryStatisticsTable(
        data = dataTEAE,
        rowVar = c("AESOC", "AEDECOD"),
        colVar = "TRTA",
        ## total
        # data
        dataTotal = dataTotalAE, 
        # row total
        rowVarTotalInclude = c("AESOC", "AEDECOD"), rowTotalLab = "Any TEAE",
        stats = getStats("n (%)"),
        labelVars = labelVars,
        rowVarLab = c('AESOC' = "SOC and Preferred Term,\nn (%)"),
        # sort rows based on the total column:
        rowOrder = "total", 
        rowOrderTotalFilterFct = function(x) subset(x, TRTA == "Total"),
        title = paste("Table: Treatment-emergent Adverse Events by System Organ Class",
            "and Preferred Term reported in at least 25% of the subjects",
            "in any treatment group (Safety Analysis Set)"
        ),
        file = file.path("tables_CSR", "Table_TEAE_SOCPT_atLeast25PercentsSubject.docx"),
        # include only events occuring in at least 25% for at least one preferred term:
        filterFct = function(x)
            ddply(x, "AESOC", function(x){ # per AESOC to include the total
                ddply(x, "AEDECOD", function(y){
                    yTotal <- subset(y, grepl("Total", TRTA))
                    if(any(yTotal$statPercN >= 25)) y
                })
            })
    )

Table: Treatment-emergent Adverse Events by System Organ Class and Preferred Term reported in at least 25% of the subjects in any treatment group (Safety Analysis Set)
SOC and Preferred Term, n (%)	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)
Dictionary-Derived Term
Any TEAE	2 (100)	2 (100)	3 (100)
GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS	0	2 (100)	3 (100)
APPLICATION SITE PRURITUS	0	2 (100)	2 (66.7)
APPLICATION SITE ERYTHEMA	0	2 (100)	1 (33.3)
APPLICATION SITE IRRITATION	0	1 (50.0)	1 (33.3)
MUSCULOSKELETAL AND CONNECTIVE TISSUE DISORDERS	0	2 (100)	2 (66.7)
PSYCHIATRIC DISORDERS	1 (50.0)	1 (50.0)	1 (33.3)
GASTROINTESTINAL DISORDERS	0	0	2 (66.7)
NAUSEA	0	0	2 (66.7)
INFECTIONS AND INFESTATIONS	0	1 (50.0)	1 (33.3)
NERVOUS SYSTEM DISORDERS	0	0	2 (66.7)
RENAL AND URINARY DISORDERS	0	1 (50.0)	1 (33.3)
RESPIRATORY, THORACIC AND MEDIASTINAL DISORDERS	0	1 (50.0)	1 (33.3)
SKIN AND SUBCUTANEOUS TISSUE DISORDERS	0	1 (50.0)	1 (33.3)

4.1.3 Treatment-emergent worst-case table

    dataTEAE <- subset(dataAll$ADAE, SAFFL == "Y" & TRTEMFL == "Y")
    
    # order treatment and severity categories
    dataTEAE$TRTA <- with(dataTEAE, reorder(TRTA, TRTAN))
    
    ## data considered for the total
    dataTotalAE <- subset(dataAll$ADSL, SAFFL == "Y")
    dataTotalAE$TRTA <- with(dataTotalAE, reorder(TRT01A, TRT01AN))
    
    # TEAE with worst intensity
    dataTEAE$AESEV <- factor(dataTEAE$AESEV, levels = c("MILD", "MODERATE", "SEVERE"))
    dataTEAE$AESEVN <- as.numeric(dataTEAE$AESEV)
    
    # extract worst-case scenario data (only one record if multiple with same severity)
    dataAEWC <- ddply(dataTEAE, c("AESOC", "AEDECOD", "USUBJID", "TRTA"), function(x){
        x[which.max(x$AESEVN), ]
    })
    # worst-case scenario in lower case
    dataAEWC$WORSTINT <- simpleCap(tolower(dataAEWC$AESEV))
    labelVars["WORSTINT"] <- "Worst-case scenario"

