more updates

R/data.R

@@ -22,7 +22,6 @@
 #' \describe{
 #' \item{USUBJID}{Unique subject identifiers for patients.}
 #' \item{ARM}{Assigned treatment arm, `"A"`.}
-#' \item{EVNT}{Event indicator `0`/`1`.}
 #' \item{AVAL}{Analysis value which in this dataset overall survival time in days.}
 #' \item{AVALU}{Unit of `AVAL`.}
 #' \item{PARAMCD}{Paramater code of `AVAL`, `"OS"`.}
@@ -67,6 +66,7 @@
 #' \item{SEX_MALE_CENTERED}{`SEX_MALE` centered by the proportion of male patients in [agd]}
 #' \item{ECOG0_CENTERED}{`ECOG0` centered by the proportion of `ECOG0` in [agd]}
 #' \item{SMOKE_CENTERED}{`SMOKE` centered by the proportion of `SMOKE` in [agd]}
+#' \item{N_PR_THER_MEDIAN_CENTERED}{`N_PR_THER` centered by the median in [agd].}
 #' }
 #' @family unanchored datasets
 #' @keywords dataset
@@ -116,6 +116,7 @@
 #' \item{SEX_MALE_COUNT}{Number of male patients}
 #' \item{ECOG0_COUNT}{Number of patients with ECOG score = 0}
 #' \item{SMOKE_COUNT}{Number of smokers}
+#' \item{N_PR_THER_MEDIAN}{Median number of prior therapies}
 #' }
 #' @family unanchored datasets
 #' @family anchored datasets
@@ -147,7 +148,6 @@
 #' \describe{
 #' \item{USUBJID}{Unique subject identifiers for patients.}
 #' \item{ARM}{Assigned treatment arm, `"A"`, `"C"`.}
-#' \item{EVNT}{Event indicator `0`/`1`.}
 #' \item{AVAL}{Analysis value which in this dataset overall survival time in days.}
 #' \item{AVALU}{Unit of `AVAL`.}
 #' \item{PARAMCD}{Parameter code of `AVAL`, `"OS"`.}
@@ -202,6 +202,7 @@
 #' \item{SEX_MALE_CENTERED}{`SEX_MALE` centered by the proportion of male patients in [agd]}
 #' \item{ECOG0_CENTERED}{`ECOG0` centered by the proportion of `ECOG0` in [agd]}
 #' \item{SMOKE_CENTERED}{`SMOKE` centered by the proportion of `SMOKE` in [agd]}
+#' \item{N_PR_THER_MEDIAN_CENTERED}{`N_PR_THER` centered by the median in [agd].}
 #' }
 #' @keywords dataset
 #' @family anchored datasets

data-raw/dummy_anchored.R

@@ -24,7 +24,7 @@ adtte <- read.csv(system.file("extdata", "adtte.csv",
  mustWork = TRUE
 ))
 adtte$TIME <- adtte$AVAL
-adtte$EVENT <- adtte$EVNT
+adtte$EVENT <- 1 - adtte$CNSR
 adtte$USUBJID <- paste0("xx", adtte$USUBJID)
 
 adtte2 <- adtte

data-raw/dummy_unanchored.R

@@ -13,7 +13,7 @@ adtte_sat <- read.csv(system.file("extdata", "adtte.csv",
  mustWork = TRUE
 ))
 adtte_sat$TIME <- adtte_sat$AVAL
-adtte_sat$EVENT <- adtte_sat$EVNT
+adtte_sat$EVENT <- 1 - adtte_sat$CNSR
 adtte_sat <- adtte_sat[adtte_sat$ARM == "A", , drop = FALSE]
 adsl_sat <- adsl_sat[adsl_sat$USUBJID %in% adtte_sat$USUBJID, , drop = FALSE]
 

