Extract prior authorization forms to structured JSON

Prior authorization forms request payer approval for procedures, medications, or equipment before services are rendered. Every payer uses a different form layout. Sensible converts PA data into structured JSON for utilization management, workflow automation, and denial tracking.

Quick links:

Healthcare template library

API documentation

How two healthcare orgs automated document processing

Schedule a demo

Why prior authorization forms break standard extraction

Payer-specific layouts, mixed clinical fields, and handwritten justifications make PA forms variable.

Payer-Specific Layouts

UnitedHealthcare, Aetna, Cigna: each designs PA forms with different field arrangements, required sections, and response formats. The extraction adapts to each payer's form while outputting a standard authorization schema.

Clinical Justification Parsing

Free-text clinical justification sections describe medical necessity in narrative form. LLM parsing extracts the key clinical details (diagnosis, failed treatments, clinical rationale) from unstructured text that rule-based parsers cannot handle.

Medication and Procedure Detail

Drug names, NDC codes, dosages, CPT codes, quantities: each requires precise extraction. Validation rules check format compliance on every field, because a wrong NDC code means a rejected authorization.

Fields we extract

Clinical and administrative fields cover utilization management. Customize for your PA tracking workflow.

Patient and provider

Patient name, DOB, member ID, group number, requesting provider name, NPI, facility name, payer name, plan type

Clinical detail

Primary diagnosis (ICD-10), secondary diagnoses, requested procedure (CPT), requested medication (NDC/drug name/dosage), clinical justification

Authorization tracking

PA request number, submission date, urgency (standard/expedited), requested service dates, units requested, estimated cost


{ /* SenseML: prior authorization form extraction */
  "fields": [
    {
      "method": {
        "id": "queryGroup",
        "queries": [
          {
            // Patient name
            "id": "patient_name",
            "description": "patient name, member name, subscriber"
          },
          {
            // Authorization number
            "id": "auth_number",
            "description": "authorization number, PA number, auth #, reference number"
          },
          {
            // Requested procedure or medication
            "id": "requested_service",
            "description": "requested procedure, requested medication, drug name, CPT code"
          },
          {
            // Authorization status
            "id": "auth_status",
            "description": "authorization decision, status, approved, denied, pending"
          }
          // Additional fields for diagnosis, provider NPI, effective dates, etc.
        ]
      }
    }
  ]
}
DME Prior Auth

Durable medical equipment authorization form for wheelchairs, CPAP, and similar devices.

Procedure Prior Auth

Pre-authorization request for surgical or diagnostic procedures.

Medication Prior Auth

Insurer form requesting authorization for non-formulary or specialty medications.

Supported PA form types

Sensible processes PA forms from any commercial payer, Medicare, Medicaid, and PBMs. The hybrid approach handles both the structured fields and the free-text clinical sections.

Commercial payers

UnitedHealthcare, Anthem, Aetna, Cigna, Humana, BCBS affiliates, regional health plans

Government and PBMs

Medicare (MAC-specific), Medicaid (state-specific), Part D, CVS Caremark, Express Scripts, OptumRx

Trusted by operations and engineering teams at

Common Questions

Answers about payer form support, clinical justification parsing, and PA tracking.

What provider information does Sensible extract from prior auth forms?

Sensible captures requesting provider name, NPI, practice name, phone, fax, and servicing facility details. Patient information including member ID and group number is also extracted.

Does Sensible capture insurer requirements from prior auth forms?

Yes. Sensible extracts the payer name, plan type, authorization number, required documentation checklist, peer-to-peer review requirements, and appeal deadlines.

What medication or procedure details does Sensible extract?

Sensible extracts the requested medication name, dosage, frequency, quantity, NDC code, or the requested procedure with CPT code, diagnosis codes, and clinical rationale.

Can Sensible extract approval status from prior auth forms?

Yes. Sensible captures the authorization decision (approved, denied, pending), effective dates, authorized units or duration, and any conditions or restrictions.

Do you support webhooks?

Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.

Does Sensible support human review?

Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.

What security certifications does Sensible have?

Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.

How long is document data retained?

Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.

Is there a free trial?

Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.

How is pricing structured?

Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.

How do I integrate with Sensible?

Sensible provides REST APIs and SDKs for Python and Node.js. Most integrations take a few hours. Webhooks, Zapier, and direct API calls are all supported.

What file formats does Sensible support?

Sensible processes PDFs (native or scanned), Microsoft Word (DOC, DOCX), spreadsheets (XLSX, XLS, CSV), single-page images (JPEG, PNG), multi-page images (TIFF), and email bodies with attachments.

How accurate is the extraction?

Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.

How fast is document processing?

Processing speed depends on document size, page count, OCR requirements, and which extraction methods are used. Simple single-page documents process in seconds. Larger or more complex documents that use LLM-based extraction take longer.

Resources

Documentation Links

Docs: Insurance template quick startDocs: Validation and human reviewDocs: API and delivery options

Related insurance documents

Docs: Insurance template quick startDocs: Validation and human reviewDocs: API and delivery options