Institutional Claim (UB-04) Extractor

Read the facility NPI, patient, payer, revenue-code line items, diagnoses, and billed, allowed and paid amounts from a UB-04 institutional claim PDF.

The full guide: Revenue codes and charges on a UB-04 claim form

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Institutional Claim (UB-04) Extractor.

Which header fields does the UB-04 extractor read?

The claim number and date, claim status, the billing facility name, NPI and tax ID, patient name, identifier and date of birth, the payer name and identifier, the service date range, admission type, and discharge status.

Are the revenue-code line items returned as a table?

Yes. The line items table returns one row per charge with the line number, four-digit revenue code, description, quantity, unit charge, total charge, allowed amount, and paid amount, so the itemized bill reconciles against the claim totals.

How are diagnoses and procedures handled?

ICD-10-CM diagnosis codes and CPT, HCPCS, or ICD-10-PCS procedure codes are captured at the claim level, and separate diagnoses and procedures tables return each code with its sequence, description, type, and procedure date.

What claim-level amounts are extracted?

Total billed amount, allowed amount, paid amount, patient responsibility, and the currency, along with the adjudication outcome for the claim.

Is uploading a claim with patient data a problem?

The claim is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Redact PHI where you can; for BAA-covered workflows, ask about the Talonic platform. Uploads are PDF only, up to 10MB and 100 pages.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See document data extraction if you run this for clinical and billing teams, or the extraction API if you are building it in.