inst/WORDLIST

@@ -1,58 +1,59 @@
-ADTTE
 ADaM
-AgD
-Azocar
-Bucher
-Comparator
-DSU
-ECOG
-ESS
-IPD
-Kaplan
-MAIC
-Paramater
-Phillippo
-Pre
-Remiro
-Schoenfeld
-Signorovitch
-TSD
-TTE
-Texp
-USUBJID
-Unanchored
-Univariable
-XXXX
 adrs
 adsl
+ADTTE
 adtte
+AgD
 agd
 agg
 al
+Azocar
 binarize
+Bucher
+Comparator
 comparator
 confounders
 csv
+DSU
 dummize
 dummized
+ECOG
+ESS
 et
 frac
 ggplot
 glm
 hta
 initializer
+IPD
 ipd
+Kaplan
+MAIC
 multivariable
 optim
+Paramater
 pharma
+Phillippo
 phillippo
+Pre
 pre
 preprocessed
+Remiro
 reproducibility
+Schoenfeld
 sd
+Signorovitch
 signorovitch
+Texp
+THER
+TSD
+TTE
 tte
+Unanchored
 unanchored
+Univariable
 unscaled
 unstacked
+USUBJID
 vcovHC
+XXXX

inst/examples/kmplot_anchored_ex.R

@@ -2,40 +2,19 @@
 
 ### IPD
 # Read in relevant ADaM data and rename variables of interest
-adsl <- read.csv(system.file("extdata", "adsl.csv",
- package = "maicplus",
- mustWork = TRUE
-))
-adtte <- read.csv(system.file("extdata", "adtte.csv",
- package = "maicplus",
- mustWork = TRUE
-))
-adtte$TIME <- adtte$AVAL
-adtte$EVENT <- adtte$EVNT
-adtte2 <- adtte
-adtte2$ARM <- "C"
-adtte2$TIME <- adtte2$TIME + 7
-adtte <- rbind(adtte, adtte2)
+adsl_twt
+adtte_twt
 
 ### AgD
 # Baseline aggregate data for the comparator population
-target_pop <- read.csv(system.file("extdata", "aggregate_data_example_1.csv",
- package = "maicplus", mustWork = TRUE
-))
+agd
+
 # for time-to-event endpoints, pseudo IPD from digitalized KM
-pseudo_ipd <- read.csv(system.file("extdata", "psuedo_IPD.csv",
- package = "maicplus",
- mustWork = TRUE
-))
-pseudo_ipd$ARM <- "B"
-pseudo_ipd2 <- pseudo_ipd
-pseudo_ipd2$ARM <- "C"
-pseudo_ipd2$Time <- pseudo_ipd2$Time + 5
-pseudo_ipd <- rbind(pseudo_ipd, pseudo_ipd2)
+pseudo_ipd_twt
 
 #### prepare data
-target_pop <- process_agd(target_pop)
-adsl <- dummize_ipd(adsl, dummize_cols = c("SEX"), dummize_ref_level = c("Female"))
+target_pop <- process_agd(agd)
+adsl <- dummize_ipd(adsl_twt, dummize_cols = c("SEX"), dummize_ref_level = c("Female"))
 use_adsl <- center_ipd(ipd = adsl, agd = target_pop)
 
 #### derive weights
@@ -49,9 +28,9 @@ match_res <- estimate_weights(
 # plot by trial
 kmplot(
  weights_object = match_res,
- tte_ipd = adtte,
+ tte_ipd = adtte_twt,
  trt_var_ipd = "ARM",
- tte_pseudo_ipd = pseudo_ipd,
+ tte_pseudo_ipd = pseudo_ipd_twt,
  trt_var_agd = "ARM",
  endpoint_name = "Overall Survival",
  trt_ipd = "A",
@@ -71,9 +50,9 @@ kmplot(
 # plot by arm
 kmplot(
  weights_object = match_res,
- tte_ipd = adtte,
+ tte_ipd = adtte_twt,
  trt_var_ipd = "ARM",
- tte_pseudo_ipd = pseudo_ipd,
+ tte_pseudo_ipd = pseudo_ipd_twt,
  trt_var_agd = "ARM",
  endpoint_name = "Overall Survival",
  trt_ipd = "A",
@@ -92,9 +71,9 @@ kmplot(
 # plot all
 kmplot(
  weights_object = match_res,
- tte_ipd = adtte,
+ tte_ipd = adtte_twt,
  trt_var_ipd = "ARM",
- tte_pseudo_ipd = pseudo_ipd,
+ tte_pseudo_ipd = pseudo_ipd_twt,
  trt_var_agd = "ARM",
  endpoint_name = "Overall Survival",
  trt_ipd = "A",

