Out of the FHIR Podcast · New episodes weekly

I help healthcare orgs make sense of FHIR, AI, and quality measurement

I'm Eugene Vestel. Through consulting, open-source tools, and the Out of the FHIR podcast, I help teams navigate healthcare interoperability and turn data into outcomes.

Payer Interoperability Analytics & AI Lead at Outcomes · Former NCQA consultant · 15+ years in healthcare data

Figure 1

What “quality measurement” looks like when it stops being a slide.

Fig. 1CBP · Controlling High Blood Pressure
SourceCQL
valueset "Systolic BP": '2.16.840.1.113883.3.526.3.1032' define "Numerator":  exists (    [Observation: "Systolic BP"] BP      where BP.effective during "Measurement Period"        and BP.value < 140 'mm[Hg]'  )
CompiledANSI SQL
SELECT DISTINCT p.patient_idFROM   patient AS pJOIN   observation AS o  ON   o.subject_ref = p.patient_idJOIN   valueset_member AS v  ON   v.code = o.code AND   v.system = o.code_systemWHERE  v.valueset_oid = '2.16.840.1.113883.3.526.3.1032'  AND  o.effective BETWEEN :period_start AND :period_end  AND  o.value_quantity < 140
Measure
1
Value sets
1
Source lines
7
Target lines
10
Fig. 1 — A quality-measure numerator written once in CQL, and the warehouse SQL it compiles to. The value set resolves to a join, the measurement period to a bounded predicate.

Track record

  • Outcomes

    Payer Interoperability Analytics & AI Lead

  • SQL on FHIR

    HL7 working group

  • NCQA

    Consultant · 2025

  • b.well Connected Health

    Director of Data & Analytics

  • UPMC Health System

    5 years in Clinical Analytics

  • HL7 FHIR DevDays

    Speaker · HealthClaw

Standards

Where the work happens

I hired and led b.well Connected Health's first FHIR team, stood up Analytics on FHIR there, and mapped the data for the interoperability platform now behind Samsung Health and Fitbit's medical records. The standards work below is where that experience keeps getting tested against other implementers.

Working groups

SQL on FHIR
HL7 working group behind ViewDefinition — the specification underneath the CQL-to-SQL work above, and the ViewDefinition packs in the library.
Agents on FHIR
Weekly working group on what it takes to put agents against clinical data safely.
Quality measurement community
Early CQL practitioner, and among the first doing CQL-to-SQL conversion for measures that have to execute at scale.

Speaking

HL7 FHIR DevDays
Presented HealthClaw — guardrails between AI agents and FHIR data.
Analytics on FHIR
Conference speaker, 2025.
FHIR Camp
2025.

Newsletter

The FHIR IQ Playbook

A weekly newsletter on FHIR implementation, quality measurement, healthcare AI, and the tools and standards shaping interoperability. Written for the people doing the actual work.

Read by 450+ healthcare data professionals · Presented at Analytics on FHIR 2025

  • Weekly insights
  • No spam, ever
  • Unsubscribe anytime

Open Source

What I'm building

A guardrail layer between AI agents and health data, a personal care agent built on top of it, and an open corpus of the quality measures the whole industry keeps rewriting from scratch. All open, all running.

Livehealthclaw.io

HealthClaw Guardrails

A security layer between AI agents and clinical data. Redacts PHI on every read, enforces multi-step human approval for clinical writes — proposal, permission evaluation, HMAC confirmation, immutable audit log — and keeps your health agent interactions HIPAA-compliant.

  • 12 MCP Tools
  • PHI Redaction
  • FHIR R4/R6
  • US Core v9
  • Fasten Connect
  • Local SQLite
Livecareagents.cloud

CareAgents

Spin up a personal health agent in under a minute. Every read redacted, every access audited, every action approved by you — guardrailed by HealthClaw. This is what the guardrail layer looks like once a person is actually using it.

  • Personal health agent
  • Redacted reads
  • Audited access
  • Human approval
Liveopenquality.us

Open Quality

An open, MIT-licensed corpus of healthcare quality measures with verified provenance, plus a typed record of what implementers have actually learned about each one. CQL and SQL alongside the measure, not buried in a PDF.

  • MIT licensed
  • Verified provenance
  • CQL + SQL
  • Implementer notes
Ecosystem Analysisainpi.dev

AINPI

An ongoing analysis of the CMS health tech ecosystem and the national provider directory modernization effort. Mapping the players, the standards, and the FHIR-based architecture behind the next-generation healthcare directory.

  • CMS Ecosystem
  • National Provider Directory
  • NPPES
  • FHIR
  • Policy Analysis

More experiments in progress — Curatr Skills and others

See all projects on GitHub

Advisory

Work with me

I advise healthcare organizations on FHIR implementation strategy, data architecture, quality measurement, and AI readiness. Whether you're starting your FHIR journey or optimizing an existing implementation, I can help you move faster and avoid common pitfalls.

Book a Call
  • FHIR implementation strategy
  • Data architecture & pipelines
  • Quality measure implementation
  • SQL on FHIR adoption
  • AI & LLM integration
  • Team training & enablement

Stay in touch

Stay in the loop

Join 450+ healthcare data professionals getting weekly insights on FHIR, AI, and quality measurement. Read by engineers, architects, and analysts at health systems, payers, and vendors.