FHIR Development Skill

Description

Build FHIR R4 compliant healthcare interoperability systems. Covers Da Vinci implementation guides (PAS, CRD, DTR), US Core profiles, CMS-0057-F compliance, and SMART on FHIR authorization.

When to Use

•Developing FHIR servers or clients
•Building prior authorization APIs (CMS-0057-F)
•Implementing CDS Hooks for coverage requirements discovery
•Creating or validating FHIR resources
•Mapping between X12 and FHIR representations
•Working toward CMS interoperability rule compliance
•Building Da Vinci PAS, CRD, or DTR implementations

Capabilities

•Resource Building: Construct FHIR R4 resources (Claim, ClaimResponse, Condition, Procedure, Coverage, QuestionnaireResponse, DetectedIssue)
•Profile Validation: Validate resources against Da Vinci PAS, CRD, DTR, and US Core profiles
•Bundle Assembly: Build and parse PAS request/response bundles
•Terminology Mapping: ICD-10 urgency tiers, CPT clinical urgency, X12 278 status codes, CMS denial reason codes
•Compliance Checking: CMS-0057-F compliance checklist with per-requirement validation
•Urgency Assessment: Map diagnosis/procedure codes to clinical urgency classifications

Da Vinci ePA Workflow

The CMS-0057-F mandated prior authorization workflow uses three Da Vinci IGs:

code

1. CRD (Coverage Requirements Discovery)
   EHR fires CDS Hook at order entry → Payer returns coverage info
   "Is this service covered? Is PA needed? What documentation?"

2. DTR (Documentation, Templates, and Rules)
   Payer sends Questionnaire → Provider completes it
   "Fill out this form with the clinical justification"

3. PAS (Prior Authorization Support)
   Provider submits Claim bundle → Payer returns ClaimResponse
   "Here is the complete PA request" → "Approved/Denied/Pended"

Usage

Build a Prior Authorization Request

python

from skills.fhir_development import build_pa_request

bundle = build_pa_request(
    patient_id="patient-123",
    diagnosis_codes=["N44.00"],      # Testicular torsion
    procedure_codes=["54600"],        # Orchiopexy
    priority="emergent",
)

Validate a FHIR Resource

python

from skills.fhir_development import validate_resource

result = validate_resource(claim_response)
if not result["valid"]:
    for error in result["errors"]:
        print(f"  - {error}")

Check CMS-0057-F Compliance

python

from skills.fhir_development import get_compliance_checklist

checklist = get_compliance_checklist(claim_response)
for item in checklist["items"]:
    status = "PASS" if item["met"] else "FAIL"
    print(f"  [{status}] {item['requirement']}")

Assess Clinical Urgency

python

from skills.fhir_development import get_urgency_assessment

assessment = get_urgency_assessment(
    diagnosis_codes=["N44.00"],
    procedure_codes=["54600"],
)
# assessment["is_time_critical"] == True
# assessment["max_urgency_tier"] == 2

Relationship to Other Skills

Skill	Relationship
MSC Safety	FHIR resources can carry safety state; MSC enforces behavioral invariants
Coverage Decision Safety Review	Uses FHIR module for input parsing and output generation
PHI Detection	Run before transmitting any FHIR resources containing patient data

Supported FHIR Profiles

Profile	Source	Use Case
PAS Claim	Da Vinci PAS v2.1	Prior authorization request
PAS ClaimResponse	Da Vinci PAS v2.1	Prior authorization decision
PAS Request Bundle	Da Vinci PAS v2.1	PA request packaging
US Core Condition	US Core R4	Patient conditions
DTR QuestionnaireResponse	Da Vinci DTR v2.0	Documentation responses

Terminology Support

Code System	Coverage
ICD-10-CM	Emergency conditions with urgency tier mapping
CPT	Common procedures with clinical urgency classification
X12 278	PA status codes with FHIR outcome mapping
CMS Denial Reasons	Full denial reason taxonomy with FHIR coding

Triggers

FHIR, HL7, Da Vinci, prior authorization API, CMS-0057, interoperability, healthcare API, CDS Hooks, US Core, ClaimResponse, PAS bundle

Success Criteria

•Generated resources pass profile validation
•PAS bundles conform to Da Vinci IG structure
•CMS-0057-F compliance items are accurately assessed
•Urgency tier mapping matches clinical evidence base