Document extraction built for healthcare engineering and operations teams.

EOBs, CMS-1500, UB-04 claims, prior authorizations, and every healthcare doc your pipeline handles. We've seen it all. Every field is validated, typed, and traced to its source.

40+
EOB payer formats prebuilt
JSON
Validated against your schema
Minutes
To configure a new payer format
HIPAA
On Enterprise · SOC 2 Type II
healthcare_eobs/uhc
Live in DevPublish configurationDocumentation ↗
MW
uhc_eob_sample⤓⤒⊘▾ 100%▾ 1/2‹›
ExtractionValidations 0Errors 0
▤{ }▾
Explanation of Benefits
U
UNITED
HEALTHCARE
Member Information
MemberSarah J. Patel
Member ID874-55-8821
Group No.0421007
PlanChoice Plus PPO
Claim Details
Claim No.2024-0915-44729
Date of Service09/12/2024
ProviderNorth Bay Family Medicine
Provider NPI1922109114
Service Lines
Service · CPTBilled · AllowedPlan Paid
Office visit, est. patient
CPT 99214$285.00
$162.40$129.92
CBC w/ differential
CPT 85025$48.00
$11.85$9.48
Comprehensive metabolic
CPT 80053$92.00
$15.20$12.16
Summary
Total Billed$499.00
Plan Discount$291.50
Member Responsibility$41.50
▶ Plan Paid$166.00
1{
2"member_id": {
3"value": "874-55-8821"
4},
5"claim_number": {
6"value": "2024-0915-44729"
7},
8"date_of_service": {
9"value": "2024-09-12",
10"type": "date"
11},
12"service_lines": [
13{
14"cpt_code": "99214",
15"billed": 285.00,
16"plan_paid": 129.92
17},
18{
19"cpt_code": "85025",
20"plan_paid": 9.48
21}
22],
23"member_responsibility": {
24"value": 41.50
25},
26"plan_paid_total": {
27"value": 166.00
28},
29"payer": "UnitedHealthcare"
30}

Trusted by teams turning documents into production data

The platform

Sensible turns healthcare documents into your data layer.

An API call sends an EOB, claim form, or prior auth to Sensible. A SenseML config (yours, ours, or built together) defines what to extract. The platform returns structured JSON validated against your schema, with source coordinates per field. Engineers ship extraction in days instead of months. RCM and claims teams stop re-keying. Compliance gets a clean trail.

API & SDKs

REST API with Python and Node SDKs, plus webhook support for async processing.

View the docs →

Off-the-shelf configs

get started in minutes using configs our team has already built for the most common doc types

Browse healthcare configs →

Schema & provenance

Type validation, cross-field reconciliation, and source-coordinate trace per field. Every output is auditable.

Managed services

Don't want to own the configs? Sensible's team builds, tests, and maintains extractions for you.

Learn about managed services →
How it works

From document to structured data, in four steps.

The same pipeline whether you're running a 2-page EOB or a 60-page medical record. Sync or async. Same auth, same schema contract.

Step 01

Send the document

POST a PDF, scan, or fax-image to the extraction endpoint with the SenseML config that matches the payer format. Sync, async, or email-driven intake.

POST /v0/extract
config: eob-uhc-v3
Step 02

Hybrid pipeline runs

Layout-based rules locate fields. LLM parsing handles ambiguous sections, tables, and prose. SenseML constrains both halves to your schema.

OCR → layout match → LLM parse → type cast
Step 03

Validate every field

Schema enforcement, type checks, cross-field reconciliation, and confidence scoring. Low-confidence fields surface for human review instead of silently shipping bad data.

schema → types → cross-ref → confidence
Step 04

Deliver to your stack

Validated JSON returns sync, or via webhook for async jobs. Plug into your RCM platform, claims workflow, prior-auth system, or data warehouse. Source coordinates ride along for audit.

{ fields: {…}, source_coords: {…} }
Healthcare documents we extract

Deep expertise in the healthcare space.

Click below to learn more about the most common use cases that we support. Don't see your specific use case? No worries, we can build configs for any document type

Explanation of benefits — sample extracted by Sensible

EOBs

40+ payer formats, line-level remits

View document type →

CMS-1500 and UB-04 claim forms — sample extracted by Sensible

CMS-1500 & UB-04

Professional and institutional claims

View document type →

Prior authorization form — sample extracted by Sensible

Prior authorizations

Status, denials, appeal letters

View document type →

Lab report — sample extracted by Sensible

Lab & imaging reports

Result panels, narrative findings

View document type →

Prescription — sample extracted by Sensible

Prescriptions & Rx

NDC, dose, sig, refills, prescriber

View document type →

Patient intake form — sample extracted by Sensible

Patient intake

Demographics, history, consent

View document type →

Browse the full healthcare config library →
Partner with us

We build the extraction layer. You ship product.

