Synthetic healthcare/Synthetic

Insurance claims

Claim lines for testing claims systems and models. Each row carries an ICD-10 diagnosis code and a CPT procedure code, plus billed and paid amounts. Patients and payers are synthetic.

Volume: 2,000,000claims
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.

claim_idstring
Identifier for one claim line.
patient_idstring
Synthetic patient identifier. Not a real person.
service_datedate
Date of service.
icd10_codestring
ICD-10 diagnosis code.
cpt_codestring
CPT procedure code.
billed_amountdecimal
Amount billed.
paid_amountdecimal
Amount paid.
statusstring
Claim status, such as paid, denied, or pending.

Columns in Insurance claims
Column	Type	Description
claim_id	string	Identifier for one claim line.
patient_id	string	Synthetic patient identifier. Not a real person.
service_date	date	Date of service.
icd10_code	string	ICD-10 diagnosis code.
cpt_code	string	CPT procedure code.
billed_amount	decimal	Amount billed.
paid_amount	decimal	Amount paid.
status	string	Claim status, such as paid, denied, or pending.

Use

Test claims ingestion and coding logic
Train models on ICD-10 and CPT pairs

Generation

Synthetic claims. Diagnosis fields use ICD-10 codes and procedure fields use CPT codes. 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.

Request a different schema