    ## datasets used for the total: 
    # for total: compute worst-case across SOC and across AE term
    # (otherwise patient counted in multiple categories if present different categories for different AEs)
    dataTotalRow <- list(
        # within SOC (across AEDECOD)
        'AEDECOD' = ddply(dataAEWC, c("AESOC", "USUBJID", "TRTA"), function(x){ 
            x[which.max(x$AESEVN), ]
        }),
        # across SOC
        'AESOC' = ddply(dataAEWC, c("USUBJID", "TRTA"), function(x){    
            x[which.max(x$AESEVN), ]
        })
    )
    
    getSummaryStatisticsTable(
        data = dataAEWC,
        ## row variables:
        rowVar = c("AESOC", "AEDECOD", "WORSTINT"), rowVarInSepCol = "WORSTINT",
        # include total across SOC and across AEDECOD
        rowVarTotalInclude = c("AESOC", "AEDECOD"), dataTotalRow = dataTotalRow, 
        rowVarTotalByVar = "WORSTINT", # count for each severity category for the total
        rowTotalLab = "Any TEAE", rowVarLab = c(AESOC = "Subjects with, n(%):", WORSTINT = "Worst-case scenario"),
        # sort per total in the total column
        rowOrder = "total", 
        ## column variables
        colVar = "TRTA", 
        stats = getStats("n (%)"),
        emptyValue = "0",
        labelVars = labelVars,
        dataTotal = dataTotalAE,
        title = toTitleCase(paste("Table: Treatment-emergent Adverse",
            "Events by system organ",
            "and preferred term by worst-case (safety Analysis Set)"
        )),
        file = file.path("tables_CSR", "Table_TEAE_Severity.docx")
    )

Table: Treatment-Emergent Adverse Events by System Organ and Preferred Term by Worst-Case (Safety Analysis Set)
Subjects with, n(%):	Worst-case scenario	Placebo (N=2)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)
Dictionary-Derived Term
Any TEAE	Severe	2 (100)	1 (50.0)	2 (66.7)
	Moderate	0	1 (50.0)	1 (33.3)
GENERAL DISORDERS AND ADMINISTRATION SITE CONDITIONS	Severe	0	1 (50.0)	0
	Moderate	0	0	2 (66.7)
	Mild	0	1 (50.0)	1 (33.3)
APPLICATION SITE PRURITUS	Moderate	0	0	1 (33.3)
	Mild	0	2 (100)	1 (33.3)
APPLICATION SITE ERYTHEMA	Mild	0	2 (100)	1 (33.3)
APPLICATION SITE IRRITATION	Moderate	0	0	1 (33.3)
	Mild	0	1 (50.0)	0
APPLICATION SITE DERMATITIS	Moderate	0	0	1 (33.3)
FATIGUE	Mild	0	0	1 (33.3)
SECRETION DISCHARGE	Mild	0	1 (50.0)	0
SUDDEN DEATH	Severe	0	1 (50.0)	0
MUSCULOSKELETAL AND CONNECTIVE TISSUE DISORDERS	Moderate	0	1 (50.0)	1 (33.3)
	Mild	0	1 (50.0)	1 (33.3)
BACK PAIN	Mild	0	0	1 (33.3)
FLANK PAIN	Moderate	0	0	1 (33.3)
MUSCULAR WEAKNESS	Moderate	0	1 (50.0)	0
SHOULDER PAIN	Mild	0	1 (50.0)	0
PSYCHIATRIC DISORDERS	Severe	1 (50.0)	0	0
	Moderate	0	1 (50.0)	1 (33.3)
COMPLETED SUICIDE	Severe	1 (50.0)	0	0
CONFUSIONAL STATE	Moderate	0	1 (50.0)	0
HALLUCINATION, VISUAL	Moderate	0	0	1 (33.3)
NERVOUS SYSTEM DISORDERS	Severe	0	0	1 (33.3)
	Moderate	0	0	1 (33.3)
AMNESIA	Mild	0	0	1 (33.3)
LETHARGY	Moderate	0	0	1 (33.3)
PARTIAL SEIZURES WITH SECONDARY GENERALISATION	Severe	0	0	1 (33.3)
GASTROINTESTINAL DISORDERS	Severe	0	0	1 (33.3)
	Mild	0	0	1 (33.3)
NAUSEA	Severe	0	0	1 (33.3)
	Mild	0	0	1 (33.3)
INFECTIONS AND INFESTATIONS	Moderate	0	1 (50.0)	1 (33.3)
LOWER RESPIRATORY TRACT INFECTION	Moderate	0	0	1 (33.3)
PNEUMONIA	Moderate	0	1 (50.0)	0
RENAL AND URINARY DISORDERS	Moderate	0	0	1 (33.3)
	Mild	0	1 (50.0)	0
CALCULUS URETHRAL	Moderate	0	0	1 (33.3)
INCONTINENCE	Mild	0	1 (50.0)	0
RESPIRATORY, THORACIC AND MEDIASTINAL DISORDERS	Moderate	0	1 (50.0)	0
	Mild	0	0	1 (33.3)
DYSPNOEA	Moderate	0	1 (50.0)	0
EPISTAXIS	Mild	0	0	1 (33.3)
SKIN AND SUBCUTANEOUS TISSUE DISORDERS	Mild	0	1 (50.0)	1 (33.3)
ACTINIC KERATOSIS	Mild	0	0	1 (33.3)
ERYTHEMA	Mild	0	1 (50.0)	0
INJURY, POISONING AND PROCEDURAL COMPLICATIONS	Moderate	0	1 (50.0)	0
JOINT DISLOCATION	Moderate	0	1 (50.0)	0
SKIN LACERATION	Mild	0	1 (50.0)	0
CARDIAC DISORDERS	Severe	1 (50.0)	0	0
MYOCARDIAL INFARCTION	Severe	1 (50.0)	0	0
INVESTIGATIONS	Mild	0	1 (50.0)	0
NASAL MUCOSA BIOPSY	Mild	0	1 (50.0)	0
METABOLISM AND NUTRITION DISORDERS	Moderate	0	0	1 (33.3)
DECREASED APPETITE	Moderate	0	0	1 (33.3)

