SENDAs Agreement 1 Codebook

load("G:/My Drive/Alvacast/SISTRAT 2023/data/20241015_out/26_ndp_2025_10_01.Rdata")

library(dplyr)

Adjuntando el paquete: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

library(codebook)
library(labelled)

Adjuntando el paquete: 'labelled'

The following object is masked from 'package:codebook':

    to_factor

# Manual variable labels definition for the specified main variables
# Based on TSV descriptions where available, inferred from provided information for others
# This includes the variables you listed, including hash_key as per your list
# Apply to SISTRAT23_c1_2010_2024_df_prev1y and generate codebook
# Manual variable labels definition for the specified main variables
# Based on TSV descriptions where available, inferred from provided information for others
# This includes the variables you listed, including hash_key as per your list
# Apply to SISTRAT23_c1_2010_2024_df_prev1y and generate codebook

labels_map <- list(
  "TABLE" = "Year of data collection (original SISTRAT table/year identifier). Represents the year the record was entered (e.g., \"2023\", \"2015\"). No transformation applied. Made in import_c1_top_data_adm_25.qmd",
  "TABLE_rec_series" = "Recoded series of TABLE",
  "rn" = "Row number or treatment episode sequence per patient. Created by `row_number() over (partition by hash_key order by adm_date)`, Step 1 (SISTRAT23_c1_2010_2024_df2). Identifies first, second, etc., treatment for each user.",
  "rn_series" = "Series of row number",
  "num_trat_ant" = "Number of prior treatments reported by patient. Direct import. May not be reliable. Not used.",
  "fecha_ultimo_tratamiento" = "Patient-reported time since last treatment (e.g., \"3 a 4 anos\"). Direct import. Categorical, not numeric. Many missing values (~50%)",
  "hash_key" = "Unique anonymized identifier for each individual (user/patient RUT derivative). Direct import from raw SISTRAT C1. Originally in uppercase letter. Generated by hashing the RUT (national ID) by MINSAL. Used to link multiple treatment episodes for the same person across years. No transformation.",
  "min_adm_age_rec3" = "min(adm_age_rec3) grouped by hash_key. Critical benchmark for validating/imputing onset ages.",
  "adm_age_rec3" = "Admission age [log1p(x)=adm_age_log, centered= adm_age_c,^2=adm_age_pow2, ^3=adm_age_pow3, three groups= adm_age_rec3_cat]",
  "birth_date_rec" = "Final authoritative date of birth. Created by selecting/imputing best `birth_date` per `hash_key` (via `kNN`, logic, or min/max validation). Used to recalculate `adm_age_rec`.",
  "adm_date_num_rec2" = "Numeric admission date recoded version 2",
  "adm_date_rec2" = "Intermediate admission date Created in Step 2 (0.c) for the resolution of overlaps",
  "dit_rec6" = "Length of stay in treatment (months) [log1p(x)=treat_log, ^2=treat_days_pow2, ^3=treat_days_pow3, <90days=treat_lt_90]",
  "disch_date_rec6" = "Final discharge date for longitudinal analysis. Created as selected consistent version for time-to-event modeling.",
  "disch_date_num_rec6_trans" = "Imputed discharge based on reference date Created in Step 3. Missing discharge dates were filled using a default value calculated from a fixed retrieval date (e.g., May 28, 2025), ensuring consistency across all treatment records and uncovering censorship mechanisms.",
  "def_date" = "Date of death (if applicable, mostly NA). Created from external mortality linkage (not in provided scripts). Parsed from mortality registry (dia_def, mes_def, ano_def), imputing missing day as 15; earliest date kept when multiple. Used to censor discharges after death. See Duplicates_25_2.qmd (pre-00.a).",
  "adm_motive" = "Admission motive",
  "tr_compliance_rec7" = "Treatment compliance category. Created in Step 4. Removed cases (n=3) with an ongoing treatment motive but with a posterior treatment after. Replaced for dropout (they had incomplete discharge information)",
  "adm_disch_reason" = "Placeholder for administrative discharge reason (mostly empty). Created as copy of `motivo_de_egreso_alta_administrativa`. Derived/translated from motivo_de_egreso_alta_administrativa; listed among deduplication key variables in Step 2. 47%-56% missing in patients with adm. discharge.",
  "referral_type" = "Recoded type of referral center. Created from `tipo_centro_derivacion` (translation): e.g., \"otro centro\" , \"other facility\", \"cosam\", \"primary health care\".",
  "plan_type" = "Recoded treatment plan type. Created as copy and translation of `tipo_de_plan` (step 1). Used in collapsing logic and outcome modeling.",
  "id_centro" = "Center ID number. Direct import. Used to link center attributes, collapse duplicates, and derive `centro_muj` (women-specific centers).",
  "senda" = "Indicator if treatment was under SENDA agreement (\"si\"/\"no\"). Direct import. Used to derive `senda_adm_date` and flag SENDA-specific episodes. No transformation initially. According to SENDA professionals, patients may be in SENDA Yes programs may anyways part of SENDA programs in some cases",
  "pub_center" = "Binary indicator for public center. Created as `tipo_centro == \"publico\"`. Used in institutional comparisons.",
  "primary_sub" = "Primary substance of use",
  "second_sub1" = "Normalized secondary substances at admission (1)",
  "second_sub2" = "Normalized secondary substances at admission (2)",
  "second_sub3" = "Normalized secondary substances at admission (3)",
  "prim_sub_freq" = "Frequency of primary substance use at admission (recoded: prim_sub_freq_rec)",
  "prim_sub_route" = "Recoded route of administration. Created from `via_administracion_sustancia_principal` into standardized terms.",
  "LB_age_primary_onset_rec2" = "Lower bound age of primary substance onset recoded 2",
  "UB_age_primary_onset_rec2" = "Upper bound age of primary substance onset recoded 2",
  "age_primary_onset_rec2" = "Created in Step 3.",
  "first_sub_used" = "Normalized first substance used. Created as `tolower(gsub(\"_\", \" \", sustancia_de_inicio))`. Input for resolving inconsistencies, prioritizing most vulnerable value = `sus_ini_mod_mvv`. Despite this, this variable was normalized in Step 3 for inconsistent values in patients.",
  "sus_ini_mod_mvv" = "Sus ini mod mvv",
  "sus_ini_1" = "Sus ini 1",
  "sus_ini_2" = "Sus ini 2",
  "sus_ini_3" = "Sus ini 3",
  "LB_age_subs_onset_rec2" = "Lower bound age of substance onset recoded 2",
  "UB_age_subs_onset_rec2" = "Upper bound age of substance onset recoded 2",
  "age_subs_onset_rec2" = "Created in Step 3.",
  "biopsych_comp" = "Recoded biopsychosocial severity. Created from `compromiso_biopsicosocial`: e.g., \"moderado\", \"2-moderate\".",
  "mod_psiq_cie_10" = "Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses",
  "mod_psiq_dsm_iv" = "Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses",
  "diagnostico_trs_fisico" = "Physical health diagnosis. Direct import. Often concatenated (e.g., \"Hepatitis alcoholica: cardiopatías\"). Preserved as-is for clinical profiling.",
  "otros_probl_at_sm_or" = "Other mental health issues (e.g., \"abuso sexual\"). Direct import. Recoded to `otros_probl_at_sm_or`. Used in vulnerability and trauma profiling.",
  "sub_dep_icd10_status" = "Severity of Substance Use Disorder (SUD)",
  "evaluacindelprocesoteraputico" = "Therapeutic process evaluation (e.g., \"logro alto\"). Direct import. Recoded to standardized categories. Used in outcome and program effectiveness analysis.",
  "eva_consumo" = "Evaluation of consumption pattern at discharge. Direct import. Part of multi-domain outcome assessment. Recoded similarly.",
  "eva_fam" = "Family situation evaluation at discharge. Direct import.",
  "eva_relinterp" = "Interpersonal relations evaluation at discharge. Direct import.",
  "eva_ocupacion" = "Occupational situation evaluation at discharge. Direct import.",
  "eva_sm" = "Mental health evaluation at discharge. Direct import.",
  "eva_fisica" = "Physical health evaluation at discharge. Direct import.",
  "eva_transgnorma" = "Social norm transgression evaluation at discharge. Direct import.",
  "dg_global_nec_int_soc_or" = "Global social integration need at admission. Direct import. Recoded to `dg_global_nec_int_soc_or`. Categorized as \"altas\", \"medias\", \"bajas\". Used in social vulnerability index.",
  "dg_nec_int_soc_cap_hum_or" = "Human capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_hum_or`. Part of social integration profile.",
  "dg_nec_int_soc_cap_fis_or" = "Physical capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_fis_or`.",
  "dg_nec_int_soc_cap_soc_or" = "Social capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_soc_or`.",
  "dg_global_nec_int_soc_egr_or" = "Global social integration need at discharge. Direct import. Recoded similarly to admission version (_60). Used for delta/change analysis.",
  "dg_nec_int_soc_cap_hum_egr_or" = "Human capital need at discharge. Direct import.",
  "dg_nec_int_soc_cap_fis_egr_or" = "Physical capital need at discharge. Direct import.",
  "dg_nec_int_soc_cap_soc_egr_or" = "Social capital need at discharge. Direct import.",
  "usuario_tribunal_trat_droga" = "Court-referred to drug treatment (very unbalanced, ~1% yes)",
  "nationality_cons" = "Recoded/standardized from nacionalidad or pais_nacimiento.",
  "ethnicity_c1_c6_historic" = "Concatenated unique non-Chilean/non-\"no pertenece\" values from etnia (C1) and ethnicity (C6), grouped by hash_key.",
  "discapacidad" = "Indicator of disability (\"si\"/\"no\"). Direct import. Used with `opcion_discapacidad` for disability profiling. Starts coding in 2019",
  "opcion_discapacidad" = "Type of disability (e.g., \"de causa psiquica\"). Direct import. Only populated if `discapacidad == \"si\"`. Used in accessibility and needs assessment.Starts coding in 2019",
  "sex_rec" = "Sex (often used for biological categorization)",
  "identidad_de_genero" = "Gender identity (e.g., \"masculino\", \"femenino\"). Direct import. Recoded to `identidad_de_genero` factor. Used to validate/override `sexo` in `sex_rec` (Step 2). Starts coding in 2019",
  "orientacion_sexual" = "Sexual orientation (e.g., \"heterosexual\"). Direct import. Sparse. Preserved for inclusivity analysis.Starts coding in 2022",
  "pregnant" = "Recoded pregnancy status at admission. Created from `se_trata_de_una_mujer_embarazada` (NA = \"no\"). Used in gender-specific analysis (Step 3). This variable (indicating if a woman is pregnant) seems to beintroduced in 2011.",
  "pregnant_disch" = "Recoded pregnancy status at discharge. Created from `ha_estado_embarazada_egreso`. Used in gender-specific analysis (Step 3). Sparse. Seems to be only accurately collected starting in 2017. Created to capture pregnancy status specifically at treatment discharge.",
  "marital_status" = "Marital status",
  "tiene_menores_de_edad_a_cargo" = "Indicator if responsible for minors (\"si\"/\"no\"). Direct import. Mostly missing before 2015 (Duplicates_25.txt). Recoded to binary flag. Used in family vulnerability index.",
  "num_hijos_trat_res" = "Number of children entering residential treatment with patient. Direct import. Often missing or 0. Later used to derive binary flag `hijos_trat_res` (\"Had children in treatments\").",
  "numero_de_hijos" = "Number of children reported by patient. Direct import. Values >11 flagged as implausible (Duplicates_25.txt). Used in `kNN` imputation and to derive `tiene_menores_de_edad_a_cargo`.",
  "con_quien_vive" = "Living arrangement/Cohabitation status",
  "tipo_de_vivienda" = "Type of housing",
  "precariedad_vivienda" = "Precarious housing. Direct import. Available since 2022 databases.",
  "tenure_status_household" = "Housing situation",
  "servicios_basicos_95" = "Basic sanitation services. Direct import. Available since 2022 databases.",
  "perso_dormitorio_vivienda" = "Persons per dwelling bedroom Direct import. Available since 2022 databases.",
  "ed_attainment" = "Recoded education level. Created from `escolaridad_ultimo_ano_cursado` into standardized categories (e.g., \"media incompleta\" = \"2-Completed high school or less\").",
  "occupation_condition" = "Recoded employment status. Created from `condicion_ocupacional`: e.g., \"cesante\"= \"unemployed\" (in Step 1).",
  "occupation_status" = "Recoded employment category. Created from `categoria_ocupacional`. Sparse; often NA.",
  "rubro_trabaja" = "Occupational sector (e.g., \"trabajadores no calificados\"). Direct import. Recoded to `rubro_trabaja_mod`. 68% missing. 13.8% among employeed",
  "laboral_ingresos" = "Monthly income. Direct import. Available since 2022 databases.",
  "yr_block" = "Birth year block (e.g., 1980, 1990) for anonymization or grouping. Created by rounding `birth_date` year to nearest decade (e.g., `floor(year(birth_date)/10)*10`). To look for data similarities (Step 1)",
  "OBS_series" = "OBS series",
  "senda_series" = "SENDA series",
  "pub_center_series" = "Public center series",
  "id_centro_series" = "Center ID series",
  "disch_date_num_rec6" = "Numeric discharge date recoded 6",
  "dg_psiq_cie_10_instudy" = "Psychiatric comorbidity (ICD-10)",
  "dg_psiq_cie_10_dg" = "Mutually exclusive (as corrected in Step 3)",
  "dg_psiq_dsm_iv_instudy" = "Psychiatric comorbidity (DSM-IV)",
  "dg_psiq_dsm_iv_dg" = "Mutually exclusive (as corrected in Step 3)",
  "plan_type_series" = "Plan type series",
  "tr_compliance_rec7_series" = "Treatment compliance recoded 7 series",
  "referral_type_series" = "Referral type series",
  "adm_age_rec3_series" = "Admission age recoded 3 series",
  "adm_date_rec2_series" = "Admission date recoded 2 series",
  "disch_date_rec6_series" = "Discharge date recoded 6 series",
  "diagnostico_trs_fisico_series" = "Physical diagnosis series",
  "otros_probl_at_sm_or_series" = "Other mental health problems series",
  "OBS" = "Observed flags or notes from cleaning (e.g., \"Duplicated Cases\"). Created during duplicate detection and resolution. Contains manual or automated flags for data quality issues, removed entries, etc. It is separated by semi-colons",
  "occupation_status_corr" = "Corrected employment status Created in Step 4. Only kept for employed; nulled for inactive/unemployed; filled as 'other' if missing. Depends on occupation_condition_inferred, occupation_status.",
  "occupation_condition_corr24" = "Employment status",
  "plan_type_corr" = "Treatment modality",
  "ed_attainment_corr" = "Educational attainment",
  "polysubstance_strict" = "Polysubstance use",
  "icd10_diag1" = "ICD10 diagnosis 1 Created in Step 4. Separated from mod_psiq_cie_10 by \"::\". Depends on mod_psiq_cie_10.",
  "icd10_diag2" = "ICD10 diagnosis 2 Created in Step 4. Separated from mod_psiq_cie_10 by \"::\". Depends on mod_psiq_cie_10.",
  "icd10_diag3" = "ICD10 diagnosis 3 Created in Step 4. Separated from mod_psiq_cie_10 \"::\". Depends on mod_psiq_cie_10.",
  "dsmiv_diag1" = "DSMIV diagnosis 1 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
  "dsmiv_diag2" = "DSMIV diagnosis 2 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
  "dsmiv_diag3" = "DSMIV diagnosis 3 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
  "adm_year" = "Admission year",
  "porc_pobr" = "Poverty index of the commune of residence [log1p(x)=porc_pobr_log, centered= porc_pobr_c, six quantile groups= porc_pobr_c_cat6]",
  "clasificacion" = "Urbanization level of the commune of residence",
  "km2_c" = "Centered km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.km_2 - mean(km_2). Depends on km_2.",
  "km2_log" = "Log km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.log1p(km_2). Depends on km_2.",
  "porc_pobr_log" = "Log poverty Created in Step 3. Re-joined in Step 4. log1p(porc_pobr). Depends on porc_pobr.",
  "porc_pobr_c" = "Centered poverty Created in Step 3. Re-joined in Step 4. porc_pobr - mean(porc_pobr). Depends on porc_pobr."
  # Removed "disch_date_real" as it doesn't exist in the dataframe
)


