Fixed case count in createStudyPopulation() when restricting time i…

…n prior `getDbSccsData()` call, e.g. by defining a study period and/or nesting cohort.

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: SelfControlledCaseSeries
 Type: Package
 Title: Self-Controlled Case Series
-Version: 5.1.1
-Date: 2024-01-29
+Version: 5.1.2
+Date: 2024-05-22
 Authors@R: c(
   person("Martijn", "Schuemie", , "schuemie@ohdsi.org", role = c("aut", "cre")),
 	person("Patrick", "Ryan", role = c("aut")),
@@ -55,6 +55,6 @@ Remotes:
 License: Apache License 2.0
 LinkingTo: Rcpp
 NeedsCompilation: yes
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 Roxygen: list(markdown = TRUE)
 Encoding: UTF-8

NEWS.md

@@ -1,3 +1,13 @@
+SelfControlledCaseSeries 5.1.2
+==============================
+
+Bugfixes
+
+1. Fixed error in SQL about "#case_in_period".
+
+2. Fixed case count in `createStudyPopulation()` when restricting time in prior `getDbSccsData()` call, e.g. by defining a study period and/or nesting cohort.
+
+
 SelfControlledCaseSeries 5.1.1
 ==============================
 

R/StudyPopulation.R

@@ -248,6 +248,14 @@ createStudyPopulation <- function(sccsData,
   metaData$outcomeId <- unique(outcomes$eraId)
   metaData$attrition <- attrition
 
+  # Restrict cases to those that have at least one outcome between start and end:
+  cases <- outcomes %>%
+    select("caseId", "eraStartDay") %>%
+    inner_join(cases,
+               by = join_by("caseId", between("eraStartDay", "startDay", "endDay"))) %>%
+    select(-"eraStartDay") %>%
+    distinct()
+
   cases <- cases %>%
     select("observationPeriodId", "caseId", "personId", "observationPeriodStartDate", "ageAtObsStart", "startDay", "endDay", "noninformativeEndCensor")
 
@@ -263,7 +271,7 @@ createStudyPopulation <- function(sccsData,
 
 countOutcomes <- function(outcomes, cases, description) {
   counts <- outcomes %>%
-    inner_join(cases, by = join_by("caseId")) %>%
+    inner_join(cases, by = join_by("caseId"), between("eraStartDay", "startDay", "endDay")) %>%
     group_by(.data$eraId) %>%
     summarise(
       outcomeSubjects = n_distinct(.data$personId),