4.2 Laboratory safety

4.2.1 Table of laboratory abnormalities

    dataLBAbn <- subset(dataAll$ADLBC, SAFFL == "Y" & LBNRIND != "NORMAL")
    
    dataLBAbn$PARAM <- with(dataLBAbn, reorder(PARAM, PARAMN))
    dataLBAbn$TRTA <- with(dataLBAbn, reorder(TRTA, TRTAN))
    dataLBAbn$LBNRIND <- factor(dataLBAbn$LBNRIND, levels = c("LOW", "HIGH"))

    dataLBAbnTotal <- subset(dataAll$ADSL, SAFFL == "Y")
    dataLBAbnTotal$TRTA <- with(dataLBAbnTotal, reorder(TRT01A, TRT01AN))
    
    getSummaryStatisticsTable(
        data = dataLBAbn,
        rowVar = c("PARCAT1", "PARAM"), 
        rowVarTotalInclude = c("PARCAT1", "PARAM"),
        colVar = "TRTA", 
        var = "LBNRIND", 
        rowVarInSepCol = "variableGroup", varSubgroupLab = "Abnormality",
        rowVarLab = c('PARCAT1' = "Laboratory Parameter\nn (%)"),
        stats = getStats("n (%)"),
        labelVars = labelVars,
        rowOrder = c("PARCAT1" = "total", "PARAM" = "total", "variableGroup" = "auto"),
        dataTotal = dataLBAbnTotal, 
        title = toTitleCase(paste("Table: Treatment-emergent",
            "Worst-case Laboratory Abnormalities (safety analysis set)"
        )),
        emptyValue = "0",
        file = file.path("tables_CSR", "Table_Lab_Severity.docx")
    )