var_label(SISTRAT23_c1_2010_2024_df_prev1y) <- labels_map

# Subset to these variables for codebook (removed disch_date_real)
main_vars <- c("TABLE", "TABLE_rec_series", "rn", "rn_series", "num_trat_ant", 
"fecha_ultimo_tratamiento", "hash_key", "min_adm_age_rec3", "adm_age_rec3", 
"birth_date_rec", "adm_date_num_rec2", "adm_date_rec2", "dit_rec6", 
"disch_date_rec6", "disch_date_num_rec6_trans", "def_date", "adm_motive", 
"tr_compliance_rec7", "adm_disch_reason", "referral_type", "plan_type", 
"id_centro", "senda", "pub_center", "primary_sub", "second_sub1", 
"second_sub2", "second_sub3", "prim_sub_freq", "prim_sub_route", 
"LB_age_primary_onset_rec2", "UB_age_primary_onset_rec2", "age_primary_onset_rec2", 
"first_sub_used", "sus_ini_mod_mvv", "sus_ini_1", "sus_ini_2", 
"sus_ini_3", "LB_age_subs_onset_rec2", "UB_age_subs_onset_rec2", 
"age_subs_onset_rec2", "biopsych_comp", "mod_psiq_cie_10", "mod_psiq_dsm_iv", 
"diagnostico_trs_fisico", "otros_probl_at_sm_or", "sub_dep_icd10_status", 
"evaluacindelprocesoteraputico", "eva_consumo", "eva_fam", "eva_relinterp", 
"eva_ocupacion", "eva_sm", "eva_fisica", "eva_transgnorma", "dg_global_nec_int_soc_or", 
"dg_nec_int_soc_cap_hum_or", "dg_nec_int_soc_cap_fis_or", "dg_nec_int_soc_cap_soc_or", 
"dg_global_nec_int_soc_egr_or", "dg_nec_int_soc_cap_hum_egr_or", 
"dg_nec_int_soc_cap_fis_egr_or", "dg_nec_int_soc_cap_soc_egr_or", 
"usuario_tribunal_trat_droga", "nationality_cons", "ethnicity_c1_c6_historic", 
"discapacidad", "opcion_discapacidad", "sex_rec", "identidad_de_genero", 
"orientacion_sexual", "pregnant", "pregnant_disch", "marital_status", 
"tiene_menores_de_edad_a_cargo", "num_hijos_trat_res", "numero_de_hijos", 
"con_quien_vive", "tipo_de_vivienda", "precariedad_vivienda", 
"tenure_status_household", "servicios_basicos_95", "perso_dormitorio_vivienda", 
"ed_attainment", "occupation_condition", "occupation_status", 
"rubro_trabaja", "laboral_ingresos", "yr_block", "OBS_series", 
"senda_series", "pub_center_series", "id_centro_series", "disch_date_num_rec6", 
"dg_psiq_cie_10_instudy", "dg_psiq_cie_10_dg", "dg_psiq_dsm_iv_instudy", 
"dg_psiq_dsm_iv_dg", "plan_type_series", "tr_compliance_rec7_series", 
"referral_type_series", "adm_age_rec3_series", "adm_date_rec2_series", 
"disch_date_rec6_series", "diagnostico_trs_fisico_series", "otros_probl_at_sm_or_series", 
"OBS", "occupation_status_corr", "occupation_condition_corr24", 
"plan_type_corr", "ed_attainment_corr", "polysubstance_strict", 
"icd10_diag1", "icd10_diag2", "icd10_diag3", "dsmiv_diag1", "dsmiv_diag2", 
"dsmiv_diag3", "adm_year", "porc_pobr", "clasificacion", "km2_c", 
"km2_log", "porc_pobr_log", "porc_pobr_c")

df_subset <- SISTRAT23_c1_2010_2024_df_prev1y %>% select(all_of(main_vars))

# Generate HTML codebook

codebook_data <- df_subset

# Add metadata
metadata(codebook_data)$datePublished <- "2024-01-01"
metadata(codebook_data)$temporalCoverage <- "2010-2024"
metadata(codebook_data)$spatialCoverage <- "Chile"

metadata(codebook_data)$creator <- list(
  list("@type" = "Person",
       givenName = "Álvaro", familyName = "Castillo-Carniglia",
       affiliation = list("@type" = "Organization",
                          name = "Universidad San Sebastián, Chile")),
  list("@type" = "Person",
       givenName = "Andrés", familyName = "González-Santa Cruz",
       email = "gonzalez.santacruz.andres@gmail.com",
       affiliation = list("@type" = "Organization",
                          name = "Universidad de Chile, Public Health")),
  list("@type" = "Person",
       givenName = "Amaru", familyName = "Agüero Jiménez",
       affiliation = list("@type" = "Organization",
                          name = "Universidad del Desarrollo, Chile"))
)
metadata(codebook_data)$citation <- "Castillo-Carniglia, Á., González-Santa Cruz, A., & Agüero Jiménez, A. (2024). Workflow of data management and analysis - Chilean substance use treatment administrative data. Consolidation of Agreement 1 Databases from 2010 to 2024. Funded by FONDECYT regular 1191282."
metadata(codebook_data)$url <- "https://github.com/FONDECYTACC/cons2025"
metadata(codebook_data)$name <- "Agreement 1 SENDA"
metadata(codebook_data)$description <- "Information About Agreement 1 of SENDA and MINSAL"

codebook(codebook_data)

Metadata

Description

Dataset name: Agreement 1 SENDA

Information About Agreement 1 of SENDA and MINSAL

Metadata for search engines

• Temporal Coverage: 2010-2024

• Spatial Coverage: Chile

• Citation: Castillo-Carniglia, Á., González-Santa Cruz, A., & Agüero Jiménez, A. (2024). Workflow of data management and analysis - Chilean substance use treatment administrative data. Consolidation of Agreement 1 Databases from 2010 to 2024. Funded by FONDECYT regular 1191282.

