Skip to contents

Survival Time Point Analysis

Source: R/survival_timepoint.R
survival_timepoint.Rd

[Stable]

Summarize patients' survival rate and difference of survival rates between groups at a time point.

Usage 

s_surv_timepoint(
  df,
  .var,
  time_point,
  is_event,
  control = control_surv_timepoint()
)

a_surv_timepoint(
  df,
  .var,
  time_point,
  is_event,
  control = control_surv_timepoint()
)

s_surv_timepoint_diff(
  df,
  .var,
  .ref_group,
  .in_ref_col,
  time_point,
  control = control_surv_timepoint(),
  ...
)

a_surv_timepoint_diff(
  df,
  .var,
  .ref_group,
  .in_ref_col,
  time_point,
  control = control_surv_timepoint(),
  ...
)

surv_timepoint(
  lyt,
  vars,
  ...,
  table_names_suffix = "",
  var_labels = "Time",
  show_labels = "visible",
  method = c("surv", "surv_diff", "both"),
  .stats = c("pt_at_risk", "event_free_rate", "rate_ci", "rate_diff", "rate_diff_ci",
    "ztest_pval"),
  .formats = NULL,
  .labels = NULL,
  .indent_mods = NULL
)

Arguments

df

(data.frame)
data set containing all analysis variables.

.var

(string)
single variable name that is passed by rtables when requested by a statistics function.

time_point

(number)
survival time point of interest.

is_event

(logical)
TRUE if event, FALSE if time to event is censored.

control

(list)
parameters for comparison details, specified by using the helper function control_surv_timepoint(). Some possible parameter options are:

  • conf_level (proportion)
    confidence level of the interval for survival rate.

  • conf_type (string)
    confidence interval type. Options are "plain" (default), "log", "log-log", see more in survival::survfit(). Note option "none" is no longer supported.

  • time_point (number)
    survival time point of interest.

.ref_group

(data.frame or vector)
the data corresponding to the reference group.

.in_ref_col

(logical)
TRUE when working with the reference level, FALSE otherwise.

...

additional arguments for the lower level functions.

lyt

(layout)
input layout where analyses will be added to.

vars

(character)
variable names for the primary analysis variable to be iterated over.

table_names_suffix

(string)
optional suffix for the table_names used for the rtables to avoid warnings from duplicate table names.

var_labels

character for label.

show_labels

label visibility: one of "default", "visible" and "hidden".

method

(string)
either surv (survival estimations), surv_diff (difference in survival with the control) or both.

.stats

(character)
statistics to select for the table.

.formats

(named character or list)
formats for the statistics.

.labels

(named character)
labels for the statistics (without indent).

.indent_mods

(named integer)
indent modifiers for the labels.

Value

The statistics are:

pt_at_risk

patients remaining at risk.

event_free_rate

event free rate (%).

rate_se

standard error of event free rate.

rate_ci

confidence interval for event free rate.

The statistics are:

rate_diff

event free rate difference between two groups.

rate_diff_ci

confidence interval for the difference.

ztest_pval

p-value to test the difference is 0.

Functions

  • s_surv_timepoint(): Statistics Function which analyzes survival rate.

  • a_surv_timepoint(): Formatted Analysis function which can be further customized by calling rtables::make_afun() on it. It is used as afun in rtables::analyze().

  • s_surv_timepoint_diff(): Statistics Function which analyzes difference between two survival rates.

  • a_surv_timepoint_diff(): Formatted Analysis function which can be further customized by calling rtables::make_afun() on it. It is used as afun in rtables::analyze().

  • surv_timepoint(): Analyze Function which adds the survival rate analysis to the input layout. Note that additional formatting arguments can be used here.

