From b7b98a613f303bcd6757044b0dd5b5a2e254ede2 Mon Sep 17 00:00:00 2001 From: Anthony Sena Date: Thu, 2 May 2024 17:03:00 -0400 Subject: [PATCH 1/3] WIP --- .../resultsDataModelSpecification.csv | 8 ++-- inst/sql/sql_server/ResultTables.sql | 46 +++++++++++-------- 2 files changed, 31 insertions(+), 23 deletions(-) diff --git a/inst/settings/resultsDataModelSpecification.csv b/inst/settings/resultsDataModelSpecification.csv index f84025f..4b7c03d 100644 --- a/inst/settings/resultsDataModelSpecification.csv +++ b/inst/settings/resultsDataModelSpecification.csv @@ -105,8 +105,6 @@ cohort_counts,person_count,int,Y,N,N,N,The number of distinct people in each coh cohort_counts,min_exposure_time,bigint,N,N,N,N,Minimum exposure time across cohort cohort_counts,mean_exposure_time,bigint,N,N,N,N,Mean exposure time across cohort cohort_counts,max_exposure_time,bigint,N,N,N,N,Max exposure time across cohort -migration,MIGRATION_FILE,varchar(100),N,N,N,N,migration files that have been run -migration,MIGRATION_ORDER,int,N,N,N,N,migration files implementation order -package_version,VERSION_NUMBER,varchar(10),N,N,N,N,version of characterization package - - +migration,migration_file,varchar(100),N,Y,N,N,migration files that have been run +migration,migration_order,int,N,Y,N,N,migration files implementation order +package_version,version_number,varchar(10),N,Y,N,N,version of characterization package diff --git a/inst/sql/sql_server/ResultTables.sql b/inst/sql/sql_server/ResultTables.sql index 663249e..8b4632f 100644 --- a/inst/sql/sql_server/ResultTables.sql +++ b/inst/sql/sql_server/ResultTables.sql @@ -3,10 +3,11 @@ CREATE TABLE @my_schema.@table_prefixtime_to_event ( target_cohort_definition_id bigint NOT NULL, outcome_cohort_definition_id bigint NOT NULL, outcome_type varchar(20) NOT NULL, - target_outcome_type varchar(20) NOT NULL, + target_outcome_type varchar(40) NOT NULL, time_to_event int NOT NULL, num_events int NOT NULL, - time_scale varchar(20) NOT NULL + time_scale varchar(20) NOT NULL, + PRIMARY KEY (database_id, target_cohort_definition_id, outcome_cohort_definition_id, outcome_type, target_outcome_type) ); CREATE TABLE @my_schema.@table_prefixrechallenge_fail_case_series ( @@ -27,7 +28,8 @@ CREATE TABLE @my_schema.@table_prefixrechallenge_fail_case_series ( rechallenge_exposure_start_date_offset int NOT NULL, rechallenge_exposure_end_date_offset int NOT NULL, rechallenge_outcome_number int NOT NULL, - rechallenge_outcome_start_date_offset int NOT NULL + rechallenge_outcome_start_date_offset int NOT NULL, + PRIMARY KEY (database_id, target_cohort_definition_id, outcome_cohort_definition_id, person_key) ); CREATE TABLE @my_schema.@table_prefixdechallenge_rechallenge ( @@ -50,7 +52,8 @@ CREATE TABLE @my_schema.@table_prefixdechallenge_rechallenge ( pct_dechallenge_fail float, pct_rechallenge_attempt float, pct_rechallenge_success float, - pct_rechallenge_fail float + pct_rechallenge_fail float, + PRIMARY KEY (database_id, dechallenge_stop_interval, dechallenge_evaluation_window, target_cohort_definition_id, outcome_cohort_definition_id) ); @@ -62,17 +65,19 @@ CREATE TABLE @my_schema.@table_prefixsettings ( risk_window_start int, start_anchor varchar(15), risk_window_end int, - end_anchor varchar(15) + end_anchor varchar(15), + PRIMARY KEY (run_id, database_id) ); -- added this table CREATE TABLE @my_schema.@table_prefixcohort_details ( run_id int NOT NULL, database_id varchar(100), - cohort_definition_id int, + cohort_definition_id bigint, target_cohort_id int, outcome_cohort_id int, - cohort_type varchar(10) + cohort_type varchar(10), + PRIMARY KEY (run_id, database_id) ); CREATE TABLE @my_schema.@table_prefixanalysis_ref ( @@ -84,32 +89,35 @@ CREATE TABLE @my_schema.@table_prefixanalysis_ref ( start_day int, end_day int, is_binary varchar(1), - missing_means_zero varchar(1) + missing_means_zero varchar(1), + PRIMARY KEY (database_id, run_id) ); CREATE TABLE @my_schema.@table_prefixcovariate_ref ( run_id int NOT NULL, database_id varchar(100) NOT NULL, - covariate_id int NOT NULL, + covariate_id bigint NOT NULL, covariate_name varchar(max) NOT NULL, analysis_id int NOT NULL, - concept_id int + concept_id bigint, + PRIMARY KEY (database_id, run_id, covariate_id) ); CREATE TABLE @my_schema.