Table: Treatment-Emergent Worst-Case Laboratory Abnormalities (Safety Analysis Set)
Laboratory Parameter n (%)	Abnormality	Placebo (N=2)	Xanomeline Low Dose (N=2)
Parameter
Any Laboratory Parameter n (%), Parameter	LOW	0	2 (100)
	HIGH	2 (100)	2 (100)
CHEM	LOW	0	2 (100)
	HIGH	2 (100)	2 (100)
Alkaline Phosphatase (U/L)	HIGH	0	2 (100)
Albumin (g/L)	LOW	0	2 (100)
Alkaline Phosphatase (U/L) change from previous visit, relative to normal range	HIGH	0	2 (100)
Albumin (g/L) change from previous visit, relative to normal range	LOW	0	2 (100)
Sodium (mmol/L)	LOW	0	1 (50.0)
Bilirubin (umol/L)	HIGH	0	1 (50.0)
Gamma Glutamyl Transferase (U/L)	HIGH	0	1 (50.0)
Alanine Aminotransferase (U/L)	HIGH	1 (50.0)	0
Aspartate Aminotransferase (U/L)	HIGH	1 (50.0)	0
Blood Urea Nitrogen (mmol/L)	HIGH	0	1 (50.0)
Cholesterol (mmol/L)	HIGH	1 (50.0)	0
Creatine Kinase (U/L)	HIGH	1 (50.0)	0
Sodium (mmol/L) change from previous visit, relative to normal range	LOW	0	1 (50.0)
Bilirubin (umol/L) change from previous visit, relative to normal range	HIGH	0	1 (50.0)
Gamma Glutamyl Transferase (U/L) change from previous visit, relative to normal range	HIGH	0	1 (50.0)
Alanine Aminotransferase (U/L) change from previous visit, relative to normal range	HIGH	1 (50.0)	0
Aspartate Aminotransferase (U/L) change from previous visit, relative to normal range	HIGH	1 (50.0)	0
Blood Urea Nitrogen (mmol/L) change from previous visit, relative to normal range	HIGH	0	1 (50.0)
Cholesterol (mmol/L) change from previous visit, relative to normal range	HIGH	1 (50.0)	0
Creatine Kinase (U/L) change from previous visit, relative to normal range	HIGH	1 (50.0)	0

4.3 Electrocardiogram

Please note that there is no ECG dataset in the CDISC Pilot dataset used for the examples, so this table is not effectively created in the vignette.

Nevertheless, an example code is provided below to create a standard table of summary statistics for the ECG parameters.

    # data of interest
    paramsECG <- c("QT", "QTCF", "QRS", "PR", "RR", "EGHR")

    dataECG <- subset(dataAll$ADEG, SAFFL == "Y" & PARAMCD %in% paramsECG)
    dataECG$TRTA <- with(dataECG, reorder(TRTA, TRTAN))
    dataECG$PARAM <- with(dataECG, reorder(PARAM, PARAMN))
    
    # consider all non-missing post-baseline records
    dataECGPostBaseline <- subset(dataECG, 
        AVISIT %in% c("Screening", "Baseline", "Worst-case post-baseline")
    )
    
    # worst-case scenario:
    dataECGWC <- subset(dataECG, AVISIT == "Worst-case post-baseline")
    # treatment-emergent
    dataECGWC$TRTEMFL <- with(dataECGWC, ifelse(BASECAT1 != CHGCAT1, "Y", "N"))
    dataECGWCTE <- subset(dataECGWC, TRTEMFL == "Y")
    dataECGWC <- convertVarToFactor(dataECGWC, 
        var = c("AVALCAT1", "CHGCAT1"), 
        varNum = c("AVALCA1N", "CHGCAT1N")
    )
    
    # create the table
    getSummaryStatisticsTable(
        data = dataECGWC,
        # layout:
        colVar = "TRTA",
        rowVar = "PARAM", rowVarLab = c('PARAM' = "ECG Parameter"),
        # metrics to compute statistics on
        var = c("AVALCAT1", "CHGCAT1"),
        # in a separated column
        rowVarInSepCol = c("variable", "variableGroup"),
        # labels
        varGeneralLab = "Abnormality",
        varSubgroupLab = "Worst-Case Post-Baseline",
        stats = getStats("n (%)"),
        labelVars = labelVars,
        # total: all post-baseline
        dataTotal = dataECGPostBaseline, 
        emptyValue = "0",
        rowVarTotalPerc = "PARAM", # total per parameter
        # ensure that categories are below the type of abnormality
        rowAutoMerge = FALSE,
        # only retain abnormalities:
        filterFct = function(x){
            subset(x, !variableGroup %in% c("<= 450 msec", "<= 30 msec"))
        },
        title = toTitleCase(paste("Table: Treatment-emergent worst-case",
            "ECG abnormalities and change from baseline ECG abnormalities (safety analysis set)"
        )),
        file = file.path("tables_CSR", "Table_ECG.docx")
    )