• URL: https://github.com/FONDECYTACC/cons2025

• Date published: 2024-01-01

• Creator:

name	value
1	Person , Álvaro , Castillo-Carniglia , Organization , Universidad San Sebastián, Chile
2	Person , Andrés , González-Santa Cruz , gonzalez.santacruz.andres@gmail.com, Organization , Universidad de Chile, Public Health
3	Person , Amaru , Agüero Jiménez , Organization , Universidad del Desarrollo, Chile

x TABLE TABLE_rec_series rn rn_series num_trat_ant fecha_ultimo_tratamiento hash_key min_adm_age_rec3 adm_age_rec3 birth_date_rec adm_date_num_rec2 adm_date_rec2 dit_rec6 disch_date_rec6 disch_date_num_rec6_trans def_date adm_motive tr_compliance_rec7 adm_disch_reason referral_type plan_type id_centro senda pub_center primary_sub second_sub1 second_sub2 second_sub3 prim_sub_freq prim_sub_route LB_age_primary_onset_rec2 UB_age_primary_onset_rec2 age_primary_onset_rec2 first_sub_used sus_ini_mod_mvv sus_ini_1 sus_ini_2 sus_ini_3 LB_age_subs_onset_rec2 UB_age_subs_onset_rec2 age_subs_onset_rec2 biopsych_comp mod_psiq_cie_10 mod_psiq_dsm_iv diagnostico_trs_fisico otros_probl_at_sm_or sub_dep_icd10_status evaluacindelprocesoteraputico eva_consumo eva_fam eva_relinterp eva_ocupacion eva_sm eva_fisica eva_transgnorma dg_global_nec_int_soc_or dg_nec_int_soc_cap_hum_or dg_nec_int_soc_cap_fis_or dg_nec_int_soc_cap_soc_or dg_global_nec_int_soc_egr_or dg_nec_int_soc_cap_hum_egr_or dg_nec_int_soc_cap_fis_egr_or dg_nec_int_soc_cap_soc_egr_or usuario_tribunal_trat_droga nationality_cons ethnicity_c1_c6_historic discapacidad opcion_discapacidad sex_rec identidad_de_genero orientacion_sexual pregnant pregnant_disch marital_status tiene_menores_de_edad_a_cargo num_hijos_trat_res numero_de_hijos con_quien_vive tipo_de_vivienda precariedad_vivienda tenure_status_household servicios_basicos_95 perso_dormitorio_vivienda ed_attainment occupation_condition occupation_status rubro_trabaja laboral_ingresos yr_block OBS_series senda_series pub_center_series id_centro_series disch_date_num_rec6 dg_psiq_cie_10_instudy dg_psiq_cie_10_dg dg_psiq_dsm_iv_instudy dg_psiq_dsm_iv_dg plan_type_series tr_compliance_rec7_series referral_type_series adm_age_rec3_series adm_date_rec2_series disch_date_rec6_series diagnostico_trs_fisico_series otros_probl_at_sm_or_series OBS occupation_status_corr occupation_condition_corr24 plan_type_corr ed_attainment_corr polysubstance_strict icd10_diag1 icd10_diag2 icd10_diag3 dsmiv_diag1 dsmiv_diag2 dsmiv_diag3 adm_year porc_pobr clasificacion km2_c km2_log porc_pobr_log porc_pobr_c

Variables

TABLE

Year of data collection (original SISTRAT table/year identifier). Represents the year the record was entered (e.g., “2023”, “2015”). No transformation applied. Made in import_c1_top_data_adm_25.qmd

Distribution

Distribution of values for TABLE

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
TABLE	Year of data collection (original SISTRAT table/year identifier). Represents the year the record was entered (e.g., “2023”, “2015”). No transformation applied. Made in import_c1_top_data_adm_25.qmd	character	0	1	15	0	4	4	0

TABLE_rec_series

Recoded series of TABLE

Distribution

Distribution of values for TABLE_rec_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
TABLE_rec_series	Recoded series of TABLE	character	0	1	400	0	8	50	0

rn

Row number or treatment episode sequence per patient. Created by row_number() over (partition by hash_key order by adm_date), Step 1 (SISTRAT23_c1_2010_2024_df2). Identifies first, second, etc., treatment for each user.

Distribution

Distribution of values for rn

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
rn	Row number or treatment episode sequence per patient. Created by row_number() over (partition by hash_key order by adm_date), Step 1 (SISTRAT23_c1_2010_2024_df2). Identifies first, second, etc., treatment for each user.	numeric	0	1	1	122890	259395	128243.1	78217.81	▇▇▇▆▇

rn_series

Series of row number

Distribution

Distribution of values for rn_series

153200 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
rn_series	Series of row number	character	153200	0.0595284	9697	0	8	48	0

num_trat_ant

Number of prior treatments reported by patient. Direct import. May not be reliable. Not used.

Distribution

Distribution of values for num_trat_ant

9266 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
num_trat_ant	Number of prior treatments reported by patient. Direct import. May not be reliable. Not used.	numeric	9266	0.9431174	0	1	11	0.898842	1.172059	▇▁▁▁▁

fecha_ultimo_tratamiento

Patient-reported time since last treatment (e.g., “3 a 4 anos”). Direct import. Categorical, not numeric. Many missing values (~50%)

Distribution

Distribution of values for fecha_ultimo_tratamiento

80571 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
fecha_ultimo_tratamiento	Patient-reported time since last treatment (e.g., “3 a 4 anos”). Direct import. Categorical, not numeric. Many missing values (~50%)	character	80571	0.5053868	6	0	10	15	0

hash_key

Unique anonymized identifier for each individual (user/patient RUT derivative). Direct import from raw SISTRAT C1. Originally in uppercase letter. Generated by hashing the RUT (national ID) by MINSAL. Used to link multiple treatment episodes for the same person across years. No transformation.

Distribution

Distribution of values for hash_key

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
hash_key	Unique anonymized identifier for each individual (user/patient RUT derivative). Direct import from raw SISTRAT C1. Originally in uppercase letter. Generated by hashing the RUT (national ID) by MINSAL. Used to link multiple treatment episodes for the same person across years. No transformation.	character	0	1	121299	0	64	64	0

min_adm_age_rec3

min(adm_age_rec3) grouped by hash_key. Critical benchmark for validating/imputing onset ages.

Distribution

Distribution of values for min_adm_age_rec3

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
min_adm_age_rec3	min(adm_age_rec3) grouped by hash_key. Critical benchmark for validating/imputing onset ages.	numeric	0	1	13	34	89	35.95135	11.04595	▅▇▃▁▁

adm_age_rec3

Admission age [log1p(x)=adm_age_log, centered= adm_age_c,^2=adm_age_pow2, ^3=adm_age_pow3, three groups= adm_age_rec3_cat]

Distribution

Distribution of values for adm_age_rec3

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
adm_age_rec3	Admission age [log1p(x)=adm_age_log, centered= adm_age_c,^2=adm_age_pow2, ^3=adm_age_pow3, three groups= adm_age_rec3_cat]	numeric	0	1	13	35	89	36.91851	11.07224	▅▇▃▁▁

birth_date_rec

Final authoritative date of birth. Created by selecting/imputing best birth_date per hash_key (via kNN, logic, or min/max validation). Used to recalculate adm_age_rec.

Distribution

19660  unique, categorical values, so not shown.

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	min	median	max
birth_date_rec	Final authoritative date of birth. Created by selecting/imputing best birth_date per hash_key (via kNN, logic, or min/max validation). Used to recalculate adm_age_rec.	Date	0	1	19660	1928-09-18	1982-01-02	2008-04-16

adm_date_num_rec2

Numeric admission date recoded version 2

Distribution

Distribution of values for adm_date_num_rec2

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
adm_date_num_rec2	Numeric admission date recoded version 2	numeric	0	1	10957	17345	20077	17378.37	1528.861	▁▁▆▇▆

adm_date_rec2

Intermediate admission date Created in Step 2 (0.c) for the resolution of overlaps

Distribution

5085  unique, categorical values, so not shown.

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	min	median	max
adm_date_rec2	Intermediate admission date Created in Step 2 (0.c) for the resolution of overlaps	Date	0	1	5085	2000-01-01	2017-06-28	2024-12-20

dit_rec6

Length of stay in treatment (months) [log1p(x)=treat_log, ^2=treat_days_pow2, ^3=treat_days_pow3, <90days=treat_lt_90]

Distribution

Distribution of values for dit_rec6

3103 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
dit_rec6	Length of stay in treatment (months) [log1p(x)=treat_log, ^2=treat_days_pow2, ^3=treat_days_pow3, <90days=treat_lt_90]	numeric	3103	0.9809512	0	180	1988	236.0513	199.5927	▇▁▁▁▁

disch_date_rec6

Final discharge date for longitudinal analysis. Created as selected consistent version for time-to-event modeling.

Distribution

5335  unique, categorical values, so not shown.

3270 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	min	median	max
disch_date_rec6	Final discharge date for longitudinal analysis. Created as selected consistent version for time-to-event modeling.	Date	3270	0.979926	5335	2003-01-01	2017-12-27	2025-05-28

disch_date_num_rec6_trans

Imputed discharge based on reference date Created in Step 3. Missing discharge dates were filled using a default value calculated from a fixed retrieval date (e.g., May 28, 2025), ensuring consistency across all treatment records and uncovering censorship mechanisms.

Distribution

Distribution of values for disch_date_num_rec6_trans

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
disch_date_num_rec6_trans	Imputed discharge based on reference date Created in Step 3. Missing discharge dates were filled using a default value calculated from a fixed retrieval date (e.g., May 28, 2025), ensuring consistency across all treatment records and uncovering censorship mechanisms.	numeric	0	1	12053	17563	20236	17619.79	1539.775	▁▂▇▇▇

Warning: Setting row names on a tibble is deprecated.

def_date

Date of death (if applicable, mostly NA). Created from external mortality linkage (not in provided scripts). Parsed from mortality registry (dia_def, mes_def, ano_def), imputing missing day as 15; earliest date kept when multiple. Used to censor discharges after death. See Duplicates_25_2.qmd (pre-00.a).

Distribution

2289  unique, categorical values, so not shown.

157391 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	min	median	max	row	expected	actual
def_date	Date of death (if applicable, mostly NA). Created from external mortality linkage (not in provided scripts). Parsed from mortality registry (dia_def, mes_def, ano_def), imputing missing day as 15; earliest date kept when multiple. Used to censor discharges after death. See Duplicates_25_2.qmd (pre-00.a).	Date	157391	0.0338005	2289	2010-01-04	2018-04-19	2020-12-31	7864	date like %d-%m-%Y	15-NA-2008

adm_motive

Admission motive

Distribution

Distribution of values for adm_motive

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
adm_motive	Admission motive	character	0	1	5	0	5	46	0

tr_compliance_rec7

Treatment compliance category. Created in Step 4. Removed cases (n=3) with an ongoing treatment motive but with a posterior treatment after. Replaced for dropout (they had incomplete discharge information)

Distribution

Distribution of values for tr_compliance_rec7

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
tr_compliance_rec7	Treatment compliance category. Created in Step 4. Removed cases (n=3) with an ongoing treatment motive but with a posterior treatment after. Replaced for dropout (they had incomplete discharge information)	character	0	1	8	0	8	19	0

adm_disch_reason

Placeholder for administrative discharge reason (mostly empty). Created as copy of motivo_de_egreso_alta_administrativa. Derived/translated from motivo_de_egreso_alta_administrativa; listed among deduplication key variables in Step 2. 47%-56% missing in patients with adm. discharge.

Distribution

Distribution of values for adm_disch_reason

156643 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
adm_disch_reason	Placeholder for administrative discharge reason (mostly empty). Created as copy of motivo_de_egreso_alta_administrativa. Derived/translated from motivo_de_egreso_alta_administrativa; listed among deduplication key variables in Step 2. 47%-56% missing in patients with adm. discharge.	character	156643	0.0383924	4	0	5	16	0

referral_type

Recoded type of referral center. Created from tipo_centro_derivacion (translation): e.g., “otro centro” , “other facility”, “cosam”, “primary health care”.

Distribution

Distribution of values for referral_type

158565 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
referral_type	Recoded type of referral center. Created from tipo_centro_derivacion (translation): e.g., “otro centro” , “other facility”, “cosam”, “primary health care”.	character	158565	0.0265935	5	0	14	25	0

plan_type

Recoded treatment plan type. Created as copy and translation of tipo_de_plan (step 1). Used in collapsing logic and outcome modeling.

Distribution

Distribution of values for plan_type

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
plan_type	Recoded treatment plan type. Created as copy and translation of tipo_de_plan (step 1). Used in collapsing logic and outcome modeling.	character	0	1	6	0	4	6	0

id_centro

Center ID number. Direct import. Used to link center attributes, collapse duplicates, and derive centro_muj (women-specific centers).

Distribution

Distribution of values for id_centro

39 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
id_centro	Center ID number. Direct import. Used to link center attributes, collapse duplicates, and derive centro_muj (women-specific centers).	numeric	39	0.9997606	104	258	899	310.5774	177.9022	▇▃▂▂▁

senda

Indicator if treatment was under SENDA agreement (“si”/“no”). Direct import. Used to derive senda_adm_date and flag SENDA-specific episodes. No transformation initially. According to SENDA professionals, patients may be in SENDA Yes programs may anyways part of SENDA programs in some cases

Distribution

Distribution of values for senda

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
senda	Indicator if treatment was under SENDA agreement (“si”/“no”). Direct import. Used to derive senda_adm_date and flag SENDA-specific episodes. No transformation initially. According to SENDA professionals, patients may be in SENDA Yes programs may anyways part of SENDA programs in some cases	character	0	1	2	0	2	2	0

pub_center

Binary indicator for public center. Created as tipo_centro == "publico". Used in institutional comparisons.

