Skip to content

Main Lessons Data Dictionary

Josh Matlock edited this page Nov 17, 2023 · 26 revisions

Note this is adapted from the original Synthea data dictionary: https://github.com/synthetichealth/synthea/wiki/CSV-File-Data-Dictionary#imaging-studies My version is different in that it replaces SNOMED codes with non-proprietary, synthetic codes to avoid licensing issues with SNOMED International.

File Description
allergies.csv Patient allergy data.
careplans.csv Patient care plan data, including goals.
conditions.csv Patient conditions or diagnoses.
devices.csv Patient-affixed permanent and semi-permanent devices.
encounters.csv Patient encounter data.
immunizations.csv Patient immunization data.
medications.csv Patient medication data.
observations.csv Patient observations including vital signs and lab reports.
organizations.csv Provider organizations including hospitals.
patients.csv Patient demographic data.
payer_transitions.csv Payer Transition data (i.e. changes in health insurance).
payers.csv Payer organization data.
procedures.csv Patient procedure data including surgeries.
providers.csv Clinicians that provide patient care.
supplies.csv Supplies used in the provision of care.

Data Dictionary information for each CSV table follows below.

Allergies

Column Name Data Type Required? Description
Start Date (YYYY-MM-DD) true The date the allergy was diagnosed.
Stop Date (YYYY-MM-DD) false The date the allergy ended, if applicable.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter when the allergy was diagnosed.
Code String true Allergy code
Description String true Description of the Allergy
Type String false Identify entry as an allergy or intolerance.
Category String false Identify the category as drug, medication, food, or environment.
Reaction1 String false Optional ICD9 code of the patients reaction.
Severity1 String false Severity of the reaction: MILD, MODERATE, or SEVERE.
Reaction2 String false Optional ICD9 code of the patients second reaction.
Severity2 String false Severity of the second reaction: MILD, MODERATE, or SEVERE.

CarePlans

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary Key. Unique Identifier of the care plan.
Start Date (YYYY-MM-DD) true The date the care plan was initiated.
Stop Date (YYYY-MM-DD) false The date the care plan ended, if applicable.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter when the care plan was initiated.
Code String true Care plan code
Description String true Description of the care plan.

Conditions

Column Name Data Type Required? Description
Start Date (YYYY-MM-DD) true The date the condition was diagnosed.
Stop Date (YYYY-MM-DD) false The date the condition resolved, if applicable.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter when the condition was diagnosed.
Code String true Diagnosis code from ICD9
Description String true Description of the condition.

Devices

Column Name Data Type Required? Description
Start iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date and time the device was associated to the patient.
Stop iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') false The date and time the device was removed, if applicable.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter when the device was associated.
Code String true Device code
Description String true Description of the device.

Encounters

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary Key. Unique Identifier of the encounter.
Start iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date and time the encounter started.
Stop iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') false The date and time the encounter concluded.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Organization String true Foreign key to the Organization.
πŸ—οΈ Provider String true Foreign key to the Provider.
πŸ—οΈ Payer String true Foreign key to the Payer.
EncounterClass String true The class of the encounter, such as ambulatory, emergency, inpatient, wellness, or urgentcare
Code String true Encounter code
Description String true Description of the type of encounter.
Base_Encounter_Cost Float true The base cost of the encounter, not including any line item costs related to medications, immunizations, procedures, or other services.
Total_Claim_Cost Float true The total cost of the encounter, including all line items.
Payer_Coverage Float true The amount of cost covered by the Payer.
ReasonCode String false Diagnosis code from ICD9 that the encounter addressed.

Immunizations

Column Name Data Type Required? Description
Date iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date the immunization was administered.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter where the immunization was administered.
Code Integer true Immunization code
Description String true Description of the immunization.

Medications

Column Name Data Type Required? Description
Start iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date and time the medication was started.
Stop iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') false The date and time the prescription stopped, if applicable.
πŸ—οΈ Patient UUID true Foreign key to the Patient.
πŸ—οΈ Payer UUID true Foreign key to the Payer.
πŸ—οΈ Encounter UUID true Foreign key to the Encounter where the medication was prescribed.
Code String true Medication code from RxNorm.
Description String true Description of the medication.
Base_Cost Float true The line item cost of the medication.
Payer_Coverage Float true The amount covered or reimbursed by the Payer.
Dispenses Float true The number of times the prescription was filled.
TotalCost Float true The total cost of the prescription, including all dispenses.

Observations

Column Name Data Type Required? Description
Date iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date and time the observation was performed.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter where the observation was performed.
Category String false Observation category.
Code String true Observation or Lab code from LOINC
Description String true Description of the observation or lab.
Value String true The recorded value of the observation.
Units String false The units of measure for the value.
Type String true The datatype of Value: text or numeric

Organizations

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary key of the Organization.
Name String true Name of the Organization.
Address String true Organization's street address without commas or newlines.
City String true Street address city.
State String false Street address state abbreviation.
Zip Integer false Street address zip or postal code.
Lat Float false Latitude of Organization's address.
Lon Float false Longitude of Organization's address.
Phone String false Organization's phone number.
Revenue Float true The monetary revenue of the organization during the entire simulation.
Utilization Integer true The number of Encounters performed by this Organization.

