Person Id is changed by computePathways

[ablack3]

Describe the bug
computePatways returns person level results (treatmentHistory) but the person Ids are not preserved which makes it difficult to debug test cases.

To Reproduce

library(dplyr)
#> Warning: package 'dplyr' was built under R version 4.5.2
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
library(CDMConnector)

json <- c('
          {
  "person": [
    {
      "person_id": 2,
      "gender_concept_id": 8532,
      "year_of_birth": 1970,
      "month_of_birth": 4,
      "day_of_birth": 6,
      "birth_datetime": "1970-04-06",
      "race_concept_id": 0,
      "ethnicity_concept_id": 0,
      "location_id": 0,
      "provider_id": 0,
      "care_site_id": 0
    }
  ],
  "observation_period": [
    {
      "observation_period_id": 2,
      "person_id": 2,
      "observation_period_start_date": "2014-01-01",
      "observation_period_end_date": "2024-01-01",
      "period_type_concept_id": 32817
    }
  ],
  "visit_occurrence": [],
  "visit_detail": [],
  "drug_exposure": [
    {
      "drug_exposure_id": 1,
      "person_id": 2,
      "drug_concept_id": 1311078,
      "drug_exposure_start_date": "2017-11-08",
      "drug_exposure_start_datetime": "2017-11-08",
      "drug_exposure_end_date": "2017-11-09",
      "drug_exposure_end_datetime": "2017-11-09",
      "drug_type_concept_id": 38000177,
      "drug_source_value": "cytarabine"
    }
  ],
  "condition_occurrence": [
    {
      "condition_occurrence_id": 1,
      "person_id": 2,
      "condition_concept_id": 140352,
      "condition_start_date": "2016-05-05",
      "condition_start_datetime": "2016-05-05",
      "condition_end_date": "2023-07-20",
      "condition_end_datetime": "2023-07-20",
      "condition_type_concept_id": 32879,
      "provider_id": 0,
      "condition_source_value": "Acute myeloid leukemia, disease"
    }
  ],
  "procedure_occurrence": [],
  "measurement": []
}         
')
readr::write_file(json, file.path(tempdir(), "aml_tp.json"))

cdm <- TestGenerator::patientsCDM(tempdir(), "aml_tp", "5.4", "TP_test5_cdm")
#> ✖ Standard table(s) in test data: person, observation_period, visit_occurrence, visit_detail, drug_exposure, condition_occurrence, procedure_occurrence and measurement
#> ✔ Patients pushed to blank CDM successfully

cdm <- generateConceptCohortSet(cdm, conceptSet = list(aml = 140352,    cytarabine = 1311078), name = "cohort")

cohortCount(cdm$cohort) %>% 
  left_join(settings(cdm$cohort))
#> Joining with `by = join_by(cohort_definition_id)`
#> # A tibble: 2 × 8
#>   cohort_definition_id number_records number_subjects cohort_name limit
#>                  <int>          <int>           <int> <chr>       <chr>
#> 1                    1              1               1 aml         first
#> 2                    2              1               1 cytarabine  first
#> # ℹ 3 more variables: prior_observation <dbl>, future_observation <dbl>,
#> #   end <chr>

cdm$cohort
#> # Source:   table<cohort> [?? x 4]
#> # Database: DuckDB 1.4.4 [root@Darwin 25.2.0:R 4.5.1//private/var/folders/2j/8z0yfn1j69q8sxjc7vj9yhz40000gp/T/RtmpUleSLV/filefe693034dcde.duckdb]
#>   cohort_definition_id subject_id cohort_start_date cohort_end_date
#>                  <int>      <int> <date>            <date>         
#> 1                    1          2 2016-05-05        2024-01-01     
#> 2                    2          2 2017-11-08        2024-01-01

cohortSet <- settings(cdm$cohort) |> 
  select(
    cohortId = "cohort_definition_id",
    cohortName = "cohort_name"
  ) |> 
  mutate(type = case_when(
    stringr::str_detect(cohortName, "aml") ~ "target",
    TRUE ~ "event"
  ))


andr <- TreatmentPatterns::computePathways(
  cohorts = cohortSet,
  cohortTableName = "cohort",
  cdm = cdm,
  analysisId = 1,
  description = "",
  tempEmulationSchema = NULL,
  startAnchor = "startDate",
  windowStart = 0,
  endAnchor = "endDate",
  windowEnd = 0,
  minEraDuration = 1,
  splitEventCohorts = NULL,
  splitTime = NULL,
  eraCollapseSize = 30,
  combinationWindow = 7,
  minPostCombinationDuration = 14,
  filterTreatments = "First",
  maxPathLength = 10,
  overlapMethod = "truncate",
  concatTargets = TRUE
)
#> -- Qualifying records for cohort definitions: 1, 2
#>  Records: 2
#>  Subjects: 1
#> -- Removing records < minEraDuration (1)
#>  Records: 2
#>  Subjects: 1
#> >> Starting on target: 1 (aml)
#> -- Removing events outside window (startDate: 0 | endDate: 0)
#>  Records: 1
#>  Subjects: 1
#> -- splitEventCohorts
#>  Records: 1
#>  Subjects: 1
#> -- No eras needed Collapsing, eraCollapse (30)
#>  Records: 1
#>  Subjects: 1
#> -- After Combination
#>  Records: 1
#>  Subjects: 1
#> -- filterTreatments (First)
#>  Records: 1
#>  Subjects: 1
#> -- Max path length (10)
#>  Records: 1
#>  Subjects: 1
#> -- treatment construction done
#>  Records: 1
#>  Subjects: 1