Distribution

Distribution of values for pub_center

39 missing values.

Summary statistics

name	label	data_type	ordered	value_labels	n_missing	complete_rate	n_unique	top_counts
pub_center	Binary indicator for public center. Created as tipo_centro == "publico". Used in institutional comparisons.	factor	FALSE	1. FALSE, 2. TRUE	39	0.9997606	2	TRU: 112242, FAL: 50616

primary_sub

Primary substance of use

Distribution

Distribution of values for primary_sub

4 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
primary_sub	Primary substance of use	character	4	0.9999754	11	0	6	27	0

second_sub1

Normalized secondary substances at admission (1)

Distribution

Distribution of values for second_sub1

45932 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
second_sub1	Normalized secondary substances at admission (1)	character	45932	0.7180304	12	0	6	33	0

second_sub2

Normalized secondary substances at admission (2)

Distribution

Distribution of values for second_sub2

101461 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
second_sub2	Normalized secondary substances at admission (2)	character	101461	0.3771463	12	0	6	33	0

second_sub3

Normalized secondary substances at admission (3)

Distribution

Distribution of values for second_sub3

142611 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
second_sub3	Normalized secondary substances at admission (3)	character	142611	0.1245327	12	0	6	33	0

prim_sub_freq

Frequency of primary substance use at admission (recoded: prim_sub_freq_rec)

Distribution

Distribution of values for prim_sub_freq

808 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
prim_sub_freq	Frequency of primary substance use at admission (recoded: prim_sub_freq_rec)	character	808	0.9950398	5	0	8	25	0

prim_sub_route

Recoded route of administration. Created from via_administracion_sustancia_principal into standardized terms.

Distribution

Distribution of values for prim_sub_route

25 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
prim_sub_route	Recoded route of administration. Created from via_administracion_sustancia_principal into standardized terms.	character	25	0.9998465	5	0	6	41	0

LB_age_primary_onset_rec2

Lower bound age of primary substance onset recoded 2

Distribution

Distribution of values for LB_age_primary_onset_rec2

91849 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
LB_age_primary_onset_rec2	Lower bound age of primary substance onset recoded 2	numeric	91849	0.4361529	5	14	71	13.38267	4.697013	▇▁▁▁▁

UB_age_primary_onset_rec2

Upper bound age of primary substance onset recoded 2

Distribution

Distribution of values for UB_age_primary_onset_rec2

91849 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
UB_age_primary_onset_rec2	Upper bound age of primary substance onset recoded 2	numeric	91849	0.4361529	13	31	82	32.69701	9.823931	▅▇▃▁▁

age_primary_onset_rec2

Created in Step 3.

Distribution

Distribution of values for age_primary_onset_rec2

1254 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
age_primary_onset_rec2	Created in Step 3.	numeric	1254	0.9923019	5	18	75	20.2022	7.575139	▇▅▁▁▁

first_sub_used

Normalized first substance used. Created as tolower(gsub("_", " ", sustancia_de_inicio)). Input for resolving inconsistencies, prioritizing most vulnerable value = sus_ini_mod_mvv. Despite this, this variable was normalized in Step 3 for inconsistent values in patients.

Distribution

Distribution of values for first_sub_used

10508 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
first_sub_used	Normalized first substance used. Created as tolower(gsub("_", " ", sustancia_de_inicio)). Input for resolving inconsistencies, prioritizing most vulnerable value = sus_ini_mod_mvv. Despite this, this variable was normalized in Step 3 for inconsistent values in patients.	character	10508	0.935493	11	0	6	27	0

sus_ini_mod_mvv

Sus ini mod mvv

Distribution

Distribution of values for sus_ini_mod_mvv

6684 missing values.

Summary statistics

name	label	data_type	ordered	value_labels	n_missing	complete_rate	n_unique	top_counts
sus_ini_mod_mvv	Sus ini mod mvv	factor	FALSE	1. cocaine paste, 2. cocaine powder, 3. alcohol, 4. marijuana, 5. others	6684	0.9589679	5	alc: 98027, mar: 33833, coc: 12128, coc: 9512

sus_ini_1

Sus ini 1

Distribution

Distribution of values for sus_ini_1

121960 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
sus_ini_1	Sus ini 1	character	121960	0.251306	10	0	6	27	0

sus_ini_2

Sus ini 2

Distribution

Distribution of values for sus_ini_2

128480 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
sus_ini_2	Sus ini 2	character	128480	0.2112807	10	0	6	27	0

sus_ini_3

Sus ini 3

Distribution

Distribution of values for sus_ini_3

157971 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
sus_ini_3	Sus ini 3	character	157971	0.03024	10	0	6	27	0

LB_age_subs_onset_rec2

Lower bound age of substance onset recoded 2

Distribution

Distribution of values for LB_age_subs_onset_rec2

91846 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
LB_age_subs_onset_rec2	Lower bound age of substance onset recoded 2	numeric	91846	0.4361713	5	5	5	5	0	▁▁▇▁▁

UB_age_subs_onset_rec2

Upper bound age of substance onset recoded 2

Distribution

Distribution of values for UB_age_subs_onset_rec2

91846 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
UB_age_subs_onset_rec2	Upper bound age of substance onset recoded 2	numeric	91846	0.4361713	13	31	82	32.69688	9.823752	▅▇▃▁▁

age_subs_onset_rec2

Created in Step 3.

Distribution

Distribution of values for age_subs_onset_rec2

6675 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
age_subs_onset_rec2	Created in Step 3.	numeric	6675	0.9590232	5	15	74	15.52318	5.12464	▇▁▁▁▁

biopsych_comp

Recoded biopsychosocial severity. Created from compromiso_biopsicosocial: e.g., “moderado”, “2-moderate”.

Distribution

Distribution of values for biopsych_comp

1947 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
biopsych_comp	Recoded biopsychosocial severity. Created from compromiso_biopsicosocial: e.g., “moderado”, “2-moderate”.	character	1947	0.9880477	3	0	6	10	0

mod_psiq_cie_10

Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses

Distribution

Distribution of values for mod_psiq_cie_10

83784 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
mod_psiq_cie_10	Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses	character	83784	0.4856627	1083	0	18	525	0

mod_psiq_dsm_iv

Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses

Distribution

Distribution of values for mod_psiq_dsm_iv

148878 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
mod_psiq_dsm_iv	Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses	character	148878	0.0860605	744	0	6	403	0

diagnostico_trs_fisico

Physical health diagnosis. Direct import. Often concatenated (e.g., “Hepatitis alcoholica: cardiopatías”). Preserved as-is for clinical profiling.

Distribution

Distribution of values for diagnostico_trs_fisico

310 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
diagnostico_trs_fisico	Physical health diagnosis. Direct import. Often concatenated (e.g., “Hepatitis alcoholica: cardiopatías”). Preserved as-is for clinical profiling.	character	310	0.998097	15	0	3	60	0

otros_probl_at_sm_or

Other mental health issues (e.g., “abuso sexual”). Direct import. Recoded to otros_probl_at_sm_or. Used in vulnerability and trauma profiling.

Distribution

Distribution of values for otros_probl_at_sm_or

34796 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
otros_probl_at_sm_or	Other mental health issues (e.g., “abuso sexual”). Direct import. Recoded to otros_probl_at_sm_or. Used in vulnerability and trauma profiling.	character	34796	0.7863926	10	0	3	37	0

sub_dep_icd10_status

Severity of Substance Use Disorder (SUD)

Distribution

Distribution of values for sub_dep_icd10_status

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
sub_dep_icd10_status	Severity of Substance Use Disorder (SUD)	character	0	1	2	0	15	21	0

evaluacindelprocesoteraputico

Therapeutic process evaluation (e.g., “logro alto”). Direct import. Recoded to standardized categories. Used in outcome and program effectiveness analysis.

Distribution

Distribution of values for evaluacindelprocesoteraputico

3599 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
evaluacindelprocesoteraputico	Therapeutic process evaluation (e.g., “logro alto”). Direct import. Recoded to standardized categories. Used in outcome and program effectiveness analysis.	character	3599	0.9779063	3	0	10	16	0

eva_consumo

Evaluation of consumption pattern at discharge. Direct import. Part of multi-domain outcome assessment. Recoded similarly.

Distribution

Distribution of values for eva_consumo

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_consumo	Evaluation of consumption pattern at discharge. Direct import. Part of multi-domain outcome assessment. Recoded similarly.	character	3621	0.9777712	3	0	10	16	0

eva_fam

Family situation evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_fam

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_fam	Family situation evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

eva_relinterp

Interpersonal relations evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_relinterp

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_relinterp	Interpersonal relations evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

eva_ocupacion

Occupational situation evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_ocupacion

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_ocupacion	Occupational situation evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

eva_sm

Mental health evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_sm

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_sm	Mental health evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

eva_fisica

Physical health evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_fisica

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_fisica	Physical health evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

eva_transgnorma

Social norm transgression evaluation at discharge. Direct import.

Distribution

Distribution of values for eva_transgnorma

3621 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
eva_transgnorma	Social norm transgression evaluation at discharge. Direct import.	character	3621	0.9777712	3	0	10	16	0

dg_global_nec_int_soc_or

Global social integration need at admission. Direct import. Recoded to dg_global_nec_int_soc_or. Categorized as “altas”, “medias”, “bajas”. Used in social vulnerability index.

Distribution

Distribution of values for dg_global_nec_int_soc_or

47767 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_global_nec_int_soc_or	Global social integration need at admission. Direct import. Recoded to dg_global_nec_int_soc_or. Categorized as “altas”, “medias”, “bajas”. Used in social vulnerability index.	character	47767	0.7067656	5	0	5	12	0

dg_nec_int_soc_cap_hum_or

Human capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_hum_or. Part of social integration profile.

Distribution

Distribution of values for dg_nec_int_soc_cap_hum_or

47768 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_hum_or	Human capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_hum_or. Part of social integration profile.	character	47768	0.7067595	5	0	5	12	0

dg_nec_int_soc_cap_fis_or

Physical capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_fis_or.

Distribution

Distribution of values for dg_nec_int_soc_cap_fis_or

47767 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_fis_or	Physical capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_fis_or.	character	47767	0.7067656	5	0	5	12	0

dg_nec_int_soc_cap_soc_or

Social capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_soc_or.

Distribution

Distribution of values for dg_nec_int_soc_cap_soc_or

47767 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_soc_or	Social capital need at admission. Direct import. Recoded to dg_nec_int_soc_cap_soc_or.	character	47767	0.7067656	5	0	5	12	0

dg_global_nec_int_soc_egr_or

Global social integration need at discharge. Direct import. Recoded similarly to admission version (_60). Used for delta/change analysis.

Distribution

Distribution of values for dg_global_nec_int_soc_egr_or

45847 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_global_nec_int_soc_egr_or	Global social integration need at discharge. Direct import. Recoded similarly to admission version (_60). Used for delta/change analysis.	character	45847	0.7185522	5	0	5	12	0

dg_nec_int_soc_cap_hum_egr_or

Human capital need at discharge. Direct import.

Distribution

Distribution of values for dg_nec_int_soc_cap_hum_egr_or

45165 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_hum_egr_or	Human capital need at discharge. Direct import.	character	45165	0.7227389	5	0	5	12	0

dg_nec_int_soc_cap_fis_egr_or

Physical capital need at discharge. Direct import.

Distribution

Distribution of values for dg_nec_int_soc_cap_fis_egr_or

45144 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_fis_egr_or	Physical capital need at discharge. Direct import.	character	45144	0.7228678	5	0	5	12	0

dg_nec_int_soc_cap_soc_egr_or

Social capital need at discharge. Direct import.

