Extract the patient, referring and referred provider, specialty, reason for referral, urgency, medications, and diagnoses from a medical referral letter PDF.
The full guide: Reason for referral and urgency from a referral letter
Need to scale? Create an API key, then run this from your own code or an agent.
Create an API keyFree account required
Upload a file or pick a sample, and see the fields come back.
No signup · nothing stored
The document number and date, the patient name, identifier (MRN), birth date, gender, address, and contact, the referring provider name and contact, the referred provider (specialist) name and specialty, the report category (clinical discipline), the reason for referral, the referral status, and the urgency level (routine, urgent, or emergency).
Yes. The clinical summary of the patient history and current presentation, the known allergies, and the conclusion (impression) come back as their own fields, and whether an appointment has been requested (with the preferred date) is read too. The tool reports these values as written and does not interpret them.
The medications table returns each drug with its name, dose, frequency, and status, and the diagnoses table returns each ICD-10 code with its description and status, so the referral context comes back structured rather than as prose.
Yes. The test results table returns each observation code (typically LOINC) with its value, unit, interpretation flag, low and high reference bounds, and observation date. The field set follows HL7 FHIR R4 DiagnosticReport and Observation resources with LOINC codes.
The letter is processed via the Talonic API for extraction only, is not retained for training, and is not shared. Handle identified PHI with care and redact where you can; for workflows that require a BAA, ask about the Talonic platform rather than the free tool. Uploads are PDF only, up to 10MB and 100 pages.
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.