Medical record extraction
Records in. Data out.
Upload visit notes, prescriptions, lab reports or discharge letters as PDFs or scans, forward them by e-mail or send them to the API. Parsevix returns patient and provider details, diagnoses, medications, lab results and vitals as structured data.
- Diagnoses, medications and lab results as lists
- Patient, provider and visit as fields
- Patient names and numbers masked before the AI step
No credit card · 20 free pages every month
What you get back
A medical record, already defined.
The built-in Medical Record category returns 36 fields: the patient, the provider and the visit, lists of diagnoses, medications and lab results, the vitals, the notes and the follow-up date. Use it as it is, or change it in your project.
Dates come back as ISO dates; doses, results and measurements as printed, with their units. A field the record doesn't contain, such as a prescriber, is left out, not guessed.
Record
- record_typestring
- notesstring
- follow_up_datedate
Patient
patient_infoobject
- full_namestring
- date_of_birthdate
- genderstring
- patient_idstring
- addressstring
- phonestring
- insurance_numberstring
Provider
provider_infoobject
- provider_namestring
- facility_namestring
- provider_addressstring
- provider_phonestring
- license_numberstring
Visit
visit_infoobject
- visit_datedate
- visit_typestring
- chief_complaintstring
Diagnoses
diagnosesarray
- diagnosis_codestring
- diagnosis_descriptionstring
Medications
medicationsarray
- medication_namestring
- dosagestring
- frequencystring
- durationstring
- routestring
- prescriberstring
Lab results
lab_resultsarray
- test_namestring
- result_valuestring
- unitstring
- reference_rangestring
- test_datedate
Vitals
vitalsobject
- blood_pressurestring
- heart_ratestring
- temperaturestring
- weightstring
- heightstring
Your own fields
A name, a type and one sentence on what it is.
- allergies
- procedure_codes
- referral_to
- sick_note_until
Made for health records
The clinical content in fields, the patient behind placeholders.
Records arrive as scans, faxes and PDFs from many practices, each with its own layout. This is what Parsevix does with them.
What the AI model sees
Before any text goes to the AI model, names, dates of birth, patient and insurance numbers and addresses are replaced with placeholders, and put back in your result afterwards. The complaint, diagnoses, medications and results are sent as written, because they are what the extraction reads.
Detection catches most personal data, not necessarily every item. The clinical content is health data, and it reaches the AI model.
- 02
Diagnoses with their codes
Each diagnosis comes back with its code, such as an ICD-10 code, and its description, as the record prints them. Parsevix doesn't assign codes the record doesn't contain.
- 03
One row per medication
Each medication comes back with its dose, frequency, duration, route and prescriber, as far as the record states them.
- 04
Lab results with units and ranges
Each test comes back with its result, unit, reference range and date. Parsevix doesn't flag values outside the range; your system can compare them.
- 05
Notes, prescriptions, lab reports
The record type is a field, so visit notes, prescriptions, lab reports and discharge letters can share one category. Add fields such as allergies for the records you handle.
- 06
Records in any language
The language is detected on every page. A record in another language fills the same fields, with ISO dates.
- 07
Every value linked to its spot
Each value is linked to the spot in the record it came from. Click it in the dashboard to see where it was printed.
How records get in
Upload them, forward them or send them from your system.
Dashboard
Upload records as PDFs or scans. Check each result next to its page, with every value marked where it was printed, and approve it.
E-mail address
Paid plansEvery project gets its own address. Forward records to it, and each attachment becomes a document.
API
Send records from your practice or claims system and get the JSON in the same response, or receive results by signed webhook or through Zapier.
Request
curl https://parsevix.com/api/v1/extract \ -H "X-API-Key: $PARSEVIX_API_KEY" \ -F file=@visit-note.pdf \ -F category="Medical Record"
The request stays open until the document is read and answers with the JSON.
- POST /documentsUpload without waiting; the result arrives by webhook or callback.
- POST /extract-autoNo category: every field Parsevix finds, named as in the document.
- POST /classifyOnly the document's category, for 1 credit.
Response · trimmed
Security & compliance
- PII maskedautomatically, before the AI step
- Encryptedin transit and at rest
- No AI trainingon your documents
- API files deletedafter processing
Priced per page, not per feature.
Every plan reads, sorts and masks documents the same way. Picking the category is included, and a document that fails costs nothing.
See pricing- credit per page
- 1
- free pages every month
- 20
- a month for 500 pages
- $39
Medical record FAQ
Medical records,
answered.
What teams ask before they send their first records.
PDF, Word (DOCX), PNG, JPG and TIFF, up to 10 MB and 30 pages each. Scans and faxes work too; every page is read as an image.
Health data is a special category of personal data under the GDPR, and you need a legal basis for processing it with a service like Parsevix. Names and numbers are masked where detection finds them, but diagnoses, medications and results reach the AI model (Google's Gemini API, possibly in the USA). Parsevix offers no HIPAA business associate agreement, so it is not suited to US protected health information.
No. It extracts what a record says into fields, for administration and data entry. It doesn't interpret findings, check doses or support clinical decisions, and nothing it returns is medical advice.
Printed and typed records work best. Handwriting is read where it is clear; what can't be read is left out, not guessed.
One credit per page: a three-page discharge letter uses three. Choosing the category is included, and if a document fails, its credits are given back.
Records uploaded in the dashboard or sent by e-mail stay in your project until you delete them. Files sent through the API are deleted after processing unless you turn on keeping them for the project. Your records are never used to train AI.
Related use cases
Documents that travel with this one.
Damage report extraction
Claim, vehicle, damaged parts, repair costs and values from appraisals.
ID document OCR
Name, number, dates and both MRZ lines from passports and ID cards.
Report data extraction
Summary, findings, recommendations and sections from long reports.