library(IncidencePrevalence)
library(dplyr)
library(tidyr)
cdm <- mockIncidencePrevalenceRef(
sampleSize = 20000,
earliestObservationStartDate = as.Date("1960-01-01"),
minOutcomeDays = 365,
outPre = 0.3
)
cdm <- generateDenominatorCohortSet(
cdm = cdm, name = "denominator",
cohortDateRange = c(as.Date("1990-01-01"), as.Date("2009-12-31")),
ageGroup = list(c(0, 150)),
sex = "Both",
daysPriorObservation = 0
)
cdm$denominator %>%
glimpse()
#> Rows: ??
#> Columns: 4
#> Database: DuckDB v1.0.0 [eburn@Windows 10 x64:R 4.2.1/:memory:]
#> $ cohort_definition_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
#> $ subject_id <int> 1, 3, 10, 12, 14, 16, 18, 19, 20, 22, 23, 25, 27,…
#> $ cohort_start_date <date> 1991-08-05, 2007-02-16, 2009-04-21, 1992-01-28, …
#> $ cohort_end_date <date> 1996-01-10, 2007-12-09, 2009-12-31, 1999-08-18, …
Using estimatePointPrevalence()
Let´s first calculate point prevalence on a yearly basis.
prev <- estimatePointPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Years",
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 144
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2147", "82", "0.0381928272007452", "0.03087585700949…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-01-01 &&& 1990-01-01", "1990-01-01 &&& 1990-01-…
plotPrevalence(prev, ylim = c(0, NA))
We can also calculate point prevalence by calendar month.
prev <- estimatePointPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Months",
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 1,244
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2147", "82", "0.0381928272007452", "0.03087585700949…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-01-01 &&& 1990-01-01", "1990-01-01 &&& 1990-01-…
plotPrevalence(prev, ylim = c(0, NA))
By using the estimatePointPrevalence() function, we can further
specify where to compute point prevalence in each time interval (start,
middle, end). By default, this parameter is set to start. But we can use
middle instead like so:
prev <- estimatePointPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Years",
timePoint = "middle",
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 144
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2160", "76", "0.0351851851851852", "0.02820349824624…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-07-01 &&& 1990-07-01", "1990-07-01 &&& 1990-07-…
plotPrevalence(prev, ylim = c(0, NA))
Using estimatePeriodPrevalence()
To calculate period prevalence by year (i.e. each period is a
calendar year)
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Years",
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 144
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2523", "189", "0.074910820451843", "0.06527258851403…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-01-01 &&& 1990-12-31", "1990-01-01 &&& 1990-12-…
plotPrevalence(prev)
To calculate period prevalence by month (i.e. each period is a
calendar month)
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Months",
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 1,244
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2176", "94", "0.0431985294117647", "0.03543109553945…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-01-01 &&& 1990-01-31", "1990-01-01 &&& 1990-01-…
plotPrevalence(prev, ylim = c(0, NA))
When using the estimatePeriodPrevalence() function, we can set the
fullContribution parameter to decide whether individuals are required to
be present in the database throughout the interval of interest in order
to be included (fullContribution=TRUE). If not, individuals will only be
required to be present for one day of the interval to contribute
(fullContribution=FALSE), which would be specified like so:
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
interval = "Months",
fullContribution = FALSE,
minCellCount = 0
)
prev %>%
glimpse()
#> Rows: 1,244
#> Columns: 13
#> $ result_id <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
#> $ cdm_name <chr> "mock", "mock", "mock", "mock", "mock", "mock", "mock…
#> $ group_name <chr> "denominator_cohort_name", "denominator_cohort_name",…
#> $ group_level <chr> "denominator_cohort_1", "denominator_cohort_1", "deno…
#> $ strata_name <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ strata_level <chr> "overall", "overall", "overall", "overall", "overall"…
#> $ variable_name <chr> "outcome_cohort_name", "outcome_cohort_name", "outcom…
#> $ variable_level <chr> "cohort_1", "cohort_1", "cohort_1", "cohort_1", "coho…
#> $ estimate_name <chr> "denominator_count", "outcome_count", "prevalence", "…
#> $ estimate_type <chr> "integer", "integer", "numeric", "numeric", "numeric"…
#> $ estimate_value <chr> "2176", "94", "0.0431985294117647", "0.03543109553945…
#> $ additional_name <chr> "prevalence_start_date &&& prevalence_end_date", "pre…
#> $ additional_level <chr> "1990-01-01 &&& 1990-01-31", "1990-01-01 &&& 1990-01-…
plotPrevalence(prev)
Stratified analyses
If we specified multiple denominator populations results will be
returned for each. Here for example we define three age groups for
denominator populations and get three sets of estimates back when
estimating prevalence.