Patients

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary Key. Unique Identifier of the patient.
BirthDate Date (YYYY-MM-DD) true The date the patient was born.
DeathDate Date (YYYY-MM-DD) false The date the patient died.
SSN String true Patient Social Security identifier.
Drivers String false Patient Drivers License identifier.
Passport String false Patient Passport identifier.
Prefix String false Name prefix, such as Mr., Mrs., Dr., etc.
First String true First name of the patient.
Last String true Last or surname of the patient.
Suffix String false Name suffix, such as PhD, MD, JD, etc.
Maiden String false Maiden name of the patient.
Marital String false Marital Status. M is married, S is single. Currently no support for divorce (D) or widowing (W)
Race String true Description of the patient's primary race.
Ethnicity String true Description of the patient's primary ethnicity.
Gender String true Gender. M is male, F is female.
BirthPlace String true Name of the town where the patient was born.
Address String true Patient's street address without commas or newlines.
City String true Patient's address city.
State String true Patient's address state.
County String false Patient's address county.
FIPS Integer false Patient's Census FIPS code.
Zip Integer false Patient's zip code.
Lat Float false Latitude of Patient's address.
Lon Float false Longitude of Patient's address.
Healthcare_Expenses Float true The total lifetime cost of healthcare to the patient (i.e. what the patient paid).
Healthcare_Coverage Float true The total lifetime cost of healthcare services that were covered by Payers (i.e. what the insurance company paid).
MRN Integer true Patient's Medical Record Number

Payer Transitions

Column Name Data Type Required? Description
πŸ—οΈ Patient String true Foreign key to the Patient.
Member ID String false Member ID for the Insurance Plan.
Start_Date Date and Time (yyyy-MM-dd'T'HH:mm'Z') true The year the coverage started (inclusive).
End_Date Date and Time (yyyy-MM-dd'T'HH:mm'Z') true The year the coverage ended (inclusive).
πŸ—οΈ Payer String true Foreign key to the Payer.
πŸ—οΈ Secondary Payer String false Foreign key to the Secondary Payer.
Plan Ownership String false The owner of the insurance policy. Legal values: Guardian, Self, Spouse.
Owner Name String false The name of the insurance policy owner.

Payers

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary key of the Payer (e.g. Insurance).
Name String true Name of the Payer.
Ownership String true Type of Payer [Government, Private, Other]
Address String false Payer's street address without commas or newlines.
City String false Street address city.
State_Headquartered String false Street address state abbreviation.
Zip String false Street address zip or postal code.
Phone String false Payer's phone number.
Amount_Covered Float true The monetary amount paid to Organizations during the entire simulation.
Amount_Uncovered Float true The monetary amount not paid to Organizations during the entire simulation, and covered out of pocket by patients.
Revenue Float true The monetary revenue of the Payer during the entire simulation.
Covered_Encounters Integer true The number of Encounters paid for by this Payer.
Uncovered_Encounters Integer true The number of Encounters not paid for by this Payer, and paid out of pocket by patients.
Covered_Medications Integer true The number of Medications paid for by this Payer.
Uncovered_Medications Integer true The number of Medications not paid for by this Payer, and paid out of pocket by patients.
Covered_Procedures Integer true The number of Procedures paid for by this Payer.
Uncovered_Procedures Integer true The number of Procedures not paid for by this Payer, and paid out of pocket by patients.
Covered_Immunizations Integer true The number of Immunizations paid for by this Payer.
Uncovered_Immunizations Integer true The number of Immunizations not paid for by this Payer, and paid out of pocket by patients.
Unique_Customers Integer true The number of unique patients enrolled with this Payer during the entire simulation.
QOLS_Avg Float true The average Quality of Life Scores (QOLS) for all patients enrolled with this Payer during the entire simulation.
Member_Months Integer true The total number of months that patients were enrolled with this Payer during the simulation and paid monthly premiums (if any).

Procedures

Column Name Data Type Required? Description
Start iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') true The date and time the procedure was performed.
Stop iso8601 UTC Date (yyyy-MM-dd'T'HH:mm'Z') false The date and time the procedure was completed, if applicable.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter where the procedure was performed.
Code String true Procedure code from ICD-9
Description String true Description of the procedure.
Base_Cost Float true The line item cost of the procedure.

Providers

Column Name Data Type Required? Description
πŸ”‘ Id String true Primary key of the Provider/Clinician.
πŸ—οΈ Organization UUID true Foreign key to the Organization that employees this provider.
Name String true First and last name of the Provider.
Gender String true Gender. M is male, F is female.
Speciality String true Provider speciality.
Address String true Provider's street address without commas or newlines.
City String true Street address city.
State String false Street address state abbreviation.
Zip Integer false Street address zip or postal code.
Lat Float false Latitude of Provider's address.
Lon Float false Longitude of Provider's address.
Encounters Integer true The number of encounters performed by this provider.
Procedures Integer true The number of procedures performed by this provider.

Supplies

Column Name Data Type Required? Description
Date Date (YYYY-MM-DD) true The date the supplies were used.
πŸ—οΈ Patient String true Foreign key to the Patient.
πŸ—οΈ Encounter String true Foreign key to the Encounter when the supplies were used.
Quantity Integer true Quantity of supply used.
Description String true Description of supply used.
Code String true Code for the type of supply used,