@table_prefixcovariates ( run_id int NOT NULL, database_id varchar(100) NOT NULL, - cohort_definition_id int NOT NULL, - covariate_id int NOT NULL, + cohort_definition_id bigint NOT NULL, + covariate_id bigint NOT NULL, sum_value int NOT NULL, - average_value float NOT NULL + average_value float NOT NULL, + PRIMARY KEY (database_id, run_id, cohort_definition_id, covariate_id) ); CREATE TABLE @my_schema.@table_prefixcovariates_continuous ( run_id int NOT NULL, database_id varchar(100) NOT NULL, - cohort_definition_id int NOT NULL, - covariate_id int NOT NULL, + cohort_definition_id bigint NOT NULL, + covariate_id bigint NOT NULL, count_value int NOT NULL, min_value float, max_value float, @@ -119,13 +127,15 @@ CREATE TABLE @my_schema.@table_prefixcovariates_continuous ( p_10_value float, p_25_value float, p_75_value float, - p_90_value float + p_90_value float, + PRIMARY KEY (database_id, run_id, cohort_definition_id, covariate_id) ); CREATE TABLE @my_schema.@table_prefixcohort_counts( run_id int NOT NULL, database_id varchar(100) NOT NULL, - cohort_definition_id int NOT NULL, + cohort_definition_id bigint NOT NULL, row_count int NOT NULL, - person_count int NOT NULL + person_count int NOT NULL, + PRIMARY KEY (run_id, database_id) ); From 8eceef247c2622db23f0d885c76cf4cd82033fdd Mon Sep 17 00:00:00 2001 From: jreps Date: Fri, 3 May 2024 08:58:39 -0400 Subject: [PATCH 2/3] fixing primary keys for test to pass fixing primary key for test to pass --- .../resultsDataModelSpecification.csv | 20 ++++++++-------- inst/sql/sql_server/ResultTables.sql | 24 +++++++++---------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/inst/settings/resultsDataModelSpecification.csv b/inst/settings/resultsDataModelSpecification.csv index 4b7c03d..339ab2a 100644 --- a/inst/settings/resultsDataModelSpecification.csv +++ b/inst/settings/resultsDataModelSpecification.csv @@ -4,16 +4,16 @@ time_to_event,target_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition i time_to_event,outcome_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the outcome cohort time_to_event,outcome_type,varchar(100),Y,Y,N,N,Is the outvome a first occurrence or repeat time_to_event,target_outcome_type,varchar(40),Y,Y,N,N,When does the outcome occur relative to target -time_to_event,time_to_event,int,Y,N,N,N,The time (in days) from target index to outcome start +time_to_event,time_to_event,int,Y,Y,N,N,The time (in days) from target index to outcome start time_to_event,num_events,int,Y,N,N,N,Number of events that occur during the specified time to event -time_to_event,time_scale,varchar(20),Y,N,N,N,time scale for the number of events +time_to_event,time_scale,varchar(20),Y,Y,N,N,time scale for the number of events rechallenge_fail_case_series,database_id,varchar(100),Y,Y,N,N,The database identifier -rechallenge_fail_case_series,dechallenge_stop_interval,int,Y,N,N,N,The time period that É -rechallenge_fail_case_series,dechallenge_evaluation_window,int,Y,N,N,N,The time period that É +rechallenge_fail_case_series,dechallenge_stop_interval,int,Y,Y,N,N,The time period that É +rechallenge_fail_case_series,dechallenge_evaluation_window,int,Y,Y,N,N,The time period that É rechallenge_fail_case_series,target_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the target cohort rechallenge_fail_case_series,outcome_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the outcome cohort rechallenge_fail_case_series,person_key,int,Y,Y,N,N,The dense rank for the patient (an identifier that is not the same as the database) -rechallenge_fail_case_series,subject_id,bigint,Y,N,N,N,The person identifier for the failed case series (optional) +rechallenge_fail_case_series,subject_id,bigint,N,N,N,N,The person identifier for the failed case series (optional) rechallenge_fail_case_series,dechallenge_exposure_number,int,Y,N,N,N,The number of times a dechallenge has occurred rechallenge_fail_case_series,dechallenge_exposure_start_date_offset,int,Y,N,N,N,The