Clinical AI
Ambient documentation, physician oversight, chart-grounded extraction, and evaluation systems that catch failure before the chart absorbs it.
View portfolioAndrew Napier, MD
Emergency physician and founder building clinical AI and airway systems for high-acuity care.
I work where ED reality breaks clean demos: airway management, ambient documentation, decision support, and the evaluation work that keeps clinical AI tied to the record.
100+
care sites using Sayvant documentation systems
800k+
structured charts generated
$95
single-use USB-C video laryngoscope platform
4
issued, pending, or provisional patent families
Start here
Different readers usually need different doors. Pick the one closest to what you came for.
Airway systems
Single-use video laryngoscopy, on-blade lens clearing, procedural guidance, and airway tools built for EMS and ED reality.
See IntuBladeStanford / research
Clinical informatics work on human-in-the-loop guidance, ambient assistants, pragmatic evaluation, and acute-care decision support.
See papersFormal record
Training, roles, patents, publications, awards, military service, and the document trail behind the work.
View CVSelected technical contributions
The common thread is acute-care deployment. The tool has to survive tired clinicians, incomplete records, bad lighting, cost pressure, and real consequences.
Clinical AI evaluation
Physician-review workflows for ambient documentation, including chart-grounding checks, failure analysis, billing completeness, and legal defensibility review.
Airway device translation
A lens-clearing video laryngoscope taken from clinical problem to patented design, FDA-cleared product, production hardware, and commercial launch.
Procedural guidance
Real-time visual guidance for intubation and bronchoscopy, including depth perception and anatomical highlighting concepts for video-assisted procedures.
Current work
The companies and academic work are separate on paper. In practice, they are the same problem from different angles.
Co-Founder & Head of Clinical AI
Sayvant
Clinical AI documentation systems for emergency and hospital medicine across 100+ care sites and more than 800,000 charts.
Learn moreFounder & CEO
IntuBlade
A $95 single-use USB-C video laryngoscope platform for EMS, EDs, and low-resource settings.
Learn moreClinical Informatics
Stanford MCiM
Current work on clinical AI evaluation, procedural guidance, ambient assistants, and pragmatic trials in acute care.
Learn moreSelected Writing
All writingMostly notes on what changes when clinical AI and devices have to survive cost, workflow, fatigue, and actual consequences.
- • 6 min read
Preventing AI Fabrication in Clinical Documentation
How I think about keeping physician-facing documentation systems from quietly making things up and losing trust.
- • 7 min read
Building a Chest Pain Risk Stratifier from Clinical Conversations
Why I worked on chest pain risk support from conversation data and why support matters more than false certainty.
- • 6 min read
Changing Models in Clinical Documentation Without Losing Control
How I think about swapping model backends in clinical documentation without turning the chart into an experiment.
Papers & proof
All papersThe publication list is short. That is true. I would rather show a small body of work tied to real problems than pad the bibliography.
Lens-Clearing Laryngoscopy
American Journal of Emergency Medicine · 2021 · PMID 33632548
Emergency Medicine Ultrasound Pocketbook Guide
Book · 2020
Clinical AI evaluation and decision support work
Stanford MCiM · Current research track
Elsewhere at Sayvant
Content hubCritical Care Billing for EM Clinicians
Sayvant · January 27, 2025
Bridging the Gap Between Decisions and Documentation
Sayvant · December 2, 2024
Why "Defensive" Documentation Fails
Sayvant · October 27, 2025
Document trail
The CV has the formal record: training, roles, publications, patents, awards, military service, and the rest.