4.4 Vital signs

4.4.1 Treatment-emergent vital signs abnormalities

    # analyis set and parameters of interest
    dataVS <- subset(dataAll$ADVS, 
        SAFFL == "Y" & ANL01FL == "Y" & VISIT != "BASELINE"
    )
    
    dataVS$PARAM <- with(dataVS, reorder(PARAM, PARAMN))
    dataVS$ANRIND <- with(dataVS, reorder(PARAM, PARAMN))
    dataVS$TRTA <- with(dataVS, reorder(TRTA, TRTAN))
    dataVS$SHIFT1 <- with(dataVS, factor(ifelse(SHIFT1 == "", NA_character_, SHIFT1)))
            
    getSummaryStatisticsTable(
        data = dataVS,
        rowVar = "PARAM", 
        rowVarInSepCol = "variableGroup", 
        rowVarInclude0 = TRUE,
        colVar = "TRTA", 
        var = "SHIFT1", varTotalInclude = TRUE,
        emptyValue = 0,
        stats = getStats("n (%)"),
        rowVarTotalPerc = "PARAM",
        labelVars = labelVars,
        title = toTitleCase(paste("Table: Treatment-emergent Worst-case",
            "Vital Sign Abnormalities (Safety Analysis Set)"
        )),
        file = file.path("tables_CSR", "Table_VitalSigns_Severity.docx")
    )

Table: Treatment-Emergent Worst-Case Vital Sign Abnormalities (Safety Analysis Set)
Parameter	Variable group	Placebo (N=1)	Xanomeline Low Dose (N=2)	Xanomeline High Dose (N=3)
Systolic Blood Pressure (mmHg)	Total	0	0	0
Diastolic Blood Pressure (mmHg)	Total	1 (100)	2 (100)	3 (100)
	High/High	0	0	1 (33.3)
	High/Low	0	0	1 (33.3)
	High/Normal	0	0	1 (33.3)
	Low/Low	0	1 (50.0)	1 (33.3)
	Low/Normal	0	1 (50.0)	2 (66.7)
	Normal/High	0	0	1 (33.3)
	Normal/Low	0	2 (100)	1 (33.3)
	Normal/Normal	1 (100)	2 (100)	3 (100)
Pulse Rate (BEATS/MIN)	Total	0	0	0
Weight (kg)	Total	0	0	0
Temperature (C)	Total	0	0	0

5 Pharmacokinetics analysis

Please note that this example pharmacodynamics dataset contains different subjects than the other datasets used in the vignette.

    paramcdPK <- c("AUCINFO", "CMAX", "TMAX")
    dataPK <- subset(dataAll$ADPP, PKFL == "Y" & PARAMCD %in% paramcdPK)
    
    dataPK$PARCAT1 <- with(dataPK, reorder(PARCAT1, PARCAT1N))
    dataPK$PARAMCD <- with(dataPK, reorder(PARAMCD, PARAMN))
    dataPK$TRTA <- with(dataPK, reorder(TRTA, TRTAN))
    dataPK$PARAMCD <- with(dataPK, reorder(PARAMCD, PARAMN))
    
    # build pretty labels
    labelsPK <- c(
        AUCINFO = "AUC_{Inf,obs}\n(h*ng/mL)",
        CMAX = "C_{max}\n(ng/mL)",
        TMAX = "t_{max}\n(h)"
    )
    dataPK$PARAM <- factor(dataPK$PARAMCD, 
        levels = levels(dataPK$PARAMCD), 
        labels = labelsPK[levels(dataPK$PARAMCD)]
    )
    
    statsPK <- dlply(dataPK, "PARAM", function(dataParam){
        getStatsData(
            data = dataParam,
            var = "AVAL",
            type = "median\n(range)",
            includeName = FALSE
        )[[1]]
    })
    
    getSummaryStatisticsTable(
        data = dataPK,
        rowVar = c("PARCAT1", "PARAM"), colVar = "TRTA",
        var = "AVAL",
#       rowVarLab = c('PARCAT1' = "PK parameters"),
        stats = statsPK, statsVarBy = "PARAM",
        emptyValue = "-",
        title = toTitleCase("Table: Summary of PK parameters (pharmacokinetics analysis set)"),
        file = file.path("tables_CSR", "Table_PK_Parameters.docx"),
        labelVars = labelVars
    )

