In Thaliehln/timci: Data management and visualisation for the TIMCI project

\newpage

write("Export Day 28 data and run corresponding quality checks", stderr())

Day 28 data quality checks

db_name <- "Day 28 follow-up"

out <- timci::format_day28_data(raw_day28fu_data,
                                is_deidentified = FALSE)
raw_allday28fu_data <- out[[3]]
n_raw_allday28fu_data_records <- nrow(raw_allday28fu_data)
raw_successday28fu_data <- out[[1]]

n_raw_allday28fu_data_records <- nrow(raw_allday28fu_data)
raw_allday28fu_is_not_empty <- timci::is_not_empty(raw_allday28fu_data)

There are r n_raw_allday28fu_data_records records in the raw r db_name database.

n_cdsa_pilot_day28fu_records <- 0
n_nonvalid_pids_day28fu_records <- 0
n_edit_nonvalid_pid_day28fu_records <- 0
n_drop_nonvalid_pid_day28fu_records <- 0
n_inconsistent_name_day28fu_records <- 0
n_edit_inconsistent_name_day28fu_records <- 0
n_drop_inconsistent_name_day28fu_records <- 0

Format raw data

day28fu_dictionary <- timci::import_country_specific_xls_dict("day28_dict.xlsx", Sys.getenv('TIMCI_COUNTRY'))
n_day28fu_dictionary_vars <- nrow(day28fu_dictionary)

There are r n_day28fu_dictionary_vars variables exported from the raw r db_name database.

day28fu_dictionary %>%
   dplyr::filter(deidentified == 1) %>%
  dplyr::select(new,
                old) %>%
  knitr::kable(col.names = c("Database reference",
                             "ODK reference"))

day28fu_deidentified_dict <- day28fu_dictionary %>%
  dplyr::filter(deidentified == 1)

day28fu_pii_drops <- day28fu_dictionary %>%
  dplyr::filter(deidentified == 0)
day28fu_pii_drops_is_not_empty <- timci::is_not_empty(day28fu_pii_drops)

Dates and times

Late submissions [Compliance check r qc_nontimely_submission_day28fu]

write(" o Inconsistent finalisation and submission", stderr())

qc_description <- "Transfer of a finalised submission to the ODK Central server not done on the day the submission was finalised (i.e. transfer time superior to 0 day)."
qc_rule <- action_alert_no_modification
qc_type <- "date_discrepancy"
df <- raw_allday28fu_data
col_date1 <- "end"
col_date2 <- "submission_date"
cleaning <- "none"
qc_text <- "the submission was not transferred on the same day it was finalised"
qc_idx <- qc_nontimely_submission_day28fu
qc_export_label <- "nontimely_day28_submission"
qc_export_description <- "the submission was not transferred on the same day it was finalised"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

fig_caption <- "Submissions not transferred on the same day they were finalised"
facility_col <- "fid"
date_col <- "week"
date_lbl <- "Weeks"
date_format <- "%b%y"
comparison <- "area"
fill_col <- "Difference"

fig_df <- qc_df %>% 
  dplyr::mutate(week = as.Date(lubridate::floor_date(as.Date(end), "week", week_start = getOption("lubridate.week.start", 1)))) %>% 
  dplyr::mutate(Difference = dplyr::case_when(
    diff < 3 ~ "Less than 3 days",
    diff >= 3 & diff < 7 ~ "3-6 days",
    diff >= 7 ~ "7 days and above"))

cat(knitr::knit_child('database_export_sub_facet_bar_plot.Rmd',
                      envir = environment(),
                      quiet = TRUE))

Late completions [Compliance check r qc_nontimely_completion_day28fu]

write(" o Non-timely completion", stderr())

qc_description <- "Finalisation of the submission not done on the same day the submission was started (i.e., duration from start to end strictly superior to 0 day)."
qc_rule <- action_alert_no_modification
qc_type <- "date_discrepancy"
df <- raw_allday28fu_data
col_date1 <- "start"
col_date2 <- "end"
cleaning <- "none"
qc_text <- "the submission was not finalised on the same day it was started"
qc_idx <- qc_nontimely_completion_day28fu
qc_export_label <- "nontimely_day28_completion"
qc_export_description <- "the submission was not finalised on the same day it was started"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

fig_caption <- "Number of submissions not finalised on the same day they were started"
facility_col <- "fid"
date_col <- "week"
date_lbl <- "Weeks"
date_format <- "%b%y"
comparison <- "area"
fill_col <- "Difference"

fig_df <- qc_df %>%
  dplyr::mutate(week = as.Date(lubridate::floor_date(as.Date(start), "week", week_start = getOption("lubridate.week.start", 1)))) %>% 
  dplyr::mutate(Difference = dplyr::case_when(
    diff <= 1 ~ "1 day",
    diff > 1 & diff < 3 ~ "1-2 days",
    diff >= 3 ~ "3 days and above"))

cat(knitr::knit_child('database_export_sub_facet_bar_plot.Rmd',
                      envir = environment(),
                      quiet = TRUE))