cdm <- generateDenominatorCohortSet(
cdm = cdm, name = "denominator_age_sex",
cohortDateRange = c(as.Date("1990-01-01"), as.Date("2009-12-31")),
ageGroup = list(c(0, 39),
c(41, 65),
c(66, 150)),
sex = "Both",
daysPriorObservation = 0
)
#> ℹ Creating denominator cohorts
#> ✔ Cohorts created in 0 min and 5 sec
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator_age_sex",
outcomeTable = "outcome",
minCellCount = 0
)
#> Getting prevalence for analysis 1 of 3
#> Getting prevalence for analysis 2 of 3
#> Getting prevalence for analysis 3 of 3
#> Time taken: 0 mins and 1 secs
plotPrevalence(prev, facet = "denominator_age_group")
While we specify time-varying stratifications when defining our
denominator populations, if we have time-invariant stratifications we
can include these at the the estimation stage. To do this we first need
to add a new column to our denominator cohort with our stratification
variable. Here we´ll add an example stratification just to show the
idea. Note, as well as getting stratified results we´ll also get overall
results.
cdm$denominator <- cdm$denominator %>%
mutate(group = if_else(as.numeric(subject_id) < 500, "first", "second"))
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
strata = "group",
minCellCount = 0
)
#> Getting prevalence for analysis 1 of 1
#> Time taken: 0 mins and 1 secs
plotPrevalence(prev,
facet = "strata_level")
We can also stratify on multiple variables at the same time.
cdm$denominator <- cdm$denominator %>%
mutate(group_1 = if_else(as.numeric(subject_id) < 1500, "first", "second"),
group_2 = if_else(as.numeric(subject_id) < 1000, "one", "two"))
prev <- estimatePeriodPrevalence(
cdm = cdm,
denominatorTable = "denominator",
outcomeTable = "outcome",
strata = list(c("group_1"), # for just group_1
c("group_2"), # for just group_2
c("group_1", "group_2")), # for group_1 and group_2
minCellCount = 0
)
#> Getting prevalence for analysis 1 of 1
#> Time taken: 0 mins and 1 secs
plotPrevalence(prev,
facet = "strata_level")
Other parameters
In the examples above, we have used calculated prevalence by months
and years, but it can be also calculated by weeks, months or for the
entire time period observed (overall). In addition, the user can decide
whether to include time intervals that are not fully captured in the
database (e.g., having data up to June for the last study year when
computing period prevalence rates). By default, incidence will only be
estimated for those intervals where the database captures all the
interval (completeDatabaseIntervals=TRUE).
Given that we can set estimatePointPrevalence() and
estimatePeriorPrevalence() to exclude individuals based on
certain parameters (e.g., fullContribution), it is important to note
that the denominator population used to compute prevalence rates might
differ from the one calculated with
generateDenominatorCohortSet().
The user can also set the minimum number of events to be reported,
below which results will be obscured. By default, results with <5
occurrences are blinded, but if minCellCount=0, all results will be
reported. 95 % confidence intervals are calculated using the Wilson
Score method. In addition, we can set verbose=TRUE to report progress as
code is running. By default, no progress is reported
(verbose=FALSE).