Table: Summary of PK Parameters (Pharmacokinetics Analysis Set)
Parameter Category 1	A (N=4)	C (N=3)
Parameter
DRUG ANAL 1 Plasma
AUCInf,obs (h*ng/mL)	4180.5 (2655,6570)	4988.6 (3838,5040)
Cmax (ng/mL)	3665.0 (1860,6440)	2320.0 (2190,4170)
tmax (h)	0.5083 (0.500,1.000)	1.0000 (0.500,1.500)
DRUG ANAL 2 Plasma
AUCInf,obs (h*ng/mL)	164397.2 (112551,299210)	164709.3 (127237,251953)
Cmax (ng/mL)	16900.0 (7920,26400)	19700.0 (11500,21700)
tmax (h)	2.0000 (1.500,4.000)	3.0000 (2.000,4.033)
DRUG ANAL 3 Plasma
AUCInf,obs (h*ng/mL)	29012.2 (14477,40242)	51233.8 (9731,61760)
Cmax (ng/mL)	3915.0 (2880,5990)	8700.0 (1900,10900)
tmax (h)	1.5000 (1.500,4.033)	1.0000 (0.983,3.000)

6 Appendix

6.1 Session information

R version 4.3.3 (2024-02-29)

Platform: x86_64-pc-linux-gnu (64-bit)

locale: LC_CTYPE=en_US.UTF-8, LC_NUMERIC=C, LC_TIME=en_US.UTF-8, LC_COLLATE=C, LC_MONETARY=en_US.UTF-8, LC_MESSAGES=en_US.UTF-8, LC_PAPER=en_US.UTF-8, LC_NAME=C, LC_ADDRESS=C, LC_TELEPHONE=C, LC_MEASUREMENT=en_US.UTF-8 and LC_IDENTIFICATION=C

attached base packages: tools, stats, graphics, grDevices, utils, datasets, methods and base

other attached packages: plyr(v.1.8.9), pander(v.0.6.5), clinUtils(v.0.1.4), inTextSummaryTable(v.3.3.2) and knitr(v.1.45)

loaded via a namespace (and not attached): gtable(v.0.3.4), xfun(v.0.42), bslib(v.0.6.1), ggplot2(v.3.5.0), htmlwidgets(v.1.6.4), ggrepel(v.0.9.5), vctrs(v.0.6.5), crosstalk(v.1.2.1), generics(v.0.1.3), curl(v.5.2.1), tibble(v.3.2.1), fansi(v.1.0.6), highr(v.0.10), pkgconfig(v.2.0.3), data.table(v.1.15.2), uuid(v.1.2-0), lifecycle(v.1.0.4), flextable(v.0.9.5), farver(v.2.1.1), stringr(v.1.5.1), compiler(v.4.3.3), textshaping(v.0.3.7), munsell(v.0.5.0), httpuv(v.1.6.14), fontquiver(v.0.2.1), fontLiberation(v.0.1.0), htmltools(v.0.5.7), sass(v.0.4.8), yaml(v.2.3.8), later(v.1.3.2), pillar(v.1.9.0), crayon(v.1.5.2), jquerylib(v.0.1.4), gfonts(v.0.2.0), ellipsis(v.0.3.2), openssl(v.2.1.1), DT(v.0.32), cachem(v.1.0.8), mime(v.0.12), fontBitstreamVera(v.0.1.1), tidyselect(v.1.2.0), zip(v.2.3.1), digest(v.0.6.34), stringi(v.1.8.3), reshape2(v.1.4.4), dplyr(v.1.1.4), labeling(v.0.4.3), forcats(v.1.0.0), cowplot(v.1.1.3), fastmap(v.1.1.1), grid(v.4.3.3), colorspace(v.2.1-0), cli(v.3.6.2), magrittr(v.2.0.3), crul(v.1.4.0), utf8(v.1.2.4), withr(v.3.0.0), gdtools(v.0.3.7), scales(v.1.3.0), promises(v.1.2.1), rmarkdown(v.2.26), officer(v.0.6.5), askpass(v.1.2.0), ragg(v.1.2.7), hms(v.1.1.3), shiny(v.1.8.0), evaluate(v.0.23), haven(v.2.5.4), viridisLite(v.0.4.2), rlang(v.1.1.3), Rcpp(v.1.0.12), xtable(v.1.8-4), glue(v.1.7.0), httpcode(v.0.3.0), xml2(v.1.3.6), jsonlite(v.1.8.8), R6(v.2.5.1) and systemfonts(v.1.0.6)