offset for the dechallenge start (number of days after index) rechallenge_fail_case_series,dechallenge_exposure_end_date_offset,int,Y,N,N,N,The offset for the dechallenge end (number of days after index) @@ -93,18 +93,18 @@ settings,outcome_washout_days,int,N,N,N,N,Patients with outcome during washout a settings,min_characterization_mean,float,N,N,N,N,Minimum fraction for feature extraction cohort_details,run_id,int,Y,Y,N,N,The run identifier cohort_details,database_id,varchar(100),Y,Y,N,N,The database identifier -cohort_details,cohort_definition_id,int,Y,N,N,N,The study cohort id +cohort_details,cohort_definition_id,int,Y,Y,N,N,The study cohort id cohort_details,cohort_type,varchar(10),Y,N,N,N,The cohort type cohort_details,target_cohort_id,int,Y,N,N,N,The target cohort id cohort_details,outcome_cohort_id,int,Y,N,N,N,The outcome cohort id cohort_counts,run_id,int,Y,Y,N,N,The run identifier cohort_counts,database_id,varchar(100),Y,Y,N,N,The database identifier -cohort_counts,cohort_definition_id,int,Y,N,N,N,The study cohort id +cohort_counts,cohort_definition_id,int,Y,Y,N,N,The study cohort id cohort_counts,row_count,int,Y,N,N,N,The number of rows in each cohort cohort_counts,person_count,int,Y,N,N,N,The number of distinct people in each cohort cohort_counts,min_exposure_time,bigint,N,N,N,N,Minimum exposure time across cohort cohort_counts,mean_exposure_time,bigint,N,N,N,N,Mean exposure time across cohort cohort_counts,max_exposure_time,bigint,N,N,N,N,Max exposure time across cohort -migration,migration_file,varchar(100),N,Y,N,N,migration files that have been run -migration,migration_order,int,N,Y,N,N,migration files implementation order -package_version,version_number,varchar(10),N,Y,N,N,version of characterization package +migration,migration_file,varchar(100),N,N,N,N,migration files that have been run +migration,migration_order,int,N,N,N,N,migration files implementation order +package_version,version_number,varchar(10),N,N,N,N,version of characterization package diff --git a/inst/sql/sql_server/ResultTables.sql b/inst/sql/sql_server/ResultTables.sql index 8b4632f..6f88bdd 100644 --- a/inst/sql/sql_server/ResultTables.sql +++ b/inst/sql/sql_server/ResultTables.sql @@ -7,14 +7,14 @@ CREATE TABLE @my_schema.@table_prefixtime_to_event ( time_to_event int NOT NULL, num_events int NOT NULL, time_scale varchar(20) NOT NULL, - PRIMARY KEY (database_id, target_cohort_definition_id, outcome_cohort_definition_id, outcome_type, target_outcome_type) + PRIMARY KEY (database_id, target_cohort_definition_id, outcome_cohort_definition_id, outcome_type, target_outcome_type, time_to_event, time_scale) ); CREATE TABLE @my_schema.@table_prefixrechallenge_fail_case_series ( --run_id, database_id varchar(100) NOT NULL, - dechallenge_stop_interval int, - dechallenge_evaluation_window int, + dechallenge_stop_interval int NOT NULL, + dechallenge_evaluation_window int NOT NULL, target_cohort_definition_id bigint NOT NULL, outcome_cohort_definition_id bigint NOT NULL, person_key int NOT NULL, @@ -29,13 +29,13 @@ CREATE TABLE @my_schema.@table_prefixrechallenge_fail_case_series ( rechallenge_exposure_end_date_offset int NOT NULL, rechallenge_outcome_number int NOT NULL, rechallenge_outcome_start_date_offset int NOT NULL, - PRIMARY KEY (database_id, target_cohort_definition_id, outcome_cohort_definition_id, person_key) + PRIMARY KEY (database_id, dechallenge_stop_interval,dechallenge_evaluation_window, target_cohort_definition_id, outcome_cohort_definition_id, person_key) ); CREATE TABLE @my_schema.@table_prefixdechallenge_rechallenge ( database_id varchar(100) NOT NULL, - dechallenge_stop_interval int, - dechallenge_evaluation_window int, + dechallenge_stop_interval int NOT NULL, + dechallenge_evaluation_window int NOT NULL, target_cohort_definition_id bigint NOT NULL, outcome_cohort_definition_id bigint NOT NULL, num_exposure_eras int NOT NULL, @@ -60,7 +60,7 @@ CREATE TABLE @my_schema.@table_prefixdechallenge_rechallenge ( -- covariateSettings CREATE TABLE @my_schema.