Discharge Summary Extractor

Turn a hospital discharge summary into data: admission and discharge dates, diagnoses, procedures, discharge medications, labs, and follow-up appointments.

The full guide: Discharge dates, ICD-10, and medication reconciliation

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 Discharge Summary Extractor.

Which discharge summary fields does the extractor read?

The document number and date, patient name, identifier (MRN), birth date and gender, the admission and discharge dates, the length of stay, the primary diagnosis, the report category (clinical service), the managing organization (facility), and the performer and requester.

Are diagnoses and procedures returned as tables?

Yes. The diagnoses table returns each ICD-10 code with its description, diagnosis type (primary, secondary, comorbidity), and onset date, and the procedures table returns each CPT or ICD procedure code with its description, date, and the provider who performed it.

Does it capture discharge medications and follow-ups?

The medications table returns each discharge drug with its name, RxNorm code, dose, frequency, route, status, and refills, and the follow-up appointments table returns each specialist type, recommended provider, timeframe, and urgency, alongside the free-text discharge instructions.

Are labs, vital signs, and imaging included?

Yes, each as its own table. Lab results return the LOINC test code, analyte, result value, unit, reference range, and interpretation flag; vital signs return the type, value, unit, and date; and imaging studies return the study type, body part, findings, and impression. The field set follows HL7 FHIR R4 resources with LOINC codes, and the tool reports these values as written without interpreting them.

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

The summary is processed via the Talonic API to extract the fields, 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.

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.