Andrew Napier, MD, FAAEM

Clinical AI product leader and practicing emergency physician working at the research-to-production boundary for LLM-based healthcare AI. Co-founded Sayvant and leads documentation and evaluation work used across 100+ care sites and more than 1.1M charts. Builds physician-written rubrics, chart-grounded QA, dangerous-fabrication review, PHI-aware routing, HIPAA/BAA-aware deployment, and post-launch monitoring. Stanford MCiM graduate, Army veteran, FDA-regulated Class I device founder, and first author on 2026 medRxiv preprints spanning production documentation QA and video-linked airway procedural telemetry.

• Clinical AI product leader across strategy, requirements, evaluation design, launch decisions, adoption, and post-launch quality in production care settings.
• Co-founded Sayvant and leads clinical AI product and evaluation work for ambient documentation systems used across 100+ care sites and more than 1.1M charts.
• Turns physician complaints, clinician adoption friction, health-system rollout lessons, and ED workflow constraints into researchable product questions and highest-impact requirements.
• Stanford MCiM graduate with active work in model evaluation, physician-grounded labels, validation planning, and acute-care implementation.
• Built privacy and safety workflows for clinical AI, including HIPAA/BAA-aware deployment, PHI-aware routing, chart grounding, hallucination review, dangerous-fabrication review, and post-launch monitoring.

• Owned clinical AI strategy, roadmap decisions, requirements, evaluation design, launch decisions, and physician-review workflows for documentation and evaluation systems used across 100+ care sites and more than 1.1M charts.
• Converted physician complaints, clinician adoption friction, health-system rollout lessons, and ED workflow constraints into researchable product questions and highest-impact requirements.
• Translated customer needs, technical constraints, and regulatory considerations into rubric changes, validation plans, QA loops, release calls, and model-output triage.
• Used production feedback from 13 hospital sites, 42 tracked physician complaints, and 1,089 optimization iterations to reach zero regressions on resolved complaints.
• Built privacy and safety controls for production clinical AI: HIPAA/BAA-aware deployment, PHI-aware routing, chart grounding, hallucination review, dangerous-fabrication review, billing completeness, and legal defensibility checks.
• Released ScribeBench and Sayvant SQS artifacts: physician-written rubric benchmarks with 282 binary checks and 166 deterministic repair rules; controlled ablation improved pass rate by 11.7 percentage points and eliminated 6/6 fabrication-class failures.
• Partnered across engineering, research, design, legal, regulatory, clinical, and GTM work to move high-stakes workflows from discovery through launch, adoption, evaluation, and post-launch QA.
• Led ED chest pain clinical AI work around paired ambient encounter signal and physician-authored decision traces, with Stanford AIMI presentation, AMIA 2026 abstract #15227, and manuscript in preparation.
• Published IntuBlade computer-vision airway telemetry preprint and public evidence package: 30 manikin runs, video-linked structured JSON, QC fields, package hashes, and bounded claims around traceability rather than autonomous guidance or clinical efficacy.
• Scaled IntuBlade from an ER problem into patented hardware, an FDA-regulated Class I product used by 400+ EMS agencies across 41 states, $250K+ recorded sales revenue, field adoption, and live operating systems across legal, shipping, inventory, pilots, AR, and GTM.

• Emergency Chest Pain Clinical AI Work. AMIA 2026 podium abstract accepted, abstract #15227, Fall 2026.
• IntuBlade pitch presentation. Stanford Emergence Annual Impact Summit, Stanford, CA, Jun 5, 2026.
• Training Clinical Decision Support from Ambient Conversation: Separating Patient Signal from Documentation Bias in Emergency Chest Pain. Stanford AIMI Symposium / Health AI Week, poster presentation, Stanford, CA, Jun 3, 2026.
• Planning for the Future: Lessons Learned Partnering with Health Systems to Implement AI in Acute Care Delivery. HITLAB Spring Summit, Sayvant session, May 5, 2026.
• The HIT Will Come. Guest lecture, Eastern Kentucky University Emergency Medical Care Program, Richmond, KY, Apr 2026.
• From Napkin Sketch to Reality: Your Path to the Creation of a Medical Device. Entrepreneurship and Networking for Doctors Conference, SoMeDocs, Jan 2023.