@table_prefixsettings ( run_id int NOT NULL, - database_id varchar(100), + database_id varchar(100) NOT NULL, covariate_setting_json varchar(MAX), risk_window_start int, start_anchor varchar(15), @@ -72,12 +72,12 @@ CREATE TABLE @my_schema.@table_prefixsettings ( -- added this table CREATE TABLE @my_schema.@table_prefixcohort_details ( run_id int NOT NULL, - database_id varchar(100), - cohort_definition_id bigint, + database_id varchar(100) NOT NULL, + cohort_definition_id bigint NOT NULL, target_cohort_id int, outcome_cohort_id int, cohort_type varchar(10), - PRIMARY KEY (run_id, database_id) + PRIMARY KEY (run_id, database_id,cohort_definition_id) ); CREATE TABLE @my_schema.@table_prefixanalysis_ref ( @@ -90,7 +90,7 @@ CREATE TABLE @my_schema.@table_prefixanalysis_ref ( end_day int, is_binary varchar(1), missing_means_zero varchar(1), - PRIMARY KEY (database_id, run_id) + PRIMARY KEY (database_id, run_id, analysis_id ) ); CREATE TABLE @my_schema.@table_prefixcovariate_ref ( @@ -137,5 +137,5 @@ CREATE TABLE @my_schema.@table_prefixcohort_counts( cohort_definition_id bigint NOT NULL, row_count int NOT NULL, person_count int NOT NULL, - PRIMARY KEY (run_id, database_id) + PRIMARY KEY (run_id, database_id, cohort_definition_id) ); From fbfb3851ad0baf78fb7ec812aae24564efcb0a53 Mon Sep 17 00:00:00 2001 From: Anthony Sena Date: Fri, 3 May 2024 10:30:32 -0400 Subject: [PATCH 3/3] Updating resultsDataModelSpecification.csv to use Yes/No vs Y/N --- .../resultsDataModelSpecification.csv | 218 +++++++++--------- 1 file changed, 109 insertions(+), 109 deletions(-) diff --git a/inst/settings/resultsDataModelSpecification.csv b/inst/settings/resultsDataModelSpecification.csv index 339ab2a..6a24ba7 100644 --- a/inst/settings/resultsDataModelSpecification.csv +++ b/inst/settings/resultsDataModelSpecification.csv @@ -1,110 +1,110 @@ table_name,column_name,data_type,is_required,primary_key,empty_is_na,min_cell_count,description -time_to_event,database_id,varchar(100),Y,Y,N,N,The database identifier -time_to_event,target_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the target cohort -time_to_event,outcome_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the outcome cohort -time_to_event,outcome_type,varchar(100),Y,Y,N,N,Is the outvome a first occurrence or repeat -time_to_event,target_outcome_type,varchar(40),Y,Y,N,N,When does the outcome occur relative to target -time_to_event,time_to_event,int,Y,Y,N,N,The time (in days) from target index to outcome start -time_to_event,num_events,int,Y,N,N,N,Number of events that occur during the specified time to event -time_to_event,time_scale,varchar(20),Y,Y,N,N,time scale for the number of events -rechallenge_fail_case_series,database_id,varchar(100),Y,Y,N,N,The database identifier -rechallenge_fail_case_series,dechallenge_stop_interval,int,Y,Y,N,N,The time period that É -rechallenge_fail_case_series,dechallenge_evaluation_window,int,Y,Y,N,N,The time period that É -rechallenge_fail_case_series,target_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the target cohort -rechallenge_fail_case_series,outcome_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the outcome cohort -rechallenge_fail_case_series,person_key,int,Y,Y,N,N,The dense rank for the patient (an identifier that is not the same as the database) -rechallenge_fail_case_series,subject_id,bigint,N,N,N,N,The person identifier for the failed case series (optional) -rechallenge_fail_case_series,dechallenge_exposure_number,int,Y,N,N,N,The number of times a dechallenge has occurred -rechallenge_fail_case_series,dechallenge_exposure_start_date_offset,int,Y,N,N,N,The offset for the dechallenge start (number of days after index) -rechallenge_fail_case_series,dechallenge_exposure_end_date_offset,int,Y,N,N,N,The offset for the dechallenge end (number of days after index) -rechallenge_fail_case_series,dechallenge_outcome_number,int,Y,N,N,N,The number of times an outcome has occurred during the dechallenge -rechallenge_fail_case_series,dechallenge_outcome_start_date_offset,int,Y,N,N,N,The offset for the outcome start (number of days after index) -rechallenge_fail_case_series,rechallenge_exposure_number,int,Y,N,N,N,The