Health information management (HIM) teams process release of information requests, chart packets, and patient record requests across faxed forms, electronic health record (EHR) printouts, and scanned documents. Nutrient Data Extraction API extracts patient identifiers, requestor details, record categories, and authorization fields — with confidence scores so staff can review exceptions, not every field.
Trusted by enterprises and teams building healthcare document workflows at scale
WALKTHROUGH
USE CASES
Extract patient identifiers, requestor details, record categories, authorization dates, delivery instructions, and expiration information from release of information (ROI) forms.
Structure medical record number (MRN), date range, record type, requestor, and delivery format from chart requests to route fulfillment without manual reentry.
Extract attorney, insurer, or payer details; authorization scope; and purpose of use from legal and third-party record requests.
Handle handwritten forms, low-quality faxes, and image-based records with intelligent character recognition and confidence scoring.
Organize multidocument chart packets containing clinical notes, lab results, discharge summaries, and supporting records into per-document structured output.
GOVERNED EXTRACTION
LLMs can reason over a patient record — but HIM and ROI workflows need deterministic, traceable output grounded in the source document, not generated answers that vary between runs.
Typed output remains tied to the source document — not generated text that changes from one run to the next.
Flag uncertain values before they move downstream into ROI platforms or fulfillment queues.
Every extracted value is anchored to its source location for traceability and staff review.
Tables, forms, checkboxes, and key-value regions preserved — not flattened into plain text.
Support validation steps before structured data enters ROI, HIM, or compliance systems.
Source context and page detail support audit trails in regulated healthcare environments.
WHAT YOU CAN EXTRACT
Name, date of birth, MRN, member ID, and contact details from ROI forms, chart requests, and authorization documents.
Requestor name, organization, purpose of use, authorization date, and expiration from ROI and legal record requests.
Record type, date range, specific record categories, and delivery format instructions from chart and ROI requests.
Authorization dates, submission dates, date ranges, and reference or tracking numbers from HIM documents.
Attorney details, insurer or payer information, case numbers, and subpoena references from legal record requests.
Checkbox states, handwritten values, and signature presence from faxed or scanned HIM forms.
HOW IT WORKS
Parse
Turn ROI forms, patient records, and scanned chart packets into document structure.
Extract
Identify patient identifiers, requestor details, record categories, authorization fields, and delivery instructions.
Map
Define the fields the workflow needs using the schema generator in Studio, or write a JSON Schema directly. Get back validated, typed output.
Structure
Return typed JSON for HIM systems and fulfillment queues, or Markdown for search and AI workflows.
Process
Send structured data into ROI platforms, HIM systems, EHR integrations, or compliance workflows.
OUTPUT FORMATS
Confidence scores, coordinates, and page context included.
Choose output: "json" or Markdown per request.
Spatial JSON
For extraction · validation · review
{ "type": "keyValueRegion", "id": "kv_r1o2i3", "bounds": { "x": 82, "y": 128, "width": 340, "height": 96 }, "confidence": 0.97, "page": { "pageIndex": 0, "pageNumber": 1 }, "pairs": [ { "key": { "entityType": "QUESTION", "value": "Patient name", "bounds": { "x": 82, "y": 128, "width": 110, "height": 24 }, "confidence": 0.99 }, "value": { "entityType": "ANSWER", "value": "Sarah K. Lindström", "bounds": { "x": 200, "y": 128, "width": 150, "height": 24 }, "confidence": 0.99 }, "relationshipConfidence": 0.97 }, { "key": { "entityType": "QUESTION", "value": "Requestor type", "bounds": { "x": 82, "y": 164, "width": 120, "height": 24 }, "confidence": 0.98 }, "value": { "entityType": "ANSWER", "value": "Patient", "bounds": { "x": 210, "y": 164, "width": 80, "height": 24 }, "confidence": 0.98 }, "relationshipConfidence": 0.96 }, { "key": { "entityType": "QUESTION", "value": "Record category", "bounds": { "x": 82, "y": 200, "width": 120, "height": 24 }, "confidence": 0.97 }, "value": { "entityType": "ANSWER", "value": "Discharge summary", "bounds": { "x": 210, "y": 200, "width": 140, "height": 24 }, "confidence": 0.97 }, "relationshipConfidence": 0.95 } ]}Markdown
For RAG · search · knowledge bases
# Release of Information Request
**Patient** Sarah K. Lindström**Date of birth** 1985-03-09**MRN** 00847321
## Request Details
| Field | Value || --- | --- || Requestor | Patient || Purpose | Continuity of care || Record category | Discharge summary |
**Date range** 2023-01-01 to 2024-06-30**Authorization date** 2024-07-10Regional processing options
Choose supported processing regions for enterprise deployments.
SOC 2 Type 2 audited
Backed by Nutrient’s SOC 2 Type 2 security practices, built for use in compliance-sensitive workflows.
Trust and compliance
TLS encryption by default
All API communication is TLS-encrypted. Documents in transit are protected end to end.
HIPAA-compatible architecture
Encrypted transport and access controls designed to support HIPAA-sensitive workflows.
Yes. For hand-completed fields, checkboxes, and handwritten values, the API applies intelligent character recognition to capture what standard OCR misses. Every extracted value includes a confidence score so uncertain fields can be flagged for staff review before moving downstream.
Data Extraction API processes PDFs; images (including scans and photos); and Word, Excel, and PowerPoint files. It handles scanned records, faxed forms, and mixed digital/image-based documents without requiring a separate OCR pipeline.
Nutrient Data Extraction API is an extraction layer, not a HIM system or ROI platform. It extracts structured data from healthcare documents so that data can be reviewed, validated, and routed into the systems organizations already use.
Every extracted element includes confidence scores, page references, and coordinates so teams can flag low-confidence fields for review, trace values back to the source document, and validate results before they enter ROI platforms or fulfillment queues.
Use the schema generator in Studio — upload example ROI forms, chart requests, or legal record requests and describe the document type. It generates a JSON Schema for the /extract endpoint. Fields like patient identifiers, requestor details, record categories, and authorization information can also be defined manually. Refer to the documentation for supported field types and limits.
Use agentic mode for degraded scans, faxed records, handwritten HIM forms, and documents with complex visual layouts where understand mode produces insufficient results. Agentic mode adds a vision language model (VLM) on top of the understand pipeline. It costs 18 credits per page.