andr$treatmentHistory %>% dplyr::collect() 
#> # A tibble: 1 × 14
#>   eventCohortId personId indexYear eventStartDate eventEndDate type    age sex  
#>   <chr>            <int>     <int>          <int>        <int> <chr> <dbl> <chr>
#> 1 2                    1      2016          17478        19723 event    47 FEMA…
#> # ℹ 6 more variables: targetCohortId <dbl>, n_target <dbl>, durationEra <int>,
#> #   sortOrder <dbl>, eventSeq <int>, eventCohortName <chr>

cdmDisconnect(cdm)
Andromeda::close(andr)

^{Created on 2026-02-17 with reprex v2.1.1}

Session info

sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#>  setting  value
#>  version  R version 4.5.1 (2025-06-13)
#>  os       macOS Tahoe 26.2
#>  system   aarch64, darwin20
#>  ui       X11
#>  language (EN)
#>  collate  en_US.UTF-8
#>  ctype    en_US.UTF-8
#>  tz       UTC
#>  date     2026-02-17
#>  pandoc   3.6.3 @ /Applications/RStudio.app/Contents/Resources/app/quarto/bin/tools/aarch64/ (via rmarkdown)
#>  quarto   1.8.27 @ /usr/local/bin/quarto
#> 
#> ─ Packages ───────────────────────────────────────────────────────────────────
#>  package           * version  date (UTC) lib source
#>  Andromeda           0.6.3    2023-03-26 [1] CRAN (R 4.5.1)
#>  arrow               22.0.0.1 2025-12-23 [1] CRAN (R 4.5.2)
#>  assertthat          0.2.1    2019-03-21 [1] CRAN (R 4.5.0)
#>  backports           1.5.0    2024-05-23 [1] CRAN (R 4.5.0)
#>  bit                 4.6.0    2025-03-06 [1] CRAN (R 4.5.0)
#>  bit64               4.6.0-1  2025-01-16 [1] CRAN (R 4.5.0)
#>  blob                1.3.0    2026-01-14 [1] CRAN (R 4.5.2)
#>  brio                1.1.5    2024-04-24 [1] CRAN (R 4.5.0)
#>  cachem              1.1.0    2024-05-16 [1] CRAN (R 4.5.0)
#>  CDMConnector      * 2.4.0    2026-02-16 [1] local
#>  cellranger          1.1.0    2016-07-27 [1] CRAN (R 4.5.0)
#>  checkmate           2.3.4    2026-02-03 [1] CRAN (R 4.5.2)
#>  cli                 3.6.5    2025-04-23 [1] CRAN (R 4.5.0)
#>  DBI                 1.2.3    2024-06-02 [1] CRAN (R 4.5.0)
#>  dbplyr              2.5.2    2026-02-13 [1] CRAN (R 4.5.2)
#>  digest              0.6.39   2025-11-19 [1] CRAN (R 4.5.2)
#>  dplyr             * 1.2.0    2026-02-03 [1] CRAN (R 4.5.2)
#>  duckdb              1.4.4    2026-01-28 [1] CRAN (R 4.5.2)
#>  evaluate            1.0.5    2025-08-27 [1] CRAN (R 4.5.0)
#>  farver              2.1.2    2024-05-13 [1] CRAN (R 4.5.0)
#>  fastmap             1.2.0    2024-05-15 [1] CRAN (R 4.5.0)
#>  fs                  1.6.6    2025-04-12 [1] CRAN (R 4.5.0)
#>  generics            0.1.4    2025-05-09 [1] CRAN (R 4.5.0)
#>  ggplot2             4.0.2    2026-02-03 [1] CRAN (R 4.5.2)
#>  glue                1.8.0    2024-09-30 [1] CRAN (R 4.5.0)
#>  gtable              0.3.6    2024-10-25 [1] CRAN (R 4.5.0)
#>  hms                 1.1.4    2025-10-17 [1] CRAN (R 4.5.0)
#>  htmltools           0.5.9    2025-12-04 [1] CRAN (R 4.5.2)
#>  jsonlite            2.0.0    2025-03-27 [1] CRAN (R 4.5.0)
#>  knitr               1.51     2025-12-20 [1] CRAN (R 4.5.2)
#>  lifecycle           1.0.5    2026-01-08 [1] CRAN (R 4.5.2)
#>  magrittr            2.0.4    2025-09-12 [1] CRAN (R 4.5.0)
#>  memoise             2.0.1    2021-11-26 [1] CRAN (R 4.5.0)
#>  omopgenerics        1.3.6    2026-01-28 [1] CRAN (R 4.5.2)
#>  openxlsx            4.2.8.1  2025-10-31 [1] CRAN (R 4.5.0)
#>  otel                0.2.0    2025-08-29 [1] CRAN (R 4.5.0)
#>  pillar              1.11.1   2025-09-17 [1] CRAN (R 4.5.0)