number of times a rechallenge exposure has occurred -rechallenge_fail_case_series,rechallenge_exposure_start_date_offset,int,Y,N,N,N,The offset for the rechallenge start (number of days after index) -rechallenge_fail_case_series,rechallenge_exposure_end_date_offset,int,Y,N,N,N,The offset for the rechallenge end (number of days after index) -rechallenge_fail_case_series,rechallenge_outcome_number,int,Y,N,N,N,The number of times the outcome has occurred during the rechallenge -rechallenge_fail_case_series,rechallenge_outcome_start_date_offset,int,Y,N,N,N,The offset for the outcome start (number of days after index) -dechallenge_rechallenge,database_id,varchar(100),Y,Y,N,N,The database identifier -dechallenge_rechallenge,dechallenge_stop_interval,int,Y,Y,N,N,The dechallenge stop interval -dechallenge_rechallenge,dechallenge_evaluation_window,int,Y,Y,N,N,The dechallenge evaluation window -dechallenge_rechallenge,target_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the target cohort -dechallenge_rechallenge,outcome_cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id for the outcome cohort -dechallenge_rechallenge,num_exposure_eras,int,Y,N,N,N,The number of exposure eras -dechallenge_rechallenge,num_persons_exposed,int,Y,N,N,N,The number of persons exposed -dechallenge_rechallenge,num_cases,int,Y,N,N,N,The number of cases -dechallenge_rechallenge,dechallenge_attempt,int,Y,N,N,N,The number of dechallenge attempts -dechallenge_rechallenge,dechallenge_fail,int,Y,N,N,N,The dechallenge fail count -dechallenge_rechallenge,dechallenge_success,int,Y,N,N,N,The dechallenge success count -dechallenge_rechallenge,rechallenge_attempt,int,Y,N,N,N,The rechallenge attempt count -dechallenge_rechallenge,rechallenge_fail,int,Y,N,N,N,The rechallenge fail count -dechallenge_rechallenge,rechallenge_success,int,Y,N,N,N,The rechallenge success count -dechallenge_rechallenge,pct_dechallenge_attempt,float,Y,N,N,N,The percentage of dechallenge attempts -dechallenge_rechallenge,pct_dechallenge_success,float,Y,N,N,N,The percentage of dechallenge success -dechallenge_rechallenge,pct_dechallenge_fail,float,Y,N,N,N,The percentage of dechallenge fails -dechallenge_rechallenge,pct_rechallenge_attempt,float,Y,N,N,N,The percentage of rechallenge attempts -dechallenge_rechallenge,pct_rechallenge_success,float,Y,N,N,N,The percentage of rechallenge success -dechallenge_rechallenge,pct_rechallenge_fail,float,Y,N,N,N,The percentage of rechallenge fails -analysis_ref,database_id,varchar(100),Y,Y,N,N,The database identifier -analysis_ref,run_id,int,Y,Y,N,N,The run identifier -analysis_ref,analysis_id,int,Y,Y,N,N,The analysis identifier -analysis_ref,analysis_name,varchar,Y,N,N,N,The analysis name -analysis_ref,domain_id,varchar,Y,N,N,N,The domain id -analysis_ref,start_day,int,Y,N,N,N,The start day -analysis_ref,end_day,int,Y,N,N,N,The end day -analysis_ref,is_binary,varchar(1),Y,N,N,N,Is this a binary analysis -analysis_ref,missing_means_zero,varchar(1),Y,N,N,N,Missing means zero -covariate_ref,database_id,varchar(100),Y,Y,N,N,The database identifier -covariate_ref,run_id,int,Y,Y,N,N,The run identifier -covariate_ref,covariate_id,bigint,Y,Y,N,N,The covariate identifier -covariate_ref,covariate_name,varchar,Y,N,N,N,The covariate name -covariate_ref,analysis_id,int,Y,N,N,N,The analysis identifier -covariate_ref,concept_id,bigint,Y,N,N,N,The concept identifier -covariates,database_id,varchar(100),Y,Y,N,N,The database identifier -covariates,run_id,int,Y,Y,N,N,The run identifier -covariates,cohort_definition_id,int,Y,Y,N,N,The cohort definition id -covariates,covariate_id,bigint,Y,Y,N,N,The covaraite id -covariates,sum_value,int,Y,N,N,N,The sum value -covariates,average_value,float,Y,N,N,N,The average value -covariates_continuous,database_id,varchar(100),Y,Y,N,N,The database identifier -covariates_continuous,run_id,int,Y,Y,N,N,The run identifier -covariates_continuous,cohort_definition_id,bigint,Y,Y,N,N,The cohort definition id -covariates_continuous,covariate_id,bigint,Y,Y,N,N,The covariate identifier -covariates_continuous,count_value,int,Y,N,N,N,The count value -covariates_continuous,min_value,float,Y,N,N,N,The min value -covariates_continuous,max_value,float,Y,N,N,N,The max value -covariates_continuous,average_value,float,Y,N,N,N,The average value -covariates_continuous,standard_deviation,float,Y,N,N,N,The standard devidation -covariates_continuous,median_value,float,Y,N,N,N,The median value -covariates_continuous,p_10_value,float,Y,N,N,N,The 10th percentile -covariates_continuous,p_25_value,float,Y,N,N,N,The 25th percentile -covariates_continuous,p_75_value,float,Y,N,N,N,The 75th percentile -covariates_continuous,p_90_value,float,Y,N,N,N,The 90th percentile -settings,run_id,int,Y,Y,N,N,The run identifier -settings,database_id,varchar(100),Y,Y,N,N,The database identifier -settings,covariate_setting_json,varchar,Y,N,N,N,The covariate settings JSON -settings,during_covariate_setting_json,varchar,Y,N,N,N,The during covariate settings JSON -settings,after_covariate_setting_json,varchar,Y,N,N,N,The after covariate settings JSON -settings,risk_window_start,int,Y,N,N,N,The risk window start -settings,risk_window_end,int,Y,N,N,N,The risk window end -settings,start_anchor,varchar(15),Y,N,N,N,The start anchor -settings,end_anchor,varchar(15),Y,N,N,N,The end anchor -settings,min_prior_observation,int,N,N,N,N,Minimum time observed before index -settings,outcome_washout_days,int,N,N,N,N,Patients with outcome during washout are excluded -settings,min_characterization_mean,float,N,N,N,N,Minimum fraction for feature extraction -cohort_details,run_id,int,Y,Y,N,N,The run identifier -cohort_details,database_id,varchar(100),Y,Y,N,N,The database identifier -cohort_details,cohort_definition_id,int,Y,Y,N,N,The study cohort id -cohort_details,cohort_type,varchar(10),Y,N,N,N,The cohort type -cohort_details,target_cohort_id,int,Y,N,N,N,The target cohort id -cohort_details,outcome_cohort_id,int,Y,N,N,N,The outcome cohort id -cohort_counts,run_id,int,Y,Y,N,N,The run identifier -cohort_counts,database_id,varchar(100),Y,Y,N,N,The database identifier -cohort_counts,cohort_definition_id,int,Y,Y,N,N,The study cohort id -cohort_counts,row_count,int,Y,N,N,N,The number of rows in each cohort -cohort_counts,person_count,int,Y,N,N,N,The number of distinct people in each cohort -cohort_counts,min_exposure_time,bigint,N,N,N,N,Minimum exposure time across cohort -cohort_counts,mean_exposure_time,bigint,N,N,N,N,Mean exposure time across cohort -cohort_counts,max_exposure_time,bigint,N,N,N,N,Max exposure time across cohort -migration,migration_file,varchar(100),N,N,N,N,migration files that have been run -migration,migration_order,int,N,N,N,N,migration files implementation order -package_version,version_number,varchar(10),N,N,N,N,version of characterization package +time_to_event,database_id,varchar(100),Yes,Yes,No,No,The database identifier +time_to_event,target_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the target cohort +time_to_event,outcome_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the outcome cohort +time_to_event,outcome_type,varchar(100),Yes,Yes,No,No,Is the outvome a first occurrence or repeat +time_to_event,target_outcome_type,varchar(40),Yes,Yes,No,No,When does the outcome occur relative to target +time_to_event,time_to_event,int,Yes,Yes,No,No,The time (in days) from target index to outcome start +time_to_event,num_events,int,Yes,No,No,No,Number of events that occur during the specified time to event +time_to_event,time_scale,varchar(20),Yes,Yes,No,No,time scale for the number of events +rechallenge_fail_case_series,database_id,varchar(100),Yes,Yes,No,No,The database identifier +rechallenge_fail_case_series,dechallenge_stop_interval,int,Yes,Yes,No,No,The time period that É +rechallenge_fail_case_series,dechallenge_evaluation_window,int,Yes,Yes,No,No,The time period that É +rechallenge_fail_case_series,target_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the target cohort +rechallenge_fail_case_series,outcome_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the outcome cohort +rechallenge_fail_case_series,person_key,int,Yes,Yes,No,No,The dense rank for the patient (an identifier that