andreas/REDCapCAST
1
0
Fork 0
mirror of https://github.com/agdamsbo/REDCapCAST.git synced 2025-12-16 17:42:10 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions
REDCapCAST/articles/Shiny-app.md

323 lines
19 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Shiny-app
To make the easiest possible transition from spreadsheet/dataset to
REDCap, I have created a small app, which adds a graphical interface to
the casting of a data dictionary and data upload. Install the package
and launch the app as follows:
``` r
REDCapCAST::shiny_cast()
```
The app primarily wraps one function:
[`ds2dd_detailed()`](https://agdamsbo.github.io/REDCapCAST/reference/ds2dd_detailed.md).
``` r
library(REDCapCAST)
ds <- REDCap_split(
records = redcapcast_data,
metadata = redcapcast_meta,
forms = "all"
) |>
sanitize_split() |>
redcap_wider()
#> Joining with `by = join_by(record_id)`
#> Joining with `by = join_by(record_id)`
str(ds)
#> tibble [6 × 49] (S3: tbl_df/tbl/data.frame)
#> $ record_id : num [1:6] 1 2 3 4 5 6
#> $ cpr : chr [1:6] "1203401OB4" "0102342303" "2301569823" "0204051342" ...
#> $ inclusion : Date[1:6], format: "2023-03-13" "2023-03-01" ...
#> $ inclusion_time : 'hms' num [1:6] 12:38:49 10:38:57 12:01:07 20:39:19 ...
#> ..- attr(*, "units")= chr "secs"
#> $ dob : Date[1:6], format: "1940-03-12" "1934-02-01" ...
#> $ age : num [1:6] 83 89.1 66.1 117.9 126.2 ...
#> $ age_integer : num [1:6] 83 89 66 117 126 91
#> $ sex : chr [1:6] "female" "male" "male" "female" ...
#> $ cohabitation : chr [1:6] "Yes" "Yes" "No" NA ...
#> $ hypertension : chr [1:6] "No" "No" "Yes" NA ...
#> $ diabetes : chr [1:6] "Yes" "No" "Yes" NA ...
#> $ region : chr [1:6] "East" "South" "North" NA ...
#> $ baseline_data_start_complete : chr [1:6] "Incomplete" "Incomplete" "Incomplete" "Incomplete" ...
#> $ mrs_assessed____inclusion : chr [1:6] "Yes" "Yes" NA NA ...
#> $ mrs_assessed____follow1 : chr [1:6] NA "Yes" "Yes" NA ...
#> $ mrs_assessed____follow2 : chr [1:6] NA NA "Yes" NA ...
#> $ mrs_date____inclusion : Date[1:6], format: "2023-03-13" "2023-03-07" ...
#> $ mrs_date____follow1 : Date[1:6], format: NA "2023-03-09" ...
#> $ mrs_date____follow2 : Date[1:6], format: NA NA ...
#> $ mrs_score____inclusion : num [1:6] 1 1 NA NA NA NA
#> $ mrs_score____follow1 : num [1:6] NA 3 2 NA NA NA
#> $ mrs_score____follow2 : num [1:6] NA NA 1 NA NA NA
#> $ mrs_complete____inclusion : chr [1:6] "Incomplete" "Incomplete" NA NA ...
#> $ mrs_complete____follow1 : chr [1:6] NA "Incomplete" "Incomplete" NA ...
#> $ mrs_complete____follow2 : chr [1:6] NA NA "Incomplete" NA ...
#> $ event_datetime____1____follow1 : POSIXct[1:6], format: NA "2024-01-18 12:49:42" ...
#> $ event_datetime____1____follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_age____1____follow1 : num [1:6] NA NA NA 96 127 NA
#> $ event_age____1____follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_type____1____follow1 : chr [1:6] NA "TIA" "AIS" "TIA" ...
#> $ event_type____1____follow2 : chr [1:6] NA NA "ICH" "AIS" ...
#> $ new_event_complete____1____follow1: chr [1:6] NA "Incomplete" "Incomplete" "Complete" ...
#> $ new_event_complete____1____follow2: chr [1:6] NA NA "Incomplete" "Complete" ...
#> $ event_datetime____2____follow1 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime____2____follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime____3____follow1 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime____3____follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_age____2____follow1 : num [1:6] NA NA NA 105 127 NA
#> $ event_age____2____follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_age____3____follow1 : num [1:6] NA NA NA NA NA NA
#> $ event_age____3____follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_type____2____follow1 : chr [1:6] NA NA "ICH" "TIA" ...