Plenty of teams would rather not write document parsers, monitor model drift, or maintain configs across format changes. Sensible's services team can handle all of it.

What you give usSample documents · target schema · target throughput
What you get backA working extraction endpoint, configs in your environment, downstream integrations wired up
PricingSame per-document rate as self-serve. No separate build fees.
01

Custom configs

SenseML for any layout your team handles. EOBs, claims, prior auths, niche payer forms, faxed referrals. Versioned in your environment

02

Integration delivery

Webhooks, batch jobs, fax and email intake, downstream mappings into your RCM platform, claims workflow, prior-auth system, EHR, or warehouse.

03

Drift & format maintenance

When a payer changes a layout or a model's behavior shifts, we update the configs. Your pipeline keeps shipping. Engineering team stays on product work.

04

White-glove onboarding

High-volume teams get a dedicated solutions engineer through go-live. Schema design, test coverage on real documents, monitoring and alerting.

Talk to managed services →Schedule a call
Customer story

How a healthcare benefits company went live with 30 configurations in weeks.

After their previous extraction vendor stalled on long-tail formats, the engineering team rebuilt on Sensible. Thirty configurations shipped through CI/CD in weeks, with schema validation and source-coordinate provenance on every field.

Read the full story →
30Configurations live in weeks
40+EOB payer formats supported
JSONValidated against your claim schema
Healthcare resources

How healthcare teams build with Sensible.

Blog · Tutorial

How to extract data from EOB documents

Multi-payer EOB patterns, line-level remits, denial codes.

Blog · Tutorial

Extract data from CMS-1500 forms

Walk-through of claim form extraction with SenseML.

Blog · Customer

30 configurations live in weeks

How a healthcare benefits company replaced a failing vendor.

Blog · Customer

Two healthcare orgs automate document processing

Side-by-side approaches and trade-offs.

Blog · Compliance

SOC 2 Type II certification

Audit scope, controls, what it covers for healthcare workloads.

Library · Configs

Healthcare config library

40+ payer EOBs and starter configs. MIT-licensed.

SOC 2 Type II

Audited annually

HIPAA-ready

Available on Enterprise

Field-level provenance

Every extraction traceable

Per-document pricing

Predictable, no surprises

FAQ

Questions healthcare teams ask.

What healthcare document types does Sensible support?
EOBs from 40+ payers (UHC, Humana, Cigna, Anthem, Kaiser, Blue Shield, Medicaid, Medicare, and more), CMS-1500 and UB-04 claim forms, prior authorizations, lab and imaging reports, prescriptions, patient intake, and medical records. Each ships as a starter config in the healthcare library.
How does Sensible handle different payer formats?
Each payer layout is its own SenseML config. Configs are versioned, testable, and deployable through CI/CD. New payer formats become new configs without changing your API integration.
Why not just prompt an LLM directly?
LLMs with structured outputs return syntactically valid JSON, but they don't enforce that claim totals reconcile, that a CPT code is one your system accepts, or that a denial code actually appears on a specific page. Sensible runs deterministic validation on top of the model output and traces every field back to its source coordinates, so a downstream system never gets a hallucinated value.
How does this compare to building extraction in-house?
First version of an in-house build usually works. The cost shows up later: model deprecations, payer format drift, prompt regressions, the audit trail you didn't build, the human-review queue you didn't design. Sensible runs that infrastructure so engineering time stays on your product. SenseML is open and MIT-licensed, so the configs are yours to fork if you ever want to take it back in-house.
Does Sensible meet healthcare compliance requirements?
SOC 2 Type II certified. HIPAA on Enterprise plans. Field-level source coordinates per extraction support audits, regulatory compliance, and clinical review.
How is pricing structured for healthcare volumes?
Per-document pricing regardless of page count or complexity. Trials start on the Growth plan for 14 days. View pricing →
Get started

Start extracting healthcare documents today.

14-day free trial on the Growth plan. Pre-built healthcare configs included. No credit card required.

Start extracting free →Schedule a demo