is not the same as the database) +rechallenge_fail_case_series,subject_id,bigint,No,No,No,No,The person identifier for the failed case series (optional) +rechallenge_fail_case_series,dechallenge_exposure_number,int,Yes,No,No,No,The number of times a dechallenge has occurred +rechallenge_fail_case_series,dechallenge_exposure_start_date_offset,int,Yes,No,No,No,The offset for the dechallenge start (number of days after index) +rechallenge_fail_case_series,dechallenge_exposure_end_date_offset,int,Yes,No,No,No,The offset for the dechallenge end (number of days after index) +rechallenge_fail_case_series,dechallenge_outcome_number,int,Yes,No,No,No,The number of times an outcome has occurred during the dechallenge +rechallenge_fail_case_series,dechallenge_outcome_start_date_offset,int,Yes,No,No,No,The offset for the outcome start (number of days after index) +rechallenge_fail_case_series,rechallenge_exposure_number,int,Yes,No,No,No,The number of times a rechallenge exposure has occurred +rechallenge_fail_case_series,rechallenge_exposure_start_date_offset,int,Yes,No,No,No,The offset for the rechallenge start (number of days after index) +rechallenge_fail_case_series,rechallenge_exposure_end_date_offset,int,Yes,No,No,No,The offset for the rechallenge end (number of days after index) +rechallenge_fail_case_series,rechallenge_outcome_number,int,Yes,No,No,No,The number of times the outcome has occurred during the rechallenge +rechallenge_fail_case_series,rechallenge_outcome_start_date_offset,int,Yes,No,No,No,The offset for the outcome start (number of days after index) +dechallenge_rechallenge,database_id,varchar(100),Yes,Yes,No,No,The database identifier +dechallenge_rechallenge,dechallenge_stop_interval,int,Yes,Yes,No,No,The dechallenge stop interval +dechallenge_rechallenge,dechallenge_evaluation_window,int,Yes,Yes,No,No,The dechallenge evaluation window +dechallenge_rechallenge,target_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the target cohort +dechallenge_rechallenge,outcome_cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id for the outcome cohort +dechallenge_rechallenge,num_exposure_eras,int,Yes,No,No,No,The number of exposure eras +dechallenge_rechallenge,num_persons_exposed,int,Yes,No,No,No,The number of persons exposed +dechallenge_rechallenge,num_cases,int,Yes,No,No,No,The number of cases +dechallenge_rechallenge,dechallenge_attempt,int,Yes,No,No,No,The number of dechallenge attempts +dechallenge_rechallenge,dechallenge_fail,int,Yes,No,No,No,The dechallenge fail count +dechallenge_rechallenge,dechallenge_success,int,Yes,No,No,No,The dechallenge success count +dechallenge_rechallenge,rechallenge_attempt,int,Yes,No,No,No,The rechallenge attempt count +dechallenge_rechallenge,rechallenge_fail,int,Yes,No,No,No,The rechallenge fail count +dechallenge_rechallenge,rechallenge_success,int,Yes,No,No,No,The rechallenge success count +dechallenge_rechallenge,pct_dechallenge_attempt,float,Yes,No,No,No,The percentage of dechallenge attempts +dechallenge_rechallenge,pct_dechallenge_success,float,Yes,No,No,No,The percentage of dechallenge success +dechallenge_rechallenge,pct_dechallenge_fail,float,Yes,No,No,No,The percentage of dechallenge fails +dechallenge_rechallenge,pct_rechallenge_attempt,float,Yes,No,No,No,The percentage of rechallenge attempts +dechallenge_rechallenge,pct_rechallenge_success,float,Yes,No,No,No,The percentage of rechallenge success +dechallenge_rechallenge,pct_rechallenge_fail,float,Yes,No,No,No,The percentage of rechallenge fails +analysis_ref,database_id,varchar(100),Yes,Yes,No,No,The database identifier +analysis_ref,run_id,int,Yes,Yes,No,No,The run identifier +analysis_ref,analysis_id,int,Yes,Yes,No,No,The analysis identifier +analysis_ref,analysis_name,varchar,Yes,No,No,No,The analysis name +analysis_ref,domain_id,varchar,Yes,No,No,No,The domain id +analysis_ref,start_daYes,int,Yes,No,No,No,The start day +analysis_ref,end_daYes,int,Yes,No,No,No,The end day +analysis_ref,is_binarYes,varchar(1),Yes,No,No,No,Is this a binary analysis +analysis_ref,missing_means_zero,varchar(1),Yes,No,No,No,Missing means