Participant identification

allday28fu_data <- raw_allday28fu_data

Follow-ups corresponding to participants enrolled in the CDSA pilot (India only) [Context check r qc_other_fids_day28fu]

write(" o Follow-ups corresponding to participants enrolled in the CDSA pilot", stderr())

r if (!is_india) {paste0("This check is only implemented for India.")}

qc_description <- paste0("Exclude follow-ups that correspond to participants enrolled in the CDSA pilot.")
qc_rule <- "Discard follow-up records of participants who are enrolled in CDSA pilot facilities."
qc_type <- "nonvalid_ids2"
df <- allday28fu_data
idcol1 <- "child_id"
refdf <- rbind(other_timci_study_df) %>%
  dplyr::filter( !is.na(child_id) )
idcol2 <- "child_id"
qc_text <- "follow-up records corresponding to participants enrolled for the CDSA pilot"
qc_idx <- qc_other_fids_day28fu
qc_export_label <- "pids_from_cdsa_pilot"
qc_export_description <- "the follow-up corresponds to a child who has been enrolled in the CDSA pilot"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_cdsa_pilot_day28fu_records <- n_detected
allday28fu_data <- cleaned_df

Follow-ups corresponding to participants enrolled outside the lock date range [context check r qc_pids_out_lock_range_day28fu]

write(" o Follow-ups corresponding to participants enrolled outside the lock date range", stderr())

qc_description <- paste0("Day 28 follow-ups are relevant only if associated to participants enrolled between the start date ", start_date, " and the lock date on ", lock_date, ".")
qc_rule <- "Discard follow-up records of participants who are enrolled in the Day 0 database outside the date range considered for the lock."
qc_type <- "nonvalid_ids2"
df <- allday28fu_data
idcol1 <- "child_id"
refdf <- rbind(facility_data_before_start,
               facility_data_after_lock) %>%
  dplyr::filter( !is.na(child_id) )
idcol2 <- "child_id"
col_date <- "date_call"
qc_text <- "participant IDs outside the lock date range"
qc_idx <- qc_pids_out_lock_range_day28fu
qc_export_label <- "pids_outside_lock_range"
qc_export_description <- "the follow-up correspond to a child who has been enrolled outside the date range for the lock"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_afterlock_pids_day28fu_records <- n_detected
allday28fu_data <- cleaned_df

Non-valid participant IDs [compliance check r qc_nonvalid_day28fu]

write(" o Non-valid participant IDs", stderr())

::: {custom-style="redparagraph"} Initial check r qc_nonvalid_day28fua :::

qc_description <- "Day 28 follow-ups are relevant only if they can be reconciled with a participant enrolled at Day 0. Reconciliation is based on the participant ID. Non-reconciled Day 28 follow-ups are searched for matched names."
qc_rule <- "Keep only IDs of children who can be found in the initial Day 0 database."
qc_type <- "nonvalid_ids_identify_names"
df <- allday28fu_data
idcol1 <- "child_id"
refdf <- allday0_data
idcol2 <- "child_id"
datecol <- "date_day0"
ldate_diff <- -2
udate_diff <- 2
matched_names <- TRUE
cleaning <- "none"
qc_text <- "non-valid participant IDs"
qc_idx <- paste0(qc_nonvalid_day28fu, "a")
qc_export_label <- "nonvalid_pids_day28fu_with_matched_names"
qc_export_description <- "the child ID does not correspond to any ID found the locked Day 0 database"
cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_nonvalid_pids_day28fu_records <- n_detected

mc_description <- ""
to_correct_df <- allday28fu_data
correction_type <- "correct_day28_non_valid_ids"

# Parameters for the quality check following manual corrections
qc_rule <- "Keep only IDs of children who can be found in the initial Day 0 database."
qc_idx <- paste0(qc_nonvalid_day28fu, "b")
cleaning <- "drop_all"

cat(knitr::knit_child('database_export_sub_corrections.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_edit_nonvalid_pid_day28fu_records <- n_mc
n_drop_nonvalid_pid_day28fu_records <- n_detected

allday28fu_data <- cleaned_df

Non-consistent participant names [Context check r qc_nonconsistent_name_day28fu]

write(" o Non-consistent participant names", stderr())

::: {custom-style="redparagraph"} Initial check r qc_nonconsistent_name_day28fua :::

qc_description <- "Day 28 follow-ups are relevant only if the name of the participant matches the name of the participant enrolled at Day 0. Some errors can be introduced when participant IDs have been duplicated or follow-ups have been entered manually."
qc_rule <- "Keep only IDs of children whose name matches the name in the initial Day 0 database."
qc_type <- "inconsistent_names"
df <- allday28fu_data
refdf <- allday0_data
datecol <- "date_day0"
ldate_diff <- -2
udate_diff <- 2
matched_names <- TRUE
qc_text <- "non-consistent participant names"
qc_idx <- paste0(qc_nonconsistent_name_day28fu, "a")
qc_export_label <- "nonconsistent_names_day28fu_with_matched_names"
qc_export_description <- paste0("the child name found in the ", db_name, " is not consistent with the name of the child with the same ID found in the locked Day 0 database")

cat(knitr::knit_child('database_export_sub_quality_check.Rmd',
                      envir = environment(),
                      quiet = TRUE))

n_inconsistent_name_day28fu_records <- n_detected

mc_description <- ""
to_correct_df <- allday28fu_data
correction_type <- "correct_day28_inconsistent_names"