#>  pkgconfig           2.0.3    2019-09-22 [1] CRAN (R 4.5.0)
#>  purrr               1.2.1    2026-01-09 [1] CRAN (R 4.5.2)
#>  R6                  2.6.1    2025-02-15 [1] CRAN (R 4.5.0)
#>  RColorBrewer        1.1-3    2022-04-03 [1] CRAN (R 4.5.0)
#>  Rcpp                1.1.1    2026-01-10 [1] CRAN (R 4.5.2)
#>  readr               2.1.6    2025-11-14 [1] CRAN (R 4.5.2)
#>  readxl              1.4.5    2025-03-07 [1] CRAN (R 4.5.0)
#>  reprex              2.1.1    2024-07-06 [1] CRAN (R 4.5.0)
#>  rJava               1.0-11   2024-01-26 [1] CRAN (R 4.5.0)
#>  rlang               1.1.7    2026-01-09 [1] CRAN (R 4.5.2)
#>  rmarkdown           2.30     2025-09-28 [1] CRAN (R 4.5.0)
#>  RSQLite             2.4.4    2025-11-10 [1] CRAN (R 4.5.0)
#>  rstudioapi          0.18.0   2026-01-16 [1] CRAN (R 4.5.2)
#>  S7                  0.2.1    2025-11-14 [1] CRAN (R 4.5.2)
#>  scales              1.4.0    2025-04-24 [1] CRAN (R 4.5.0)
#>  sessioninfo         1.2.3    2025-02-05 [1] CRAN (R 4.5.0)
#>  snakecase           0.11.1   2023-08-27 [1] CRAN (R 4.5.0)
#>  stringi             1.8.7    2025-03-27 [1] CRAN (R 4.5.0)
#>  stringr             1.6.0    2025-11-04 [1] CRAN (R 4.5.0)
#>  TestGenerator       0.5.0    2026-01-14 [1] CRAN (R 4.5.2)
#>  testthat            3.3.2    2026-01-11 [1] CRAN (R 4.5.2)
#>  tibble              3.3.1    2026-01-11 [1] CRAN (R 4.5.2)
#>  tidyr               1.3.2    2025-12-19 [1] CRAN (R 4.5.2)
#>  tidyselect          1.2.1    2024-03-11 [1] CRAN (R 4.5.0)
#>  TreatmentPatterns   3.1.2    2026-02-16 [1] local
#>  tzdb                0.5.0    2025-03-15 [1] CRAN (R 4.5.0)
#>  utf8                1.2.6    2025-06-08 [1] CRAN (R 4.5.0)
#>  vctrs               0.7.1    2026-01-23 [1] CRAN (R 4.5.2)
#>  withr               3.0.2    2024-10-28 [1] CRAN (R 4.5.0)
#>  xfun                0.56     2026-01-18 [1] CRAN (R 4.5.2)
#>  yaml                2.3.12   2025-12-10 [1] CRAN (R 4.5.2)
#>  zip                 2.3.3    2025-05-13 [1] CRAN (R 4.5.0)
#> 
#>  [1] /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/library
#>  * ── Packages attached to the search path.
#> 
#> ──────────────────────────────────────────────────────────────────────────────

Notice that the person id in this example was changed from 2 to 1.

Expected behavior
Person ID in the output should match the subject_id in the input cohorts

[mvankessel-EMC]

Correct. The person_id maps to the person_id in andr$cohortTable, which contains subject_id_origin which maps to the original subject_id's in the cohort table.

The reason for this is person_id's in the person table can be anything. Which on SQLite could case issues or significant slow downs.

[ablack3]

I thought the person_id has to be an integer (or bigint).
https://ohdsi.github.io/CommonDataModel/cdm54.html#person

It was making it difficult to check test cases when the person_id in the treatment patterns table does not match the input data.

@antonbarchuk Can explain as well.

[mvankessel-EMC]

I thought the person_id has to be an integer (or bigint).
https://ohdsi.github.io/CommonDataModel/cdm54.html#person
Image

Yes you are correct. On second thought I think the actual reason is that with Andromeda and R, 64bit integers could get rounded.

This snippet should add the subject_id_origin to the treatment history:

andr$treatmentHistory |>
  dplyr::left_join(
    andr$cohortTable |>
      dplyr::select("personId", "subject_id_origin"), by = "personId")
  )