#> $ event_type____2____follow2 : chr [1:6] NA NA "TIA" "ICH" ...
#> $ event_type____3____follow1 : chr [1:6] NA NA NA NA ...
#> $ event_type____3____follow2 : chr [1:6] NA NA "AIS" "Unknown" ...
#> $ new_event_complete____2____follow1: chr [1:6] NA NA "Incomplete" "Complete" ...
#> $ new_event_complete____2____follow2: chr [1:6] NA NA "Incomplete" "Incomplete" ...
#> $ new_event_complete____3____follow1: chr [1:6] NA NA NA NA ...
#> $ new_event_complete____3____follow2: chr [1:6] NA NA "Incomplete" "Complete" ...
#> - attr(*, "problems")=<externalptr>
```
``` r
ds|>
ds2dd_detailed(metadata = names(REDCapCAST::redcapcast_meta))|>
purrr::pluck("data") |>
str()
#> tibble [6 × 49] (S3: tbl_df/tbl/data.frame)
#> $ record_id : num [1:6] 1 2 3 4 5 6
#> $ cpr : chr [1:6] "1203401OB4" "0102342303" "2301569823" "0204051342" ...
#> $ inclusion : Date[1:6], format: "2023-03-13" "2023-03-01" ...
#> $ inclusion_time : chr [1:6] "12:38:49" "10:38:57" "12:01:07" "20:39:19" ...
#> $ dob : Date[1:6], format: "1940-03-12" "1934-02-01" ...
#> $ age : num [1:6] 83 89.1 66.1 117.9 126.2 ...
#> $ age_integer : num [1:6] 83 89 66 117 126 91
#> $ sex : chr [1:6] "female" "male" "male" "female" ...
#> $ cohabitation : chr [1:6] "Yes" "Yes" "No" NA ...
#> $ hypertension : chr [1:6] "No" "No" "Yes" NA ...
#> $ diabetes : chr [1:6] "Yes" "No" "Yes" NA ...
#> $ region : chr [1:6] "East" "South" "North" NA ...
#> $ baseline_data_start_complete : chr [1:6] "Incomplete" "Incomplete" "Incomplete" "Incomplete" ...
#> $ mrs_assessed__inclusion : chr [1:6] "Yes" "Yes" NA NA ...
#> $ mrs_assessed__follow1 : chr [1:6] NA "Yes" "Yes" NA ...
#> $ mrs_assessed__follow2 : chr [1:6] NA NA "Yes" NA ...
#> $ mrs_date__inclusion : Date[1:6], format: "2023-03-13" "2023-03-07" ...
#> $ mrs_date__follow1 : Date[1:6], format: NA "2023-03-09" ...
#> $ mrs_date__follow2 : Date[1:6], format: NA NA ...
#> $ mrs_score__inclusion : num [1:6] 1 1 NA NA NA NA
#> $ mrs_score__follow1 : num [1:6] NA 3 2 NA NA NA
#> $ mrs_score__follow2 : num [1:6] NA NA 1 NA NA NA
#> $ mrs_complete__inclusion : chr [1:6] "Incomplete" "Incomplete" NA NA ...
#> $ mrs_complete__follow1 : chr [1:6] NA "Incomplete" "Incomplete" NA ...
#> $ mrs_complete__follow2 : chr [1:6] NA NA "Incomplete" NA ...
#> $ event_datetime__1__follow1 : POSIXct[1:6], format: NA "2024-01-18 12:49:42" ...
#> $ event_datetime__1__follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_age__1__follow1 : num [1:6] NA NA NA 96 127 NA
#> $ event_age__1__follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_type__1__follow1 : chr [1:6] NA "TIA" "AIS" "TIA" ...
#> $ event_type__1__follow2 : chr [1:6] NA NA "ICH" "AIS" ...
#> $ new_event_complete__1__follow1: chr [1:6] NA "Incomplete" "Incomplete" "Complete" ...
#> $ new_event_complete__1__follow2: chr [1:6] NA NA "Incomplete" "Complete" ...
#> $ event_datetime__2__follow1 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime__2__follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime__3__follow1 : POSIXct[1:6], format: NA NA ...
#> $ event_datetime__3__follow2 : POSIXct[1:6], format: NA NA ...