Distribution

Distribution of values for dg_nec_int_soc_cap_soc_egr_or

45285 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dg_nec_int_soc_cap_soc_egr_or	Social capital need at discharge. Direct import.	character	45285	0.7220022	5	0	5	12	0

usuario_tribunal_trat_droga

Court-referred to drug treatment (very unbalanced, ~1% yes)

Distribution

Distribution of values for usuario_tribunal_trat_droga

5888 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
usuario_tribunal_trat_droga	Court-referred to drug treatment (very unbalanced, ~1% yes)	character	5888	0.9638545	2	0	2	2	0

nationality_cons

Recoded/standardized from nacionalidad or pais_nacimiento.

Distribution

Distribution of values for nationality_cons

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
nationality_cons	Recoded/standardized from nacionalidad or pais_nacimiento.	character	0	1	83	0	4	31	0

ethnicity_c1_c6_historic

Concatenated unique non-Chilean/non-“no pertenece” values from etnia (C1) and ethnicity (C6), grouped by hash_key.

Distribution

Distribution of values for ethnicity_c1_c6_historic

150808 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
ethnicity_c1_c6_historic	Concatenated unique non-Chilean/non-“no pertenece” values from etnia (C1) and ethnicity (C6), grouped by hash_key.	character	150808	0.0742125	31	0	5	22	0

discapacidad

Indicator of disability (“si”/“no”). Direct import. Used with opcion_discapacidad for disability profiling. Starts coding in 2019

Distribution

Distribution of values for discapacidad

99545 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
discapacidad	Indicator of disability (“si”/“no”). Direct import. Used with opcion_discapacidad for disability profiling. Starts coding in 2019	character	99545	0.3889083	2	0	2	2	0

opcion_discapacidad

Type of disability (e.g., “de causa psiquica”). Direct import. Only populated if discapacidad == "si". Used in accessibility and needs assessment.Starts coding in 2019

Distribution

Distribution of values for opcion_discapacidad

160052 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
opcion_discapacidad	Type of disability (e.g., “de causa psiquica”). Direct import. Only populated if discapacidad == "si". Used in accessibility and needs assessment.Starts coding in 2019	character	160052	0.017465	5	0	16	21	0

sex_rec

Sex (often used for biological categorization)

Distribution

Distribution of values for sex_rec

4 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
sex_rec	Sex (often used for biological categorization)	character	4	0.9999754	2	0	5	6	0

identidad_de_genero

Gender identity (e.g., “masculino”, “femenino”). Direct import. Recoded to identidad_de_genero factor. Used to validate/override sexo in sex_rec (Step 2). Starts coding in 2019

Distribution

Distribution of values for identidad_de_genero

99545 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
identidad_de_genero	Gender identity (e.g., “masculino”, “femenino”). Direct import. Recoded to identidad_de_genero factor. Used to validate/override sexo in sex_rec (Step 2). Starts coding in 2019	character	99545	0.3889083	8	0	8	19	0

orientacion_sexual

Sexual orientation (e.g., “heterosexual”). Direct import. Sparse. Preserved for inclusivity analysis.Starts coding in 2022

Distribution

Distribution of values for orientacion_sexual

129745 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
orientacion_sexual	Sexual orientation (e.g., “heterosexual”). Direct import. Sparse. Preserved for inclusivity analysis.Starts coding in 2022	character	129745	0.2035151	5	0	7	12	0

pregnant

Recoded pregnancy status at admission. Created from se_trata_de_una_mujer_embarazada (NA = “no”). Used in gender-specific analysis (Step 3). This variable (indicating if a woman is pregnant) seems to beintroduced in 2011.

Distribution

Distribution of values for pregnant

87172 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
pregnant	Recoded pregnancy status at admission. Created from se_trata_de_una_mujer_embarazada (NA = “no”). Used in gender-specific analysis (Step 3). This variable (indicating if a woman is pregnant) seems to beintroduced in 2011.	character	87172	0.4648643	2	0	2	3	0

pregnant_disch

Recoded pregnancy status at discharge. Created from ha_estado_embarazada_egreso. Used in gender-specific analysis (Step 3). Sparse. Seems to be only accurately collected starting in 2017. Created to capture pregnancy status specifically at treatment discharge.

Distribution

Distribution of values for pregnant_disch

100935 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
pregnant_disch	Recoded pregnancy status at discharge. Created from ha_estado_embarazada_egreso. Used in gender-specific analysis (Step 3). Sparse. Seems to be only accurately collected starting in 2017. Created to capture pregnancy status specifically at treatment discharge.	character	100935	0.3803753	2	0	2	3	0

marital_status

Marital status

Distribution

Distribution of values for marital_status

317 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
marital_status	Marital status	character	317	0.998054	4	0	6	27	0

tiene_menores_de_edad_a_cargo

Indicator if responsible for minors (“si”/“no”). Direct import. Mostly missing before 2015 (Duplicates_25.txt). Recoded to binary flag. Used in family vulnerability index.

Distribution

Distribution of values for tiene_menores_de_edad_a_cargo

61317 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
tiene_menores_de_edad_a_cargo	Indicator if responsible for minors (“si”/“no”). Direct import. Mostly missing before 2015 (Duplicates_25.txt). Recoded to binary flag. Used in family vulnerability index.	character	61317	0.6235842	2	0	2	2	0

num_hijos_trat_res

Number of children entering residential treatment with patient. Direct import. Often missing or 0. Later used to derive binary flag hijos_trat_res (“Had children in treatments”).

Distribution

Distribution of values for num_hijos_trat_res

9266 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
num_hijos_trat_res	Number of children entering residential treatment with patient. Direct import. Often missing or 0. Later used to derive binary flag hijos_trat_res (“Had children in treatments”).	numeric	9266	0.9431174	0	0	11	0.0478289	0.2730079	▇▁▁▁▁

numero_de_hijos

Number of children reported by patient. Direct import. Values >11 flagged as implausible (Duplicates_25.txt). Used in kNN imputation and to derive tiene_menores_de_edad_a_cargo.

Distribution

Distribution of values for numero_de_hijos

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
numero_de_hijos	Number of children reported by patient. Direct import. Values >11 flagged as implausible (Duplicates_25.txt). Used in kNN imputation and to derive tiene_menores_de_edad_a_cargo.	numeric	0	1	0	1	71	1.663032	1.705014	▇▁▁▁▁

con_quien_vive

Living arrangement/Cohabitation status

Distribution

Distribution of values for con_quien_vive

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
con_quien_vive	Living arrangement/Cohabitation status	character	0	1	15	0	4	53	0

tipo_de_vivienda

Type of housing

Distribution

Distribution of values for tipo_de_vivienda

12176 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
tipo_de_vivienda	Type of housing	character	12176	0.9252534	10	0	4	37	0

precariedad_vivienda

Precarious housing. Direct import. Available since 2022 databases.

Distribution

Distribution of values for precariedad_vivienda

130860 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
precariedad_vivienda	Precarious housing. Direct import. Available since 2022 databases.	character	130860	0.1966703	2	0	37	82	0

tenure_status_household

Housing situation

Distribution

Distribution of values for tenure_status_household

7738 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
tenure_status_household	Housing situation	character	7738	0.9524976	5	0	6	42	0

servicios_basicos_95

Basic sanitation services. Direct import. Available since 2022 databases.

Distribution

Distribution of values for servicios_basicos_95

130860 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
servicios_basicos_95	Basic sanitation services. Direct import. Available since 2022 databases.	character	130860	0.1966703	2	0	55	135	0

perso_dormitorio_vivienda

Persons per dwelling bedroom Direct import. Available since 2022 databases.

Distribution

Distribution of values for perso_dormitorio_vivienda

130860 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
perso_dormitorio_vivienda	Persons per dwelling bedroom Direct import. Available since 2022 databases.	character	130860	0.1966703	2	0	20	20	0

ed_attainment

Recoded education level. Created from escolaridad_ultimo_ano_cursado into standardized categories (e.g., “media incompleta” = “2-Completed high school or less”).

Distribution

Distribution of values for ed_attainment

1105 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
ed_attainment	Recoded education level. Created from escolaridad_ultimo_ano_cursado into standardized categories (e.g., “media incompleta” = “2-Completed high school or less”).	character	1105	0.9932166	3	0	23	34	0

occupation_condition

Recoded employment status. Created from condicion_ocupacional: e.g., “cesante”= “unemployed” (in Step 1).

Distribution

Distribution of values for occupation_condition

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
occupation_condition	Recoded employment status. Created from condicion_ocupacional: e.g., “cesante”= “unemployed” (in Step 1).	character	0	1	3	0	8	10	0

occupation_status

Recoded employment category. Created from categoria_ocupacional. Sparse; often NA.

Distribution

Distribution of values for occupation_status

107379 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
occupation_status	Recoded employment category. Created from categoria_ocupacional. Sparse; often NA.	character	107379	0.3408166	6	0	5	20	0

rubro_trabaja

Occupational sector (e.g., “trabajadores no calificados”). Direct import. Recoded to rubro_trabaja_mod. 68% missing. 13.8% among employeed

Distribution

Distribution of values for rubro_trabaja

109056 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
rubro_trabaja	Occupational sector (e.g., “trabajadores no calificados”). Direct import. Recoded to rubro_trabaja_mod. 68% missing. 13.8% among employeed	character	109056	0.3305217	11	0	21	77	0

laboral_ingresos

Monthly income. Direct import. Available since 2022 databases.

Distribution

Distribution of values for laboral_ingresos

148124 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
laboral_ingresos	Monthly income. Direct import. Available since 2022 databases.	character	148124	0.0906892	11	0	16	19	0

yr_block

Birth year block (e.g., 1980, 1990) for anonymization or grouping. Created by rounding birth_date year to nearest decade (e.g., floor(year(birth_date)/10)*10). To look for data similarities (Step 1)

Distribution

Distribution of values for yr_block

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
yr_block	Birth year block (e.g., 1980, 1990) for anonymization or grouping. Created by rounding birth_date year to nearest decade (e.g., floor(year(birth_date)/10)*10). To look for data similarities (Step 1)	numeric	0	1	1925	1980	2005	1978.161	11.40454	▁▁▅▇▃

OBS_series

OBS series

Distribution

Distribution of values for OBS_series

153200 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
OBS_series	OBS series	character	153200	0.0595284	993	0	45	999	0

senda_series

SENDA series

Distribution

Distribution of values for senda_series

153200 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
senda_series	SENDA series	character	153200	0.0595284	4	0	2	5	0

pub_center_series

Public center series

Distribution

Distribution of values for pub_center_series

153200 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
pub_center_series	Public center series	character	153200	0.0595284	4	0	4	10	0

id_centro_series

Center ID series

Distribution

Distribution of values for id_centro_series

153200 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
id_centro_series	Center ID series	character	153200	0.0595284	2773	0	3	15	0

disch_date_num_rec6

Numeric discharge date recoded 6

Distribution

Distribution of values for disch_date_num_rec6

3270 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
disch_date_num_rec6	Numeric discharge date recoded 6	numeric	3270	0.979926	12053	17527	20236	17566.2	1508.771	▁▂▇▇▇

dg_psiq_cie_10_instudy

Psychiatric comorbidity (ICD-10)

Distribution

Distribution of values for dg_psiq_cie_10_instudy

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	count	mean
dg_psiq_cie_10_instudy	Psychiatric comorbidity (ICD-10)	logical	0	1	FAL: 136904, TRU: 25993	0.1595671

dg_psiq_cie_10_dg

Mutually exclusive (as corrected in Step 3)

Distribution

Distribution of values for dg_psiq_cie_10_dg

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	count	mean
dg_psiq_cie_10_dg	Mutually exclusive (as corrected in Step 3)	logical	0	1	FAL: 83784, TRU: 79113	0.4856627

dg_psiq_dsm_iv_instudy

Psychiatric comorbidity (DSM-IV)

Distribution

Distribution of values for dg_psiq_dsm_iv_instudy

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	count	mean
dg_psiq_dsm_iv_instudy	Psychiatric comorbidity (DSM-IV)	logical	0	1	FAL: 91558, TRU: 71339	0.4379393

dg_psiq_dsm_iv_dg

Mutually exclusive (as corrected in Step 3)

