Healthcare/Synthetic
Healthcare records
One healthcare bundle. Patients have age and sex. Encounters are outpatient, telehealth, emergency, or inpatient, with a length of stay on inpatient visits. Diagnoses use ICD-10-CM codes from the generator's catalog. Procedures use CPT codes chosen from the primary diagnosis. Each encounter has one modeled claim, with billed, allowed, and paid amounts and a status of paid, pending, denied, or patient balance. Facilities, providers, and payer types are synthetic. The published example is 80 patients and 200 encounters. The volume is part of the request. No real medical record is used.
- Volume
- 200example encounters
- Formats
- CSV · Parquet · JSONL
- Label
- Synthetic
Purchase
Sold on Datarade. This site does not take payment.
Placeholder — listing URL not set
Schema
Column preview for the launch specification. Names and types describe the file. They are not a sample of rows.
- patient_idstring
Synthetic patient identifier. Not a real person.
- encounter_idstring
One visit, admission, or telehealth contact.
- encounter_typestring
outpatient, telehealth, emergency, or inpatient.
- encounter_datedate
Service date.
- primary_icd10string
Primary ICD-10-CM diagnosis code.
- cptstring
CPT procedure code from the curated catalog.
- claim_statusstring
paid, pending, denied, or patient_balance.
- billed_amount_usddecimal
Modeled charge on the claim, in dollars.
Use
- Test software that reads coded clinical records and claims
- Develop models on synthetic ICD-10-CM and CPT fields
Generation
Synthetic patients, encounters, diagnoses, procedures, and claims. No real patients.
- Every dataset is 100% synthetic. It is not copied from real customers, cardholders, or patients.
- Each product is labeled as synthetic in the title, the description, and the file metadata.
- Delivery includes a generation note: the methods and algorithms used, the schema, and known limitations.