#> $ event_age__2__follow1 : num [1:6] NA NA NA 105 127 NA
#> $ event_age__2__follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_age__3__follow1 : num [1:6] NA NA NA NA NA NA
#> $ event_age__3__follow2 : num [1:6] NA NA NA 118 NA NA
#> $ event_type__2__follow1 : chr [1:6] NA NA "ICH" "TIA" ...
#> $ event_type__2__follow2 : chr [1:6] NA NA "TIA" "ICH" ...
#> $ event_type__3__follow1 : chr [1:6] NA NA NA NA ...
#> $ event_type__3__follow2 : chr [1:6] NA NA "AIS" "Unknown" ...
#> $ new_event_complete__2__follow1: chr [1:6] NA NA "Incomplete" "Complete" ...
#> $ new_event_complete__2__follow2: chr [1:6] NA NA "Incomplete" "Incomplete" ...
#> $ new_event_complete__3__follow1: chr [1:6] NA NA NA NA ...
#> $ new_event_complete__3__follow2: chr [1:6] NA NA "Incomplete" "Complete" ...
```
``` r
ds|>
ds2dd_detailed(metadata = names(REDCapCAST::redcapcast_meta))|>
purrr::pluck("meta") |>
head(10)
#> # A tibble: 10 × 18
#> field_name form_name section_header field_type field_label
#> <chr> <chr> <lgl> <chr> <chr>
#> 1 record_id data NA text record_id
#> 2 cpr data NA text cpr
#> 3 inclusion data NA text inclusion
#> 4 inclusion_time data NA text inclusion_time
#> 5 dob data NA text dob
#> 6 age data NA text age
#> 7 age_integer data NA text age_integer
#> 8 sex data NA text sex
#> 9 cohabitation data NA text cohabitation
#> 10 hypertension data NA text hypertension
#> # ℹ 13 more variables: select_choices_or_calculations <lgl>, field_note <lgl>,
#> # text_validation_type_or_show_slider_number <chr>,
#> # text_validation_min <lgl>, text_validation_max <lgl>, identifier <lgl>,
#> # branching_logic <lgl>, required_field <lgl>, custom_alignment <lgl>,
#> # question_number <lgl>, matrix_group_name <lgl>, matrix_ranking <lgl>,
#> # field_annotation <lgl>
```
Different data formats are accepted, which all mostly implements the
[`readr::col_guess()`](https://readr.tidyverse.org/reference/parse_guess.html)
functionality to parse column classes.
To ensure uniformity in data import this parsing has been implemented on
its own to use with
[`ds2dd_detailed()`](https://agdamsbo.github.io/REDCapCAST/reference/ds2dd_detailed.md)
or any other data set for that matter:
``` r
ds_parsed <- redcapcast_data |>
dplyr::mutate(dplyr::across(dplyr::everything(),as.character)) |>
parse_data()
str(ds_parsed)
#> tibble [25 × 27] (S3: tbl_df/tbl/data.frame)
#> $ record_id : num [1:25] 1 2 2 2 3 3 3 3 3 3 ...
#> $ redcap_event_name : chr [1:25] "inclusion" "inclusion" "follow1" "follow1" ...
#> $ redcap_repeat_instrument : chr [1:25] NA NA NA "New Event (?)" ...
#> $ redcap_repeat_instance : num [1:25] NA NA NA 1 NA NA NA 1 2 1 ...
#> $ cpr : chr [1:25] "1203401OB4" "0102342303" NA NA ...
#> $ inclusion : Date[1:25], format: "2023-03-13" "2023-03-01" ...
#> $ inclusion_time : 'hms' num [1:25] 12:38:49 10:38:57 NA NA ...
#> ..- attr(*, "units")= chr "secs"
#> $ dob : Date[1:25], format: "1940-03-12" "1934-02-01" ...
#> $ age : num [1:25] 83 89.1 NA NA 66.1 ...
#> $ age_integer : num [1:25] 83 89 NA NA 66 NA NA NA NA NA ...
#> $ sex : chr [1:25] "female" "male" NA NA ...
#> $ cohabitation : chr [1:25] "Yes" "Yes" NA NA ...
#> $ hypertension : chr [1:25] "No" "No" NA NA ...
#> $ diabetes : chr [1:25] "Yes" "No" NA NA ...
#> $ region : chr [1:25] "East" "South" NA NA ...
#> $ baseline_data_start_complete: chr [1:25] "Incomplete" "Incomplete" NA NA ...
#> $ mrs_assessed : chr [1:25] "Yes" "Yes" "Yes" NA ...