Distribution

Distribution of values for dg_psiq_dsm_iv_dg

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	count	mean
dg_psiq_dsm_iv_dg	Mutually exclusive (as corrected in Step 3)	logical	0	1	FAL: 148878, TRU: 14019	0.0860605

plan_type_series

Plan type series

Distribution

Distribution of values for plan_type_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
plan_type_series	Plan type series	character	0	1	184	0	8	51	0

tr_compliance_rec7_series

Treatment compliance recoded 7 series

Distribution

Distribution of values for tr_compliance_rec7_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
tr_compliance_rec7_series	Treatment compliance recoded 7 series	character	0	1	40	0	12	77	0

referral_type_series

Referral type series

Distribution

Distribution of values for referral_type_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
referral_type_series	Referral type series	character	0	1	127	0	6	108	0

adm_age_rec3_series

Admission age recoded 3 series

Distribution

Distribution of values for adm_age_rec3_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
adm_age_rec3_series	Admission age recoded 3 series	character	0	1	15333	0	6	51	0

adm_date_rec2_series

Admission date recoded 2 series

Distribution

Distribution of values for adm_date_rec2_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
adm_date_rec2_series	Admission date recoded 2 series	character	0	1	14635	0	14	86	0

disch_date_rec6_series

Discharge date recoded 6 series

Distribution

Distribution of values for disch_date_rec6_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
disch_date_rec6_series	Discharge date recoded 6 series	character	0	1	14768	0	6	86	0

diagnostico_trs_fisico_series

Physical diagnosis series

Distribution

Distribution of values for diagnostico_trs_fisico_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
diagnostico_trs_fisico_series	Physical diagnosis series	character	0	1	362	0	6	198	0

otros_probl_at_sm_or_series

Other mental health problems series

Distribution

Distribution of values for otros_probl_at_sm_or_series

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
otros_probl_at_sm_or_series	Other mental health problems series	character	0	1	431	0	6	168	0

OBS

Observed flags or notes from cleaning (e.g., “Duplicated Cases”). Created during duplicate detection and resolution. Contains manual or automated flags for data quality issues, removed entries, etc. It is separated by semi-colons

Distribution

Distribution of values for OBS

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
OBS	Observed flags or notes from cleaning (e.g., “Duplicated Cases”). Created during duplicate detection and resolution. Contains manual or automated flags for data quality issues, removed entries, etc. It is separated by semi-colons	character	0	1	1053	1	0	634	0

occupation_status_corr

Corrected employment status Created in Step 4. Only kept for employed; nulled for inactive/unemployed; filled as ‘other’ if missing. Depends on occupation_condition_inferred, occupation_status.

Distribution

Distribution of values for occupation_status_corr

85961 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
occupation_status_corr	Corrected employment status Created in Step 4. Only kept for employed; nulled for inactive/unemployed; filled as ‘other’ if missing. Depends on occupation_condition_inferred, occupation_status.	character	85961	0.4722984	6	0	5	20	0

occupation_condition_corr24

Employment status

Distribution

Distribution of values for occupation_condition_corr24

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
occupation_condition_corr24	Employment status	character	0	1	3	0	8	10	0

plan_type_corr

Treatment modality

Distribution

Distribution of values for plan_type_corr

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
plan_type_corr	Treatment modality	character	0	1	5	0	4	6	0

ed_attainment_corr

Educational attainment

Distribution

Distribution of values for ed_attainment_corr

1105 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
ed_attainment_corr	Educational attainment	character	1105	0.9932166	3	0	23	34	0

polysubstance_strict

Polysubstance use

Distribution

Distribution of values for polysubstance_strict

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
polysubstance_strict	Polysubstance use	numeric	0	1	0	1	1	0.7185522	0.4497068	▃▁▁▁▇

icd10_diag1

ICD10 diagnosis 1 Created in Step 4. Separated from mod_psiq_cie_10 by “::”. Depends on mod_psiq_cie_10.

Distribution

Distribution of values for icd10_diag1

148878 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
icd10_diag1	ICD10 diagnosis 1 Created in Step 4. Separated from mod_psiq_cie_10 by “::”. Depends on mod_psiq_cie_10.	character	148878	0.0860605	94	0	6	149	0

icd10_diag2

ICD10 diagnosis 2 Created in Step 4. Separated from mod_psiq_cie_10 by “::”. Depends on mod_psiq_cie_10.

Distribution

Distribution of values for icd10_diag2

161349 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
icd10_diag2	ICD10 diagnosis 2 Created in Step 4. Separated from mod_psiq_cie_10 by “::”. Depends on mod_psiq_cie_10.	character	161349	0.0095029	84	0	7	202	0

icd10_diag3

ICD10 diagnosis 3 Created in Step 4. Separated from mod_psiq_cie_10 “::”. Depends on mod_psiq_cie_10.

Distribution

Distribution of values for icd10_diag3

162566 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
icd10_diag3	ICD10 diagnosis 3 Created in Step 4. Separated from mod_psiq_cie_10 “::”. Depends on mod_psiq_cie_10.	character	162566	0.002032	46	0	25	129	0

dsmiv_diag1

DSMIV diagnosis 1 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.

Distribution

Distribution of values for dsmiv_diag1

148878 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dsmiv_diag1	DSMIV diagnosis 1 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.	character	148878	0.0860605	94	0	6	149	0

dsmiv_diag2

DSMIV diagnosis 2 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.

Distribution

Distribution of values for dsmiv_diag2

161349 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dsmiv_diag2	DSMIV diagnosis 2 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.	character	161349	0.0095029	84	0	7	202	0

dsmiv_diag3

DSMIV diagnosis 3 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.

Distribution

Distribution of values for dsmiv_diag3

162566 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
dsmiv_diag3	DSMIV diagnosis 3 Created in Step 4. Separated from mod_psiq_dsm_iv “::”. Depends on mod_psiq_dsm_iv.	character	162566	0.002032	46	0	25	129	0

adm_year

Admission year

Distribution

Distribution of values for adm_year

0 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
adm_year	Admission year	numeric	0	1	2000	2017	2024	2017.116	4.182583	▁▁▆▇▆

porc_pobr

Poverty index of the commune of residence [log1p(x)=porc_pobr_log, centered= porc_pobr_c, six quantile groups= porc_pobr_c_cat6]

Distribution

Distribution of values for porc_pobr

3 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
porc_pobr	Poverty index of the commune of residence [log1p(x)=porc_pobr_log, centered= porc_pobr_c, six quantile groups= porc_pobr_c_cat6]	numeric	3	0.9999816	0.0017	0.13	0.64	0.1418689	0.0648752	▇▇▁▁▁

clasificacion

Urbanization level of the commune of residence

Distribution

Distribution of values for clasificacion

1 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	n_unique	empty	min	max	whitespace
clasificacion	Urbanization level of the commune of residence	character	1	0.9999939	3	0	5	6	0

km2_c

Centered km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.km_2 - mean(km_2). Depends on km_2.

Distribution

Distribution of values for km2_c

1 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
km2_c	Centered km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.km_2 - mean(km_2). Depends on km_2.	numeric	1	0.9999939	-2206	-1981	46483	0	5897.095	▇▁▁▁▁

km2_log

Log km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.log1p(km_2). Depends on km_2.

Distribution

Distribution of values for km2_log

1 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
km2_log	Log km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.log1p(km_2). Depends on km_2.	numeric	1	0.9999939	2.1	5.5	11	5.555289	2.179414	▆▇▇▃▂

porc_pobr_log

Log poverty Created in Step 3. Re-joined in Step 4. log1p(porc_pobr). Depends on porc_pobr.

Distribution

Distribution of values for porc_pobr_log

3 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
porc_pobr_log	Log poverty Created in Step 3. Re-joined in Step 4. log1p(porc_pobr). Depends on porc_pobr.	numeric	3	0.9999816	0.0017	0.12	0.49	0.1311123	0.0552621	▅▇▂▁▁

porc_pobr_c

Centered poverty Created in Step 3. Re-joined in Step 4. porc_pobr - mean(porc_pobr). Depends on porc_pobr.

Distribution

Distribution of values for porc_pobr_c

3 missing values.

Summary statistics

name	label	data_type	n_missing	complete_rate	min	median	max	mean	sd	hist
porc_pobr_c	Centered poverty Created in Step 3. Re-joined in Step 4. porc_pobr - mean(porc_pobr). Depends on porc_pobr.	numeric	3	0.9999816	-0.14	-0.0098	0.49	0	0.0648752	▇▇▁▁▁

Missingness report

Codebook table

JSON-LD metadata

The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.

