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.

Product competencies: Product strategy and roadmap | LLM/model evaluation | Physician-written rubric design | Clinician-in-the-loop QA | Privacy and safety controls | HIPAA/BAA-aware workflows | Discovery-to-launch execution

• 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.

Stanford University School of Medicine: Master of Science, Clinical Informatics Management (Jun 2025 - Jun 2026, Stanford, CA) | University of South Florida College of Medicine: Doctor of Medicine (Aug 2013 - May 2017, Tampa, FL) | Eastern Kentucky University: Bachelor of Science, Biomedical Science (May 2009 - Dec 2012, Richmond, KY)

Research outreach is focused on collaborators evaluating clinical AI in real care: ambient documentation QA, physician-grounded labels, acute-care decision support, clinical coding, implementation science, and human-in-the-loop procedural guidance. Best-fit projects combine governed clinical signal, clinician adjudication, careful validation, and publishable methods.

• Production clinical AI documentation QA: medRxiv preprint posted May 29, 2026, with peer-review package and reproducibility materials in preparation.
• ED chest pain decision support: Stanford AIMI poster presented Jun 3, 2026 and AMIA 2026 abstract #15227 accepted, with manuscript and validation plan in preparation.
• ScribeBench / SQS / EM benchmark: public benchmark and scoring framework for clinical documentation quality, source fidelity, leak detection, dangerous fabrication, and rubric-based review.
• Diagnosis-to-ICD-10 code selection: private research/software with Geanderson Santos using California HCAI code-frequency data, synthetic EM/HM examples, frequency-aware retrieval, constrained LLM selection, and error analysis.
• Computer-vision airway procedural telemetry: medRxiv preprint posted Jun 29, 2026 with a public 30-run manikin evidence package, package checker, QC records, and repository-level reproducibility materials.
• Pediatric video laryngoscopy cost-effectiveness analysis: manuscript and budget-impact appendix in progress.

• Rice Business School Veterans Business Battle, First Place, IntuBlade, 1st of 15 finalist teams, $15,000 Prize (2026)
• Tillman Military Scholar, Pat Tillman Foundation (2012)
• U.S. Army: Purple Heart, Combat Medical Badge, Combat Action Badge, Valorous Unit Award
• VetsInTech Pitch Competition, First Place, $25,000 Prize (2024)
• UCSF Rosenman Institute Health Innovation Fellow
• EMS World Innovation Award, Finalist (2024 and 2020)
• Warrior Rising Pitch Competition, First Place, $20,000 Prize (2023)
• InnovatorMD startup competition, First Place (2022)