inst/examples/maic_unanchored_binary_ex.R

@@ -1,19 +1,14 @@
-# load in prognostic IPD data and AgD
-load(system.file("extdata", "ipd.rda", package = "maicplus", mustWork = TRUE))
-load(system.file("extdata", "agd.rda", package = "maicplus", mustWork = TRUE))
-ipd_centered <- center_ipd(ipd = ipd, agd = agd)
+# load in centered prognostic IPD data
 
-# estimate weights
-centered_colnames <- c("AGE", "AGE_SQUARED", "SEX_MALE", "ECOG0", "SMOKE", "N_PR_THER_MEDIAN")
-centered_colnames <- paste0(centered_colnames, "_CENTERED")
+centered_ipd_sat
+centered_colnames <- grep("_CENTERED$", colnames(centered_ipd_sat), value = TRUE)
+weighted_data <- estimate_weights(data = centered_ipd_sat, centered_colnames = centered_colnames)
+weighted_data2 <- estimate_weights(data = centered_ipd_sat, centered_colnames = centered_colnames, n_boot_iteration = 500)
 
-weighted_data <- estimate_weights(data = ipd_centered, centered_colnames = centered_colnames)
-weighted_data2 <- estimate_weights(data = ipd_centered, centered_colnames = centered_colnames, n_boot_iteration = 500)
+# binary IPD
+adrs_sat
 
 # get dummy binary IPD
-adrs <- read.csv(system.file("extdata", "adrs.csv", package = "maicplus", mustWork = TRUE))
-adrs$RESPONSE <- adrs$AVAL
-
 pseudo_adrs <- get_pseudo_ipd_binary(
  binary_agd = data.frame(
  ARM = rep("B", 2),
@@ -26,7 +21,7 @@ pseudo_adrs <- get_pseudo_ipd_binary(
 # unanchored binary MAIC, with CI based on sandwich estimator
 maic_unanchored(
  weights_object = weighted_data,
- ipd = adrs,
+ ipd = adrs_sat,
  pseudo_ipd = pseudo_adrs,
  trt_ipd = "A",
  trt_agd = "B",
@@ -42,7 +37,7 @@ maic_unanchored(
 # unanchored binary MAIC, with bootstrapped CI
 maic_unanchored(
  weights_object = weighted_data2,
- ipd = adrs,
+ ipd = adrs_sat,
  pseudo_ipd = pseudo_adrs,
  trt_ipd = "A",
  trt_agd = "B",

inst/extdata/aggregate_data_example_1.csv

@@ -1,4 +1,4 @@
-STUDY,ARM,N,AGE_MEAN,AGE_MEDIAN,AGE_SD,SEX_MALE_COUNT,ECOG0_COUNT,SMOKE_COUNT
-Study_XXXX,Total,300,51,49,3.25,147,105,58
-Study_XXXX,Intervention,,,,,,,
-Study_XXXX,Comparator,,,,,,,
+STUDY,ARM,N,AGE_MEAN,AGE_MEDIAN,AGE_SD,SEX_MALE_COUNT,ECOG0_COUNT,SMOKE_COUNT,N_PR_THER_MEDIAN
+Study_XXXX,Total,300,51,49,3.25,147,105,58,2
+Study_XXXX,Intervention,,,,,,,,
+Study_XXXX,Comparator,,,,,,,,