#> $ mrs_date : Date[1:25], format: "2023-03-13" "2023-03-07" ...
#> $ mrs_score : num [1:25] 1 1 3 NA NA 2 1 NA NA NA ...
#> $ mrs_complete : chr [1:25] "Incomplete" "Incomplete" "Incomplete" NA ...
#> $ con_mrs : logi [1:25] NA NA NA NA NA NA ...
#> $ con_calc : logi [1:25] NA NA NA NA NA NA ...
#> $ consensus_complete : chr [1:25] NA NA "Incomplete" NA ...
#> $ event_datetime : POSIXct[1:25], format: NA NA ...
#> $ event_age : num [1:25] NA NA NA NA NA NA NA NA NA NA ...
#> $ event_type : chr [1:25] NA NA NA "TIA" ...
#> $ new_event_complete : chr [1:25] NA NA NA "Incomplete" ...
#> - attr(*, "problems")=<externalptr>
```
It will ignore specified columns, which is neat for numeric-looking
strings like cpr-with a leading 0:
``` r
redcapcast_data |>
dplyr::mutate(dplyr::across(dplyr::everything(),as.character)) |>
parse_data(ignore.vars = c("record_id","cpr")) |>
str()
#> tibble [25 × 27] (S3: tbl_df/tbl/data.frame)
#> $ record_id : chr [1:25] "1" "2" "2" "2" ...
#> $ redcap_event_name : chr [1:25] "inclusion" "inclusion" "follow1" "follow1" ...
#> $ redcap_repeat_instrument : chr [1:25] NA NA NA "New Event (?)" ...
#> $ redcap_repeat_instance : num [1:25] NA NA NA 1 NA NA NA 1 2 1 ...
#> $ cpr : chr [1:25] "1203401OB4" "0102342303" NA NA ...
#> $ inclusion : Date[1:25], format: "2023-03-13" "2023-03-01" ...
#> $ inclusion_time : 'hms' num [1:25] 12:38:49 10:38:57 NA NA ...
#> ..- attr(*, "units")= chr "secs"
#> $ dob : Date[1:25], format: "1940-03-12" "1934-02-01" ...
#> $ age : num [1:25] 83 89.1 NA NA 66.1 ...
#> $ age_integer : num [1:25] 83 89 NA NA 66 NA NA NA NA NA ...
#> $ sex : chr [1:25] "female" "male" NA NA ...
#> $ cohabitation : chr [1:25] "Yes" "Yes" NA NA ...
#> $ hypertension : chr [1:25] "No" "No" NA NA ...
#> $ diabetes : chr [1:25] "Yes" "No" NA NA ...
#> $ region : chr [1:25] "East" "South" NA NA ...
#> $ baseline_data_start_complete: chr [1:25] "Incomplete" "Incomplete" NA NA ...
#> $ mrs_assessed : chr [1:25] "Yes" "Yes" "Yes" NA ...
#> $ mrs_date : Date[1:25], format: "2023-03-13" "2023-03-07" ...
#> $ mrs_score : num [1:25] 1 1 3 NA NA 2 1 NA NA NA ...
#> $ mrs_complete : chr [1:25] "Incomplete" "Incomplete" "Incomplete" NA ...
#> $ con_mrs : logi [1:25] NA NA NA NA NA NA ...
#> $ con_calc : logi [1:25] NA NA NA NA NA NA ...
#> $ consensus_complete : chr [1:25] NA NA "Incomplete" NA ...
#> $ event_datetime : POSIXct[1:25], format: NA NA ...
#> $ event_age : num [1:25] NA NA NA NA NA NA NA NA NA NA ...
#> $ event_type : chr [1:25] NA NA NA "TIA" ...
#> $ new_event_complete : chr [1:25] NA NA NA "Incomplete" ...
#> - attr(*, "problems")=<externalptr>
```
Column classes can be passed to
[`parse_data()`](https://agdamsbo.github.io/REDCapCAST/reference/parse_data.md).
Making a few crude assumption for factorising data,
[`numchar2fct()`](https://agdamsbo.github.io/REDCapCAST/reference/numchar2fct.md)
factorises numerical and character vectors based on a set threshold for
unique values:
``` r
mtcars |> str()
#> 'data.frame': 32 obs. of 11 variables:
#> $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
#> $ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
#> $ disp: num 160 160 108 258 360 ...
#> $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
#> $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
#> $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
#> $ qsec: num 16.5 17 18.6 19.4 17 ...
