Trusted by teams turning documents into production data
Healthcare
Medical records arrive as multi-page PDFs from disparate EHRs, scanned chart copies, and faxed summaries. Diagnoses, medications, encounters, and labs sit in narrative prose mixed with structured tables. Sensible converts any medical record format into normalized JSON for claims review, prior auth, and care coordination.
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
Narrative encounter notes, ICD-10 codes buried in prose, and EHR-specific exports demand more than table extraction. Sensible reads chart notes the way clinicians do, then validates against standard code sets.
01
HPI, assessment, and plan sections contain critical clinical data in unstructured prose. Sensible parses narrative sections into discrete fields without losing context, while keeping the source text linked for review.
02
Every extracted ICD-10, CPT, and RxNorm code gets validated against the active code set. Invalid or deprecated codes get flagged before they reach claims systems, where they would cause rejections.
03
Epic, Cerner, athena, Meditech, and dozens of regional EHRs export records differently. Each layout requires its own extraction configuration, and SenseML makes each one repeatable.
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 medical record extraction to your exact schema, not a fixed field list. The fields below are the ones clinical teams pull most often — tell us what your claims, prior-auth, or care-coordination pipeline needs and we map the rest.
01
Patient and encounter
Patient name, date of birth, MRN, encounter date, provider, facility, encounter type, chief complaint
02
Clinical data
Diagnoses (ICD-10), procedures (CPT), medications (RxNorm), allergies, vital signs, lab values, imaging findings
03
History and plan
Past medical history, family history, social history, assessment, plan, follow-up instructions
config.json
SenseML
{ /* SenseML: medical record extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{ "id": "encounter_date", "description": "encounter date, date of service" },
{ "id": "diagnoses", "description": "diagnoses, problems, ICD-10 codes" },
{ "id": "medications", "description": "medications, current meds, RX" },
{ "id": "assessment", "description": "assessment, impression" }
// + more fields, mapped to your schema
]
}
}
]
}Sensible processes medical records from any EHR, with pre-built configurations for major systems.
Epic, Cerner, athenaClinicals, Allscripts, Meditech, NextGen — pre-built configurations for each, validated against their standard export formats.
Legacy paper charts, faxed summaries, and scanned PDFs. Hybrid OCR plus narrative parsing handles degraded inputs.
Answers about EHR formats, narrative parsing, and code validation.
Yes. Long chart packets with multiple encounters get split per visit. Each encounter becomes its own structured record with date, provider, diagnoses, medications, and plan fields preserved.
Yes. Every extracted ICD-10, CPT, and RxNorm code is validated against the active code set. Invalid or deprecated codes get flagged before they reach claims or prior-auth systems.
HPI, assessment, and plan sections get parsed into discrete fields without losing context. Source text stays linked to each extracted value so clinicians can verify findings against the original note.
Records from any EHR. Pre-built configurations cover Epic, Cerner, athenaClinicals, Allscripts, Meditech, and NextGen, and the list is where we started, not where it stops. Faxed and scanned chart summaries from any source, including systems not named here, get 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.