Trusted by teams turning documents into production data
Healthcare
Referrals arrive as faxed forms, EHR-generated PDFs, and free-text letters. Specialty, diagnosis, prior auth requirements, and clinical context need to be parsed into your intake or routing system without manual data entry. Sensible converts any referral format into structured JSON for specialty intake and network management.
Validated JSON
Schema-enforced output; every field matches your contract
Source coordinates
Every value links back to page + bounding box for audit
Per-document pricing
Predictable cost. No token-volatility surprises
Trusted by teams turning documents into production data
Mixed-format referrals, missing prior auth context, and inconsistent diagnosis coding mean staff spend hours per day on data entry. Sensible automates the structured fields and flags what needs human review.
01
Referrals show up as faxed paper forms, EHR-generated PDFs, plain-text letters, and structured C-CDAs. Each format gets its own configuration, and SenseML makes each one repeatable.
02
ICD-10 codes embedded in referral text often arrive truncated, deprecated, or formatted differently across systems. Validation catches these before they hit your scheduling and prior auth workflows.
03
A referral isn't just a name and diagnosis — relevant labs, imaging history, and prior treatments sit in narrative sections that specialists need before scheduling. Sensible parses these into structured fields.
Managed services
Solutions engineers handle plan, build, deploy, and adjust on your behalf. You see clean JSON in your API response. Same engine as self-serve, just with the configuration work outsourced.
What's included
01Plan.Engineers review your samples and pick the right method
02Build.SenseML configs written from your samples
03Deploy.Same engine as self-serve, ready for production
04Adjust.We update configs when formats shift or new edge cases appear
05Integrate.Help with custom integration into your downstream systems
We configure every referral extraction to your exact schema, not a fixed field list. The fields below are the ones intake teams pull most often — tell us what your intake, scheduling, or prior-auth pipeline needs and we map the rest.
01
Patient and referring provider
Patient name, date of birth, contact info, referring provider, NPI, referring facility, referral date
02
Clinical reason
Specialty requested, diagnosis (ICD-10), reason for referral, urgency, chief complaint
03
Authorization context
Insurance carrier, member ID, prior auth required, prior auth number, supporting documents flag
config.json
SenseML
{ /* SenseML: referral extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{ "id": "specialty_requested", "description": "specialty, referred to" },
{ "id": "diagnosis_code", "description": "diagnosis code, ICD-10" },
{ "id": "urgency", "description": "urgency, routine or urgent" }
// + more fields, mapped to your schema
]
}
}
]
}Sensible processes referrals from any source, with pre-built configurations for common EHR exports.
Epic referral letters, Cerner specialty consult requests, athena referral forms, and C-CDA structured documents.
Traditional faxed referral pads, dictated letters, and unstructured PDFs from independent practices.
Answers about referral formats, diagnosis code validation, and prior authorization context.
Hybrid OCR handles low-contrast and degraded fax inputs. Deterministic rules enforce the output schema so faxed and structured referrals produce consistent JSON for intake systems.
Yes. Insurance carrier, member ID, prior auth required flag, prior auth number, and supporting-document flags get extracted alongside clinical fields. This gives intake staff everything they need to route a referral.
Yes. Specialty requested, diagnosis (ICD-10), reason for referral, and urgency come out as discrete fields, with embedded diagnosis codes validated against the active code set before they reach scheduling or prior-auth systems. The fields are defined in configuration, so you add or reshape them to fit your routing.
Sensible processes referrals from any source. Pre-built configurations cover Epic referral letters, Cerner specialty consult requests, athena referral forms, and C-CDA structured documents. Faxed and free-text referrals can be configured in SenseML.
Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.
Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.
Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.
Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.
Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.
Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.
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.
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.
Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.
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.
Start free
Free 14-day trial. No credit card required. Start extracting in minutes.