{
  "datePublished": "2024-01-01",
  "temporalCoverage": "2010-2024",
  "spatialCoverage": "Chile",
  "creator": [
    {
      "@type": "Person",
      "givenName": "Álvaro",
      "familyName": "Castillo-Carniglia",
      "affiliation": {
        "@type": "Organization",
        "name": "Universidad San Sebastián, Chile"
      }
    },
    {
      "@type": "Person",
      "givenName": "Andrés",
      "familyName": "González-Santa Cruz",
      "email": "gonzalez.santacruz.andres@gmail.com",
      "affiliation": {
        "@type": "Organization",
        "name": "Universidad de Chile, Public Health"
      }
    },
    {
      "@type": "Person",
      "givenName": "Amaru",
      "familyName": "Agüero Jiménez",
      "affiliation": {
        "@type": "Organization",
        "name": "Universidad del Desarrollo, Chile"
      }
    }
  ],
  "citation": "Castillo-Carniglia, Á., González-Santa Cruz, A., & Agüero Jiménez, A. (2024). Workflow of data management and analysis - Chilean substance use treatment administrative data. Consolidation of Agreement 1 Databases from 2010 to 2024. Funded by FONDECYT regular 1191282.",
  "url": "https://github.com/FONDECYTACC/cons2025",
  "name": "Agreement 1 SENDA",
  "description": "Information About Agreement 1 of SENDA and MINSAL\n\n\n## Table of variables\nThis table contains variable names, labels, and number of missing values.\nSee the complete codebook for more.\n\n[truncated]\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.9.6).",
  "keywords": ["TABLE", "TABLE_rec_series", "rn", "rn_series", "num_trat_ant", "fecha_ultimo_tratamiento", "hash_key", "min_adm_age_rec3", "adm_age_rec3", "birth_date_rec", "adm_date_num_rec2", "adm_date_rec2", "dit_rec6", "disch_date_rec6", "disch_date_num_rec6_trans", "def_date", "adm_motive", "tr_compliance_rec7", "adm_disch_reason", "referral_type", "plan_type", "id_centro", "senda", "pub_center", "primary_sub", "second_sub1", "second_sub2", "second_sub3", "prim_sub_freq", "prim_sub_route", "LB_age_primary_onset_rec2", "UB_age_primary_onset_rec2", "age_primary_onset_rec2", "first_sub_used", "sus_ini_mod_mvv", "sus_ini_1", "sus_ini_2", "sus_ini_3", "LB_age_subs_onset_rec2", "UB_age_subs_onset_rec2", "age_subs_onset_rec2", "biopsych_comp", "mod_psiq_cie_10", "mod_psiq_dsm_iv", "diagnostico_trs_fisico", "otros_probl_at_sm_or", "sub_dep_icd10_status", "evaluacindelprocesoteraputico", "eva_consumo", "eva_fam", "eva_relinterp", "eva_ocupacion", "eva_sm", "eva_fisica", "eva_transgnorma", "dg_global_nec_int_soc_or", "dg_nec_int_soc_cap_hum_or", "dg_nec_int_soc_cap_fis_or", "dg_nec_int_soc_cap_soc_or", "dg_global_nec_int_soc_egr_or", "dg_nec_int_soc_cap_hum_egr_or", "dg_nec_int_soc_cap_fis_egr_or", "dg_nec_int_soc_cap_soc_egr_or", "usuario_tribunal_trat_droga", "nationality_cons", "ethnicity_c1_c6_historic", "discapacidad", "opcion_discapacidad", "sex_rec", "identidad_de_genero", "orientacion_sexual", "pregnant", "pregnant_disch", "marital_status", "tiene_menores_de_edad_a_cargo", "num_hijos_trat_res", "numero_de_hijos", "con_quien_vive", "tipo_de_vivienda", "precariedad_vivienda", "tenure_status_household", "servicios_basicos_95", "perso_dormitorio_vivienda", "ed_attainment", "occupation_condition", "occupation_status", "rubro_trabaja", "laboral_ingresos", "yr_block", "OBS_series", "senda_series", "pub_center_series", "id_centro_series", "disch_date_num_rec6", "dg_psiq_cie_10_instudy", "dg_psiq_cie_10_dg", "dg_psiq_dsm_iv_instudy", "dg_psiq_dsm_iv_dg", "plan_type_series", "tr_compliance_rec7_series", "referral_type_series", "adm_age_rec3_series", "adm_date_rec2_series", "disch_date_rec6_series", "diagnostico_trs_fisico_series", "otros_probl_at_sm_or_series", "OBS", "occupation_status_corr", "occupation_condition_corr24", "plan_type_corr", "ed_attainment_corr", "polysubstance_strict", "icd10_diag1", "icd10_diag2", "icd10_diag3", "dsmiv_diag1", "dsmiv_diag2", "dsmiv_diag3", "adm_year", "porc_pobr", "clasificacion", "km2_c", "km2_log", "porc_pobr_log", "porc_pobr_c"],
  "@context": "https://schema.org/",
  "@type": "Dataset",
  "variableMeasured": [
    {
      "name": "TABLE",
      "description": "Year of data collection (original SISTRAT table/year identifier). Represents the year the record was entered (e.g., \"2023\", \"2015\"). No transformation applied. Made in import_c1_top_data_adm_25.qmd",
      "@type": "propertyValue"
    },
    {
      "name": "TABLE_rec_series",
      "description": "Recoded series of TABLE",
      "@type": "propertyValue"
    },
    {
      "name": "rn",
      "description": "Row number or treatment episode sequence per patient. Created by `row_number() over (partition by hash_key order by adm_date)`, Step 1 (SISTRAT23_c1_2010_2024_df2). Identifies first, second, etc., treatment for each user.",
      "@type": "propertyValue"
    },
    {
      "name": "rn_series",
      "description": "Series of row number",
      "@type": "propertyValue"
    },
    {
      "name": "num_trat_ant",
      "description": "Number of prior treatments reported by patient. Direct import. May not be reliable. Not used.",
      "@type": "propertyValue"
    },
    {
      "name": "fecha_ultimo_tratamiento",
      "description": "Patient-reported time since last treatment (e.g., \"3 a 4 anos\"). Direct import. Categorical, not numeric. Many missing values (~50%)",
      "@type": "propertyValue"
    },
    {
      "name": "hash_key",
      "description": "Unique anonymized identifier for each individual (user/patient RUT derivative). Direct import from raw SISTRAT C1. Originally in uppercase letter. Generated by hashing the RUT (national ID) by MINSAL. Used to link multiple treatment episodes for the same person across years. No transformation.",
      "@type": "propertyValue"
    },
    {
      "name": "min_adm_age_rec3",
      "description": "min(adm_age_rec3) grouped by hash_key. Critical benchmark for validating/imputing onset ages.",
      "@type": "propertyValue"
    },
    {
      "name": "adm_age_rec3",
      "description": "Admission age [log1p(x)=adm_age_log, centered= adm_age_c,^2=adm_age_pow2, ^3=adm_age_pow3, three groups= adm_age_rec3_cat]",
      "@type": "propertyValue"
    },
    {
      "name": "birth_date_rec",
      "description": "Final authoritative date of birth. Created by selecting/imputing best `birth_date` per `hash_key` (via `kNN`, logic, or min/max validation). Used to recalculate `adm_age_rec`.",
      "@type": "propertyValue"
    },
    {
      "name": "adm_date_num_rec2",
      "description": "Numeric admission date recoded version 2",
      "@type": "propertyValue"
    },
    {
      "name": "adm_date_rec2",
      "description": "Intermediate admission date Created in Step 2 (0.c) for the resolution of overlaps",
      "@type": "propertyValue"
    },
    {
      "name": "dit_rec6",
      "description": "Length of stay in treatment (months) [log1p(x)=treat_log, ^2=treat_days_pow2, ^3=treat_days_pow3, <90days=treat_lt_90]",
      "@type": "propertyValue"
    },
    {
      "name": "disch_date_rec6",
      "description": "Final discharge date for longitudinal analysis. Created as selected consistent version for time-to-event modeling.",
      "@type": "propertyValue"
    },
    {
      "name": "disch_date_num_rec6_trans",
      "description": "Imputed discharge based on reference date Created in Step 3. Missing discharge dates were filled using a default value calculated from a fixed retrieval date (e.g., May 28, 2025), ensuring consistency across all treatment records and uncovering censorship mechanisms.",
      "@type": "propertyValue"
    },
    {
      "name": "def_date",
      "description": "Date of death (if applicable, mostly NA). Created from external mortality linkage (not in provided scripts). Parsed from mortality registry (dia_def, mes_def, ano_def), imputing missing day as 15; earliest date kept when multiple. Used to censor discharges after death. See Duplicates_25_2.qmd (pre-00.a).",
      "@type": "propertyValue"
    },
    {
      "name": "adm_motive",
      "description": "Admission motive",
      "@type": "propertyValue"
    },
    {
      "name": "tr_compliance_rec7",
      "description": "Treatment compliance category. Created in Step 4. Removed cases (n=3) with an ongoing treatment motive but with a posterior treatment after. Replaced for dropout (they had incomplete discharge information)",
      "@type": "propertyValue"
    },
    {
      "name": "adm_disch_reason",
      "description": "Placeholder for administrative discharge reason (mostly empty). Created as copy of `motivo_de_egreso_alta_administrativa`. Derived/translated from motivo_de_egreso_alta_administrativa; listed among deduplication key variables in Step 2. 47%-56% missing in patients with adm. discharge.",
      "@type": "propertyValue"
    },
    {
      "name": "referral_type",
      "description": "Recoded type of referral center. Created from `tipo_centro_derivacion` (translation): e.g., \"otro centro\" , \"other facility\", \"cosam\", \"primary health care\".",
      "@type": "propertyValue"
    },
    {
      "name": "plan_type",
      "description": "Recoded treatment plan type. Created as copy and translation of `tipo_de_plan` (step 1). Used in collapsing logic and outcome modeling.",
      "@type": "propertyValue"
    },
    {
      "name": "id_centro",
      "description": "Center ID number. Direct import. Used to link center attributes, collapse duplicates, and derive `centro_muj` (women-specific centers).",
      "@type": "propertyValue"
    },
    {
      "name": "senda",
      "description": "Indicator if treatment was under SENDA agreement (\"si\"/\"no\"). Direct import. Used to derive `senda_adm_date` and flag SENDA-specific episodes. No transformation initially. According to SENDA professionals, patients may be in SENDA Yes programs may anyways part of SENDA programs in some cases",
      "@type": "propertyValue"
    },
    {
      "name": "pub_center",
      "description": "Binary indicator for public center. Created as `tipo_centro == \"publico\"`. Used in institutional comparisons.",
      "value": "1. FALSE,\n2. TRUE",
      "@type": "propertyValue"
    },
    {
      "name": "primary_sub",
      "description": "Primary substance of use",
      "@type": "propertyValue"
    },
    {
      "name": "second_sub1",
      "description": "Normalized secondary substances at admission (1)",
      "@type": "propertyValue"
    },
    {
      "name": "second_sub2",
      "description": "Normalized secondary substances at admission (2)",
      "@type": "propertyValue"
    },
    {
      "name": "second_sub3",
      "description": "Normalized secondary substances at admission (3)",
      "@type": "propertyValue"
    },
    {
      "name": "prim_sub_freq",
      "description": "Frequency of primary substance use at admission (recoded: prim_sub_freq_rec)",
      "@type": "propertyValue"
    },
    {
      "name": "prim_sub_route",
      "description": "Recoded route of administration. Created from `via_administracion_sustancia_principal` into standardized terms.",
      "@type": "propertyValue"
    },
    {
      "name": "LB_age_primary_onset_rec2",
      "description": "Lower bound age of primary substance onset recoded 2",
      "@type": "propertyValue"
    },
    {
      "name": "UB_age_primary_onset_rec2",
      "description": "Upper bound age of primary substance onset recoded 2",
      "@type": "propertyValue"
    },
    {
      "name": "age_primary_onset_rec2",
      "description": "Created in Step 3.",
      "@type": "propertyValue"
    },
    {
      "name": "first_sub_used",
      "description": "Normalized first substance used. Created as `tolower(gsub(\"_\", \" \", sustancia_de_inicio))`. Input for resolving inconsistencies, prioritizing most vulnerable value = `sus_ini_mod_mvv`. Despite this, this variable was normalized in Step 3 for inconsistent values in patients.",
      "@type": "propertyValue"
    },
    {
      "name": "sus_ini_mod_mvv",
      "description": "Sus ini mod mvv",
      "value": "1. cocaine paste,\n2. cocaine powder,\n3. alcohol,\n4. marijuana,\n5. others",
      "@type": "propertyValue"
    },
    {
      "name": "sus_ini_1",
      "description": "Sus ini 1",
      "@type": "propertyValue"
    },
    {
      "name": "sus_ini_2",
      "description": "Sus ini 2",
      "@type": "propertyValue"
    },
    {
      "name": "sus_ini_3",
      "description": "Sus ini 3",
      "@type": "propertyValue"
    },
    {
      "name": "LB_age_subs_onset_rec2",
      "description": "Lower bound age of substance onset recoded 2",
      "@type": "propertyValue"
    },
    {
      "name": "UB_age_subs_onset_rec2",
      "description": "Upper bound age of substance onset recoded 2",
      "@type": "propertyValue"
    },
    {
      "name": "age_subs_onset_rec2",
      "description": "Created in Step 3.",
      "@type": "propertyValue"
    },
    {
      "name": "biopsych_comp",
      "description": "Recoded biopsychosocial severity. Created from `compromiso_biopsicosocial`: e.g., \"moderado\", \"2-moderate\".",
      "@type": "propertyValue"
    },
    {
      "name": "mod_psiq_cie_10",
      "description": "Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses",
      "@type": "propertyValue"
    },
    {
      "name": "mod_psiq_dsm_iv",
      "description": "Created in Step 3, concatenated main and sub-dg to allow multiple diagnoses",
      "@type": "propertyValue"
    },
    {
      "name": "diagnostico_trs_fisico",
      "description": "Physical health diagnosis. Direct import. Often concatenated (e.g., \"Hepatitis alcoholica: cardiopatías\"). Preserved as-is for clinical profiling.",
      "@type": "propertyValue"
    },
    {
      "name": "otros_probl_at_sm_or",
      "description": "Other mental health issues (e.g., \"abuso sexual\"). Direct import. Recoded to `otros_probl_at_sm_or`. Used in vulnerability and trauma profiling.",
      "@type": "propertyValue"
    },
    {
      "name": "sub_dep_icd10_status",
      "description": "Severity of Substance Use Disorder (SUD)",
      "@type": "propertyValue"