# Parameters for the quality check following manual corrections
qc_idx <- paste0(qc_nonconsistent_name_day28fu, "b")
qc_export_label <- "nonconsistent_names_day28fu_with_matched_names"

cat(knitr::knit_child('database_export_sub_corrections.Rmd',
                      envir = environment(),
                      quiet = TRUE))

allday28fu_data <- corrected_df
n_edit_inconsistent_name_day28fu_records <- n_mc

mc_description <- "Delete records where it cannot be ascertained that the child enrolled and followed-up are the same individual (manual evaluation)."
to_correct_df <- allday28fu_data
correction_type <- "delete_day28_records"

# Parameters for the quality check following manual corrections
qc_idx <- paste0(qc_nonconsistent_name_day28fu, "c")
qc_rule <- "Remaining records with inconsistent names are kept in the database (i.e. some similarity have been found despite the low automated score)."
qc_export_label <- "nonconsistent_names_day28fu_with_matched_names"
cleaning <- "none"

cat(knitr::knit_child('database_export_sub_corrections.Rmd',
                      envir = environment(),
                      quiet = TRUE))

allday28fu_data <- corrected_df
n_drop_inconsistent_name_day28fu_records <- n_mc

Pseudonymisation

write(" o Pseudonymisation", stderr())

The columns listed in the table below are dropped from the cleaned r db_name database.

day28fu_pii_drops %>%
  dplyr::select(new) %>%
  knitr::kable(row.names = FALSE,
               col.names = c("Database reference"),
               caption = "Columns dropped for the cleaned data export")

allday28fu_data_no_pii <- allday28fu_data %>%
  dplyr::select(dplyr::any_of(c(day28fu_deidentified_dict$new)))

Pseudonymisation is performed using a cryptographic hash function (md5) that takes strings as input (variables uuid,child_id, and device_id) and produces a random-like fixed-length output.

allday28fu_data_no_pii <- allday28fu_data_no_pii %>%
  dplyr::rowwise() %>%
  dplyr::mutate(uuid = ifelse(uuid != "", digest(uuid, algo = crypto_algo), ""),
                child_id = ifelse(child_id != "", digest(child_id, algo = crypto_algo), ""),
                device_id = ifelse(device_id != "", digest(device_id, algo = crypto_algo), "")) %>%
  dplyr::ungroup()

n_cleaned_allday28fu_records <- nrow(allday28fu_data_no_pii)

Data cleaning summary

write(" o Data cleaning summary", stderr())

timci::create_day28fu_qc_flowchart(n_raw_allday28fu_data_records,
                                   n_cdsa_pilot_day28fu_records,
                                   n_afterlock_pids_day28fu_records,
                                   n_nonvalid_pids_day28fu_records,
                                   n_edit_nonvalid_pid_day28fu_records,
                                   n_drop_nonvalid_pid_day28fu_records,
                                   n_inconsistent_name_day28fu_records,
                                   n_edit_inconsistent_name_day28fu_records,
                                   n_drop_inconsistent_name_day28fu_records,
                                   n_cleaned_allday28fu_records)

Data overview

write(" o Data overview", stderr())

fig_df <- allday28fu_data %>%
  dplyr::mutate(Status = dplyr::case_when(
    proceed_day28 == 1 ~ "Done",
    .default      = "Not done")) %>% 
  dplyr::mutate(week = lubridate::floor_date(as.Date(start),
                                             "week",
                                             week_start = getOption("lubridate.week.start", 1)))

fig_caption <- "Day 28 follow-up data overview over time by facility"
facility_col <- "fid"
date_col <- "week"
date_lbl <- "Weeks"
date_format <- "%b%y"
fill_col <- "Status"
comparison <- "type"

cat(knitr::knit_child('database_export_sub_facet_bar_plot.Rmd',
                      envir = environment(),
                      quiet = TRUE))

skimr::skim(allday28fu_data_no_pii)

Data export

write(" o Data export", stderr())

timci::dataset_export(raw_allday28fu_data,
                      "06a",
                      "timci_followup_day28_data",
                      rctls_dir,
                      "Raw Day 28 follow-up data")

timci::dataset_export(allday28fu_data_no_pii,
                      "06a",
                      "timci_followup_day28_data",
                      locked_db_dir,
                      "Cleaned Day 28 follow-up data")

rm(raw_allday28fu_data)
gc()

Thaliehln/timci documentation built on April 8, 2024, 3:38 p.m.