#> $ vs : num 0 0 1 1 0 1 0 1 1 1 ...
#> $ am : num 1 1 1 0 0 0 0 0 0 0 ...
#> $ gear: num 4 4 4 3 3 3 3 4 4 4 ...
#> $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
mtcars |>
numchar2fct(numeric.threshold = 6) |>
str()
#> 'data.frame': 32 obs. of 11 variables:
#> $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
#> $ cyl : Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
#> $ disp: num 160 160 108 258 360 ...
#> $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
#> $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
#> $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
#> $ qsec: num 16.5 17 18.6 19.4 17 ...
#> $ vs : Factor w/ 2 levels "0","1": 1 1 2 2 1 2 1 2 2 2 ...
#> $ am : Factor w/ 2 levels "0","1": 2 2 2 1 1 1 1 1 1 1 ...
#> $ gear: Factor w/ 3 levels "3","4","5": 2 2 2 1 1 1 1 2 2 2 ...
#> $ carb: Factor w/ 6 levels "1","2","3","4",..: 4 4 1 1 2 1 4 2 2 4 ...
```
``` r
ds_parsed|>
numchar2fct(numeric.threshold = 2) |>
str()
#> tibble [25 × 27] (S3: tbl_df/tbl/data.frame)
#> $ record_id : num [1:25] 1 2 2 2 3 3 3 3 3 3 ...
#> $ redcap_event_name : Factor w/ 3 levels "inclusion","follow1",..: 1 1 2 2 1 2 3 2 2 3 ...
#> $ redcap_repeat_instrument : Factor w/ 1 level "New Event (?)": NA NA NA 1 NA NA NA 1 1 1 ...
#> $ redcap_repeat_instance : num [1:25] NA NA NA 1 NA NA NA 1 2 1 ...
#> $ cpr : chr [1:25] "1203401OB4" "0102342303" NA NA ...
#> $ inclusion : Date[1:25], format: "2023-03-13" "2023-03-01" ...
#> $ inclusion_time : 'hms' num [1:25] 12:38:49 10:38:57 NA NA ...
#> ..- attr(*, "units")= chr "secs"
#> $ dob : Date[1:25], format: "1940-03-12" "1934-02-01" ...
#> $ age : num [1:25] 83 89.1 NA NA 66.1 ...
#> $ age_integer : num [1:25] 83 89 NA NA 66 NA NA NA NA NA ...
#> $ sex : Factor w/ 2 levels "female","male": 1 2 NA NA 2 NA NA NA NA NA ...
#> $ cohabitation : Factor w/ 2 levels "Yes","No": 1 1 NA NA 2 NA NA NA NA NA ...
#> $ hypertension : Factor w/ 2 levels "No","Yes": 1 1 NA NA 2 NA NA NA NA NA ...
#> $ diabetes : Factor w/ 2 levels "Yes","No": 1 2 NA NA 1 NA NA NA NA NA ...
#> $ region : Factor w/ 3 levels "East","South",..: 1 2 NA NA 3 NA NA NA NA NA ...
#> $ baseline_data_start_complete: Factor w/ 2 levels "Incomplete","Complete": 1 1 NA NA 1 NA NA NA NA NA ...
#> $ mrs_assessed : Factor w/ 1 level "Yes": 1 1 1 NA NA 1 1 NA NA NA ...
#> $ mrs_date : Date[1:25], format: "2023-03-13" "2023-03-07" ...
#> $ mrs_score : num [1:25] 1 1 3 NA NA 2 1 NA NA NA ...
#> $ mrs_complete : Factor w/ 1 level "Incomplete": 1 1 1 NA 1 1 1 NA NA NA ...
#> $ con_mrs : logi [1:25] NA NA NA NA NA NA ...
#> $ con_calc : logi [1:25] NA NA NA NA NA NA ...
#> $ consensus_complete : Factor w/ 1 level "Incomplete": NA NA 1 NA NA 1 1 NA NA NA ...
#> $ event_datetime : POSIXct[1:25], format: NA NA ...
#> $ event_age : num [1:25] NA NA NA NA NA NA NA NA NA NA ...
#> $ event_type : Factor w/ 4 levels "TIA","AIS","ICH",..: NA NA NA 1 NA NA NA 2 3 3 ...
#> $ new_event_complete : Factor w/ 2 levels "Incomplete","Complete": NA NA NA 1 NA NA NA 1 1 1 ...
#> - attr(*, "problems")=<externalptr>
```
Reference in a new issue View git blame Copy permalink