    },
    {
      "name": "evaluacindelprocesoteraputico",
      "description": "Therapeutic process evaluation (e.g., \"logro alto\"). Direct import. Recoded to standardized categories. Used in outcome and program effectiveness analysis.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_consumo",
      "description": "Evaluation of consumption pattern at discharge. Direct import. Part of multi-domain outcome assessment. Recoded similarly.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_fam",
      "description": "Family situation evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_relinterp",
      "description": "Interpersonal relations evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_ocupacion",
      "description": "Occupational situation evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_sm",
      "description": "Mental health evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_fisica",
      "description": "Physical health evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "eva_transgnorma",
      "description": "Social norm transgression evaluation at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_global_nec_int_soc_or",
      "description": "Global social integration need at admission. Direct import. Recoded to `dg_global_nec_int_soc_or`. Categorized as \"altas\", \"medias\", \"bajas\". Used in social vulnerability index.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_hum_or",
      "description": "Human capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_hum_or`. Part of social integration profile.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_fis_or",
      "description": "Physical capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_fis_or`.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_soc_or",
      "description": "Social capital need at admission. Direct import. Recoded to `dg_nec_int_soc_cap_soc_or`.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_global_nec_int_soc_egr_or",
      "description": "Global social integration need at discharge. Direct import. Recoded similarly to admission version (_60). Used for delta/change analysis.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_hum_egr_or",
      "description": "Human capital need at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_fis_egr_or",
      "description": "Physical capital need at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "dg_nec_int_soc_cap_soc_egr_or",
      "description": "Social capital need at discharge. Direct import.",
      "@type": "propertyValue"
    },
    {
      "name": "usuario_tribunal_trat_droga",
      "description": "Court-referred to drug treatment (very unbalanced, ~1% yes)",
      "@type": "propertyValue"
    },
    {
      "name": "nationality_cons",
      "description": "Recoded/standardized from nacionalidad or pais_nacimiento.",
      "@type": "propertyValue"
    },
    {
      "name": "ethnicity_c1_c6_historic",
      "description": "Concatenated unique non-Chilean/non-\"no pertenece\" values from etnia (C1) and ethnicity (C6), grouped by hash_key.",
      "@type": "propertyValue"
    },
    {
      "name": "discapacidad",
      "description": "Indicator of disability (\"si\"/\"no\"). Direct import. Used with `opcion_discapacidad` for disability profiling. Starts coding in 2019",
      "@type": "propertyValue"
    },
    {
      "name": "opcion_discapacidad",
      "description": "Type of disability (e.g., \"de causa psiquica\"). Direct import. Only populated if `discapacidad == \"si\"`. Used in accessibility and needs assessment.Starts coding in 2019",
      "@type": "propertyValue"
    },
    {
      "name": "sex_rec",
      "description": "Sex (often used for biological categorization)",
      "@type": "propertyValue"
    },
    {
      "name": "identidad_de_genero",
      "description": "Gender identity (e.g., \"masculino\", \"femenino\"). Direct import. Recoded to `identidad_de_genero` factor. Used to validate/override `sexo` in `sex_rec` (Step 2). Starts coding in 2019",
      "@type": "propertyValue"
    },
    {
      "name": "orientacion_sexual",
      "description": "Sexual orientation (e.g., \"heterosexual\"). Direct import. Sparse. Preserved for inclusivity analysis.Starts coding in 2022",
      "@type": "propertyValue"
    },
    {
      "name": "pregnant",
      "description": "Recoded pregnancy status at admission. Created from `se_trata_de_una_mujer_embarazada` (NA = \"no\"). Used in gender-specific analysis (Step 3). This variable (indicating if a woman is pregnant) seems to beintroduced in 2011.",
      "@type": "propertyValue"
    },
    {
      "name": "pregnant_disch",
      "description": "Recoded pregnancy status at discharge. Created from `ha_estado_embarazada_egreso`. Used in gender-specific analysis (Step 3). Sparse. Seems to be only accurately collected starting in 2017. Created to capture pregnancy status specifically at treatment discharge.",
      "@type": "propertyValue"
    },
    {
      "name": "marital_status",
      "description": "Marital status",
      "@type": "propertyValue"
    },
    {
      "name": "tiene_menores_de_edad_a_cargo",
      "description": "Indicator if responsible for minors (\"si\"/\"no\"). Direct import. Mostly missing before 2015 (Duplicates_25.txt). Recoded to binary flag. Used in family vulnerability index.",
      "@type": "propertyValue"
    },
    {
      "name": "num_hijos_trat_res",
      "description": "Number of children entering residential treatment with patient. Direct import. Often missing or 0. Later used to derive binary flag `hijos_trat_res` (\"Had children in treatments\").",
      "@type": "propertyValue"
    },
    {
      "name": "numero_de_hijos",
      "description": "Number of children reported by patient. Direct import. Values >11 flagged as implausible (Duplicates_25.txt). Used in `kNN` imputation and to derive `tiene_menores_de_edad_a_cargo`.",
      "@type": "propertyValue"
    },
    {
      "name": "con_quien_vive",
      "description": "Living arrangement/Cohabitation status",
      "@type": "propertyValue"
    },
    {
      "name": "tipo_de_vivienda",
      "description": "Type of housing",
      "@type": "propertyValue"
    },
    {
      "name": "precariedad_vivienda",
      "description": "Precarious housing. Direct import. Available since 2022 databases.",
      "@type": "propertyValue"
    },
    {
      "name": "tenure_status_household",
      "description": "Housing situation",
      "@type": "propertyValue"
    },
    {
      "name": "servicios_basicos_95",
      "description": "Basic sanitation services. Direct import. Available since 2022 databases.",
      "@type": "propertyValue"
    },
    {
      "name": "perso_dormitorio_vivienda",
      "description": "Persons per dwelling bedroom Direct import. Available since 2022 databases.",
      "@type": "propertyValue"
    },
    {
      "name": "ed_attainment",
      "description": "Recoded education level. Created from `escolaridad_ultimo_ano_cursado` into standardized categories (e.g., \"media incompleta\" = \"2-Completed high school or less\").",
      "@type": "propertyValue"
    },
    {
      "name": "occupation_condition",
      "description": "Recoded employment status. Created from `condicion_ocupacional`: e.g., \"cesante\"= \"unemployed\" (in Step 1).",
      "@type": "propertyValue"
    },
    {
      "name": "occupation_status",
      "description": "Recoded employment category. Created from `categoria_ocupacional`. Sparse; often NA.",
      "@type": "propertyValue"
    },
    {
      "name": "rubro_trabaja",
      "description": "Occupational sector (e.g., \"trabajadores no calificados\"). Direct import. Recoded to `rubro_trabaja_mod`. 68% missing. 13.8% among employeed",
      "@type": "propertyValue"
    },
    {
      "name": "laboral_ingresos",
      "description": "Monthly income. Direct import. Available since 2022 databases.",
      "@type": "propertyValue"
    },
    {
      "name": "yr_block",
      "description": "Birth year block (e.g., 1980, 1990) for anonymization or grouping. Created by rounding `birth_date` year to nearest decade (e.g., `floor(year(birth_date)/10)*10`). To look for data similarities (Step 1)",
      "@type": "propertyValue"
    },
    {
      "name": "OBS_series",
      "description": "OBS series",
      "@type": "propertyValue"
    },
    {
      "name": "senda_series",
      "description": "SENDA series",
      "@type": "propertyValue"
    },
    {
      "name": "pub_center_series",
      "description": "Public center series",
      "@type": "propertyValue"
    },
    {
      "name": "id_centro_series",
      "description": "Center ID series",
      "@type": "propertyValue"
    },
    {
      "name": "disch_date_num_rec6",
      "description": "Numeric discharge date recoded 6",
      "@type": "propertyValue"
    },
    {
      "name": "dg_psiq_cie_10_instudy",
      "description": "Psychiatric comorbidity (ICD-10)",
      "@type": "propertyValue"
    },
    {
      "name": "dg_psiq_cie_10_dg",
      "description": "Mutually exclusive (as corrected in Step 3)",
      "@type": "propertyValue"
    },
    {
      "name": "dg_psiq_dsm_iv_instudy",
      "description": "Psychiatric comorbidity (DSM-IV)",
      "@type": "propertyValue"
    },
    {
      "name": "dg_psiq_dsm_iv_dg",
      "description": "Mutually exclusive (as corrected in Step 3)",
      "@type": "propertyValue"
    },
    {
      "name": "plan_type_series",
      "description": "Plan type series",
      "@type": "propertyValue"
    },
    {
      "name": "tr_compliance_rec7_series",
      "description": "Treatment compliance recoded 7 series",
      "@type": "propertyValue"
    },
    {
      "name": "referral_type_series",
      "description": "Referral type series",
      "@type": "propertyValue"
    },
    {
      "name": "adm_age_rec3_series",
      "description": "Admission age recoded 3 series",
      "@type": "propertyValue"
    },
    {
      "name": "adm_date_rec2_series",
      "description": "Admission date recoded 2 series",
      "@type": "propertyValue"
    },
    {
      "name": "disch_date_rec6_series",
      "description": "Discharge date recoded 6 series",
      "@type": "propertyValue"
    },
    {
      "name": "diagnostico_trs_fisico_series",
      "description": "Physical diagnosis series",
      "@type": "propertyValue"
    },
    {
      "name": "otros_probl_at_sm_or_series",
      "description": "Other mental health problems series",
      "@type": "propertyValue"
    },
    {
      "name": "OBS",
      "description": "Observed flags or notes from cleaning (e.g., \"Duplicated Cases\"). Created during duplicate detection and resolution. Contains manual or automated flags for data quality issues, removed entries, etc. It is separated by semi-colons",
      "@type": "propertyValue"
    },
    {
      "name": "occupation_status_corr",
      "description": "Corrected employment status Created in Step 4. Only kept for employed; nulled for inactive/unemployed; filled as 'other' if missing. Depends on occupation_condition_inferred, occupation_status.",
      "@type": "propertyValue"
    },
    {
      "name": "occupation_condition_corr24",
      "description": "Employment status",
      "@type": "propertyValue"
    },
    {
      "name": "plan_type_corr",
      "description": "Treatment modality",
      "@type": "propertyValue"
    },
    {
      "name": "ed_attainment_corr",
      "description": "Educational attainment",
      "@type": "propertyValue"
    },
    {
      "name": "polysubstance_strict",
      "description": "Polysubstance use",
      "@type": "propertyValue"
    },
    {
      "name": "icd10_diag1",
      "description": "ICD10 diagnosis 1 Created in Step 4. Separated from mod_psiq_cie_10 by \"::\". Depends on mod_psiq_cie_10.",
      "@type": "propertyValue"
    },
    {
      "name": "icd10_diag2",
      "description": "ICD10 diagnosis 2 Created in Step 4. Separated from mod_psiq_cie_10 by \"::\". Depends on mod_psiq_cie_10.",
      "@type": "propertyValue"
    },
    {
      "name": "icd10_diag3",
      "description": "ICD10 diagnosis 3 Created in Step 4. Separated from mod_psiq_cie_10 \"::\". Depends on mod_psiq_cie_10.",
      "@type": "propertyValue"
    },
    {
      "name": "dsmiv_diag1",
      "description": "DSMIV diagnosis 1 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
      "@type": "propertyValue"
    },
    {
      "name": "dsmiv_diag2",
      "description": "DSMIV diagnosis 2 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
      "@type": "propertyValue"
    },
    {
      "name": "dsmiv_diag3",
      "description": "DSMIV diagnosis 3 Created in Step 4. Separated from mod_psiq_dsm_iv \"::\". Depends on mod_psiq_dsm_iv.",
      "@type": "propertyValue"
    },
    {
      "name": "adm_year",
      "description": "Admission year",
      "@type": "propertyValue"
    },
    {
      "name": "porc_pobr",
      "description": "Poverty index of the commune of residence [log1p(x)=porc_pobr_log, centered= porc_pobr_c, six quantile groups= porc_pobr_c_cat6]",
      "@type": "propertyValue"
    },
    {
      "name": "clasificacion",
      "description": "Urbanization level of the commune of residence",
      "@type": "propertyValue"
    },
    {
      "name": "km2_c",
      "description": "Centered km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.km_2 - mean(km_2). Depends on km_2.",
      "@type": "propertyValue"
    },
    {
      "name": "km2_log",
      "description": "Log km^2 Created in Step 4. Created in Step 4. km_2 - mean(km_2). Depends on km_2.log1p(km_2). Depends on km_2.",
      "@type": "propertyValue"
    },
    {
      "name": "porc_pobr_log",
      "description": "Log poverty Created in Step 3. Re-joined in Step 4. log1p(porc_pobr). Depends on porc_pobr.",
      "@type": "propertyValue"
    },
    {
      "name": "porc_pobr_c",
      "description": "Centered poverty Created in Step 3. Re-joined in Step 4. porc_pobr - mean(porc_pobr). Depends on porc_pobr.",
      "@type": "propertyValue"
    }
  ]
}`