Examples 

library(dplyr)

adtte_f <- tern_ex_adtte %>%
  filter(PARAMCD == "OS") %>%
  mutate(
    AVAL = day2month(AVAL),
    is_event = CNSR == 0
  )
df <- adtte_f %>%
  filter(ARMCD == "ARM A")

# Internal function - s_surv_timepoint
if (FALSE) {
s_surv_timepoint(df, .var = "AVAL", time_point = 7, is_event = "is_event")
}

# Internal function - a_surv_timepoint
if (FALSE) {
a_surv_timepoint(df, .var = "AVAL", time_point = 7, is_event = "is_event")
}

df_ref_group <- adtte_f %>%
  filter(ARMCD == "ARM B")

# Internal function - s_surv_timepoint_diff
if (FALSE) {
s_surv_timepoint_diff(df, df_ref_group, .in_ref_col = TRUE, .var = "AVAL", is_event = "is_event")
s_surv_timepoint_diff(
  df,
  df_ref_group,
  .in_ref_col = FALSE,
  .var = "AVAL",
  time_point = 7,
  is_event = "is_event"
)
}

# Internal function - a_surv_timepoint_diff
if (FALSE) {
a_surv_timepoint_diff(
  df,
  df_ref_group,
  .in_ref_col = FALSE,
  .var = "AVAL",
  time_point = 7,
  is_event = "is_event"
)
}

# Survival at given time points.
basic_table() %>%
  split_cols_by(var = "ARMCD", ref_group = "ARM A") %>%
  add_colcounts() %>%
  surv_timepoint(
    vars = "AVAL",
    var_labels = "Months",
    is_event = "is_event",
    time_point = 7
  ) %>%
  build_table(df = adtte_f)
#>                                    ARM A            ARM B            ARM C     
#>                                    (N=69)           (N=73)           (N=58)    
#> ———————————————————————————————————————————————————————————————————————————————
#> 7 Months                                                                       
#>   Patients remaining at risk         54               57               42      
#>   Event Free Rate (%)              84.89            79.43            75.50     
#>   95% CI                       (76.24, 93.53)   (70.15, 88.71)   (64.33, 86.67)

# Difference in survival at given time points.
basic_table() %>%
  split_cols_by(var = "ARMCD", ref_group = "ARM A") %>%
  add_colcounts() %>%
  surv_timepoint(
    vars = "AVAL",
    var_labels = "Months",
    is_event = "is_event",
    time_point = 9,
    method = "surv_diff",
    .indent_mods = c("rate_diff" = 0L, "rate_diff_ci" = 2L, "ztest_pval" = 2L)
  ) %>%
  build_table(df = adtte_f)
#>                                   ARM A        ARM B            ARM C     
#>                                   (N=69)       (N=73)           (N=58)    
#> ——————————————————————————————————————————————————————————————————————————
#> 9 Months                                                                  
#>   Difference in Event Free Rate                -9.64            -13.03    
#>       95% CI                               (-22.80, 3.52)   (-27.59, 1.53)
#>       p-value (Z-test)                         0.1511           0.0794    

# Survival and difference in survival at given time points.
basic_table() %>%
  split_cols_by(var = "ARMCD", ref_group = "ARM A") %>%
  add_colcounts() %>%
  surv_timepoint(
    vars = "AVAL",
    var_labels = "Months",
    is_event = "is_event",
    time_point = 9,
    method = "both"
  ) %>%
  build_table(df = adtte_f)
#>                                     ARM A            ARM B            ARM C     
#>                                     (N=69)           (N=73)           (N=58)    
#> ————————————————————————————————————————————————————————————————————————————————
#> 9 Months                                                                        
#>   Patients remaining at risk          53               53               39      
#>   Event Free Rate (%)               84.89            75.25            71.86     
#>   95% CI                        (76.24, 93.53)   (65.32, 85.17)   (60.14, 83.57)
#> Difference in Event Free Rate                        -9.64            -13.03    
#> 95% CI                                           (-22.80, 3.52)   (-27.59, 1.53)
#> p-value (Z-test)                                     0.1511           0.0794