Dental Claim (ADA) Extractor

Extract the patient, provider NPI, payer, CDT service lines with tooth numbers and surfaces, and billed, allowed and paid amounts from an ADA dental claim PDF.

The full guide: CDT codes, tooth numbers, and surfaces on a dental claim

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 Dental Claim (ADA) Extractor.

What does the dental claim extractor read?

The claim number and date, the claim type and claim status, the patient name, member ID, and date of birth, the dental provider name, NPI, and taxonomy (specialty) code, the payer name and payer ID, the plan name, and the service date range.

Are the service lines returned as a table?

Yes. The service lines table returns each line with its CDT (Current Dental Terminology) procedure code, description, tooth number (FDI notation), tooth surface, oral cavity designation, quantity, unit price, line total, allowed and paid amounts, patient responsibility, and status.

Which money and adjudication fields come out?

The billed, allowed, and paid amounts, the total amount, patient responsibility, deductible applied, coinsurance percentage, the diagnosis codes (ICD-10), the service authorization number, and the adjudication outcome, plus a patient benefits table with coverage percentage, annual maximum, used, and remaining per benefit category.

How is a dental claim different from a CMS-1500 or UB-04 claim?

A dental (ADA) claim uses CDT procedure codes with tooth-number and tooth-surface designations. A professional (CMS-1500) claim uses CPT/HCPCS codes, and an institutional (UB-04) claim uses revenue codes. For those, use the professional claim or institutional claim extractor.

Is it safe to upload a claim that contains patient data?

The claim is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Redact the member ID and date of birth where you can; for BAA-covered workflows, ask about the Talonic platform. 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.