zero +covariate_ref,database_id,varchar(100),Yes,Yes,No,No,The database identifier +covariate_ref,run_id,int,Yes,Yes,No,No,The run identifier +covariate_ref,covariate_id,bigint,Yes,Yes,No,No,The covariate identifier +covariate_ref,covariate_name,varchar,Yes,No,No,No,The covariate name +covariate_ref,analysis_id,int,Yes,No,No,No,The analysis identifier +covariate_ref,concept_id,bigint,Yes,No,No,No,The concept identifier +covariates,database_id,varchar(100),Yes,Yes,No,No,The database identifier +covariates,run_id,int,Yes,Yes,No,No,The run identifier +covariates,cohort_definition_id,int,Yes,Yes,No,No,The cohort definition id +covariates,covariate_id,bigint,Yes,Yes,No,No,The covaraite id +covariates,sum_value,int,Yes,No,No,No,The sum value +covariates,average_value,float,Yes,No,No,No,The average value +covariates_continuous,database_id,varchar(100),Yes,Yes,No,No,The database identifier +covariates_continuous,run_id,int,Yes,Yes,No,No,The run identifier +covariates_continuous,cohort_definition_id,bigint,Yes,Yes,No,No,The cohort definition id +covariates_continuous,covariate_id,bigint,Yes,Yes,No,No,The covariate identifier +covariates_continuous,count_value,int,Yes,No,No,No,The count value +covariates_continuous,min_value,float,Yes,No,No,No,The min value +covariates_continuous,max_value,float,Yes,No,No,No,The max value +covariates_continuous,average_value,float,Yes,No,No,No,The average value +covariates_continuous,standard_deviation,float,Yes,No,No,No,The standard devidation +covariates_continuous,median_value,float,Yes,No,No,No,The median value +covariates_continuous,p_10_value,float,Yes,No,No,No,The 10th percentile +covariates_continuous,p_25_value,float,Yes,No,No,No,The 25th percentile +covariates_continuous,p_75_value,float,Yes,No,No,No,The 75th percentile +covariates_continuous,p_90_value,float,Yes,No,No,No,The 90th percentile +settings,run_id,int,Yes,Yes,No,No,The run identifier +settings,database_id,varchar(100),Yes,Yes,No,No,The database identifier +settings,covariate_setting_json,varchar,Yes,No,No,No,The covariate settings JSON +settings,during_covariate_setting_json,varchar,Yes,No,No,No,The during covariate settings JSON +settings,after_covariate_setting_json,varchar,Yes,No,No,No,The after covariate settings JSON +settings,risk_window_start,int,Yes,No,No,No,The risk window start +settings,risk_window_end,int,Yes,No,No,No,The risk window end +settings,start_anchor,varchar(15),Yes,No,No,No,The start anchor +settings,end_anchor,varchar(15),Yes,No,No,No,The end anchor +settings,min_prior_observation,int,No,No,No,No,Minimum time observed before index +settings,outcome_washout_days,int,No,No,No,No,Patients with outcome during washout are excluded +settings,min_characterization_mean,float,No,No,No,No,Minimum fraction for feature extraction +cohort_details,run_id,int,Yes,Yes,No,No,The run identifier +cohort_details,database_id,varchar(100),Yes,Yes,No,No,The database identifier +cohort_details,cohort_definition_id,int,Yes,Yes,No,No,The study cohort id +cohort_details,cohort_type,varchar(10),Yes,No,No,No,The cohort type +cohort_details,target_cohort_id,int,Yes,No,No,No,The target cohort id +cohort_details,outcome_cohort_id,int,Yes,No,No,No,The outcome cohort id +cohort_counts,run_id,int,Yes,Yes,No,No,The run identifier +cohort_counts,database_id,varchar(100),Yes,Yes,No,No,The database identifier +cohort_counts,cohort_definition_id,int,Yes,Yes,No,No,The study cohort id +cohort_counts,row_count,int,Yes,No,No,No,The number of rows in each cohort +cohort_counts,person_count,int,Yes,No,No,No,The number of distinct people in each cohort +cohort_counts,min_exposure_time,bigint,No,No,No,No,Minimum exposure time across cohort +cohort_counts,mean_exposure_time,bigint,No,No,No,No,Mean exposure time across cohort +cohort_counts,max_exposure_time,bigint,No,No,No,No,Max exposure time across cohort +migration,migration_file,varchar(100),No,Yes,No,No,migration files that have been run +migration,migration_order,int,No,No,No,No,migration files implementation order +package_version,version_number,varchar(10),No,Yes,No,No,version of characterization package