hinna0818/ukbanalytica_v2/ukbsci-cohort

library(UKBAnalytica)
library(data.table)
 
# dt is the data.table produced by rap_extract_pheno() / rap_submit_extract()
stopifnot(data.table::is.data.table(dt))
stopifnot("eid" %in% colnames(dt))
stopifnot("p53_i0" %in% colnames(dt))   # baseline date

defs_all <- get_predefined_diseases()
names(defs_all)
#> "AA", "TAA", "AAA", "CVD", "MI", "HF", "Stroke", "Hypertension",
#> "Diabetes", "T1DM", "T2DM", "Atrial_Fibrillation", "Lung_Cancer", ...
 
# Subset to your study endpoints
diseases <- defs_all[c("AA", "Hypertension", "Diabetes")]

# Code-level table: source, code_system, field_id, code, validation_status
get_disease_catalog(disease = "COPD")
get_disease_catalog(disease = "diabetes", code_system = "ICD-10")
 
# Pomegranate-derived disease definitions that current parsers can use
pom_defs <- get_predefined_diseases(source = "pomegranate")
 
# Matched curated + Pomegranate definitions.
# "intersection" is conservative; "union" expands matched code sets and
# retains unmatched definitions from both sources.
shared_defs <- get_predefined_diseases(
  source = "both",
  merge_type = "intersection"
)
expanded_defs <- get_predefined_diseases(
  source = "both",
  merge_type = "union"
)

copd_def <- create_disease_definition(
  name             = "COPD",
  icd10_pattern    = "^J4[0-4]",        # J40-J44
  icd9_pattern     = "^49[0-2]",        # 490-492
  sr_codes         = c(1112, 1113, 1472),
  death_icd10      = "^J4[0-4]",
  opcs4_pattern    = NULL,
  algo_date_field   = 42016,            # UKB algorithmic COPD date field
  algo_source_field = 42017             # Source: hospital / death / algorithm
)

lung_ca_def <- create_disease_definition(
  name                 = "LungCancer_strict",
  cancer_icd10_pattern = "^C34",
  cancer_histology     = c(8070, 8071, 8140, 8240),   # squamous, adenoca, etc.
  cancer_behaviour     = 3L                            # malignant only
)

cvd_composite <- combine_disease_definitions(
  defs_all$MI, defs_all$Stroke, defs_all$HF,
  name = "MACE"
)

icd10 <- parse_icd10_diagnoses(dt)
# → eid, icd10_code, diag_date (Date), source = "ICD10"
 
icd9  <- parse_icd9_diagnoses(dt)
opcs4 <- parse_opcs4_procedures(dt)
canc  <- parse_cancer_registry(dt)
# → cancer_icd10_code, cancer_histology, cancer_behaviour, diag_date
 
death <- parse_death_records(dt)
# → death_code, death_date, source = "Death", cause_type (primary/secondary)
 
dod   <- get_death_dates(dt)
# → eid, death_date  (earliest per participant — for censoring)
 
sr    <- parse_self_reported_illnesses(dt, baseline_col = "p53_i0")
# → sr_code, diag_date (month-precision, imputed to day 15), instance, array_idx

mi_def <- get_predefined_diseases(
  source = "both",
  merge_type = "union",
  disease = "MI"
)
 
mi_dx <- extract_disease_diagnosis(
  dt                  = dt,
  disease             = "MI",
  disease_definitions = mi_def,
  sources             = c("ICD10", "ICD9", "Death"),
  censor_date         = as.Date("2023-10-31"),
  baseline_col        = "p53_i0",
  include_all         = TRUE
)
# Columns: eid, disease, diagnosed, prevalent_case, incident_case,
# earliest_date, diagnosis_source, status, surv_time

cases_long <- extract_cases_by_source(
  dt                  = dt,
  disease_definitions = diseases,
  sources             = c("ICD10", "ICD9", "Self-report", "Death",
                          "OPCS4", "CancerRegistry",
                          "FirstOccurrence", "Algorithm"),
  censor_date  = as.Date("2023-10-31"),
  baseline_col = "p53_i0"
)
str(cases_long)
#> eid, disease, status, surv_time, prevalent_case,
#> earliest_date, diagnosis_source

history <- extract_disease_history(
  dt                  = dt,
  diseases            = c("Hypertension", "Diabetes"),
  disease_definitions = defs_all,
  sources             = c("ICD10", "ICD9", "Self-report"),
  baseline_col        = "p53_i0"
)
#> Adds columns: Hypertension_history (0/1), Diabetes_history (0/1)

sens <- extract_disease_history_sensitivity(
  dt                  = dt,
  diseases            = c("Diabetes"),
  disease_definitions = defs_all,
  baseline_col        = "p53_i0"
)
#> Adds: Diabetes_history_ICD10, Diabetes_history_hospital, Diabetes_history_all

qc <- compare_data_sources(
  dt                  = dt,
  disease_definitions = diseases,
  baseline_col        = "p53_i0"
)

time_skel <- ukb_time_skeleton(
  data                 = dt,
  id_col               = "eid",
  baseline_col         = "p53_i0",
  birth_year_col       = "p34",
  birth_month_col      = "p52",
  age_col              = "p21022",
  death_date_cols      = "^(participant\\.)?p40000_i[0-9]+$",
  lost_to_followup_col = "p191",
  admin_censor_date    = as.Date("2023-10-31")
)

cohort <- build_survival_dataset(
  dt                  = dt,
  disease_definitions = diseases,
  prevalent_sources   = c("ICD10", "ICD9", "Self-report", "Death"),
  outcome_sources     = c("ICD10", "ICD9", "Death"),
  censor_date         = as.Date("2023-10-31"),
  baseline_col        = "p53_i0",
  time_skeleton       = time_skel,
  primary_disease     = "AA",          # one key, or a vector for independent endpoints
  output              = "wide",        # or "long"
  include_all         = TRUE,
  show_flow           = TRUE,
  dt_threads          = 8
)
 
# Inspect attrition
flow <- attr(cohort, "participant_flow")
if (!is.null(flow)) print(flow)