Work built for the part after launch.

Three representative systems: production clinical AI, fielded airway hardware, and a training product I built for the mats.

Clinical AI / acute care documentation

Sayvant

Co-Founder & Head of Clinical AI

Production documentation AI designed around source fidelity, physician review, and the failures that appear after launch.

Problem: A fluent note can still invent a medication, flatten uncertainty, or leave a physician with unsafe cleanup work.
Built: Physician-written rubrics, chart-grounded QA, dangerous-fabrication review, PHI-aware routing, and closed-loop complaint repair.
Result: Used across 100+ care sites and more than 1.1M charts; 1,089 closed-loop QA iterations across the published production study.

Visit Sayvant Read the production QA preprint

Airway hardware / procedural telemetry

IntuBlade

Founder & Product Lead

Single-use video laryngoscopy built around access, lens clearing, and the operational realities of field medicine.

Problem: Video airway tools often assume clean views, reusable monitors, maintenance infrastructure, and budgets that many EMS systems do not have.
Built: A single-use USB-C laryngoscope with fluid-assisted lens clearing, familiar Macintosh geometry, and connected video workflows.
Result: Used by 400+ EMS agencies across 41 states, with public video-linked telemetry and a 30-run manikin evidence-package audit.

Visit IntuBlade Read the airway telemetry preprint

Training software / BJJ analytics

Jits Analytics

Founder & Product Builder

A published training journal built to make progress on the mats visible between sessions.

Problem: Training notes, failed techniques, and coaching cues disappear quickly; generic habit trackers do not understand the structure of jiu jitsu.
Built: Session analysis, skill progression, weekly drills, Fighter DNA, coach chat, video review, gym connection, and iOS support.
Result: A live web and iOS product with real athletes, gyms, video analysis, and a full feedback loop outside healthcare.

Open Jits Analytics View the App Store listing

Research and supporting work

The deeper methods, public evidence, and technical artifacts behind the case studies.

Open the research record

100+ care sites

1.1M+ charts

1,089 QA iterations

30 airway runs audited

Clinical AI methods 5 operating areas

Translational study design

I start with the clinical action, not the model. For chest pain, that means ACS risk, history quality, disposition, calibration, expected utility, and whether the bedside workflow can carry the output.

Clinical annotation and QA

Physician complaint review, note-defect triage, chart-grounding checks, and repair loops for documentation systems that clinicians actually sign.

Model evaluation

Benchmarks have to catch the thing that hurts patients and physicians: invented findings, missing context, brittle raters, silent drift, and notes that look better than they are.

High-acuity workflow

I have led ED operations and still practice emergency medicine. That matters for bedside AI. Someone has to know when another alert, score, or note field becomes clinician cleanup labor.

Procedural AI and devices

Video laryngoscopy work now extends into human-in-the-loop procedural guidance: connected video, computer vision observations, event telemetry, public package checks, and trainer-confirmed safety fields.

Selected research proof 5 records

Computer-Vision Procedural Telemetry for Airway Guidance: A Public 30-Run Manikin Evidence-Package Audit

medRxiv preprint. First-author preprint with Serge Klement and Ben Fedeles. The work audits a public post-reconciliation evidence package from 30 simulated airway runs using an IntuBlade device and iPhone workflow. The claim is intentionally bounded: video-linked structured JSON, QC status, app/model metadata, package hashes, and assigned-condition consistency for formative airway telemetry, not autonomous guidance, model accuracy, training effectiveness, clinical efficacy, or patient outcomes. DOI: 10.64898/2026.06.26.26356677.

Closed-Loop Quality Assurance for Production Clinical AI Documentation

medRxiv preprint. First-author preprint with Justin Wiley and Mark Heslin. The work turns physician complaints from production AI documentation across 13 hospital sites into reproducible QA artifacts, driving 1,089 optimization iterations with zero regressions on resolved complaints. Evidence base: 42 tracked complaints, 282 binary checks, 166 deterministic repair rules, and 6/6 fabrication-class failures eliminated in ablation. DOI: 10.64898/2026.05.27.26353977v1.

Training Clinical Decision Support from Ambient Conversation

Stanford AIMI / AMIA 2026 / manuscript in preparation. Stanford MCiM capstone work with a public control repo, AIMI poster, and AMIA 2026 podium abstract #15227. The project pairs ambient patient signal with physician-authored decision traces so decision-support models are not trained only on downstream chart text. Manuscript and validation plan in preparation with Ashley Griffin and Mark Musen.

Health-System Implementation of AI in Acute Care Delivery

HITLAB Spring Summit, Sayvant session. Sayvant session on acute-care AI rollouts, workflow ownership, clinician review, rollout friction, feedback loops, and product lessons from health-system deployment. Final title: Planning for the Future: Lessons Learned Partnering with Health Systems to Implement AI in Acute Care Delivery.

ScribeBench and Sayvant SQS Framework

Public benchmark and framework artifacts. Public clinical documentation benchmark and scoring framework for narrative quality, source fidelity, leak detection, dangerous fabrication, and rubric-based review of ambient scribe output.

Public software and artifacts 11 projects

Jits Analytics

A published jiu jitsu training journal and analytics app for tracking progress on the mats, with AI-powered session analysis, skill progression, Fighter DNA, weekly drills, coach chat, video analysis, and iOS support via Capacitor.

BJJ training journal and analytics app Open

Jits Analytics iOS

The native iOS listing for Jits Analytics, the app version of the BJJ training journal and analytics project.

App Store listing Open

Closed-loop QA preprint

Production clinical AI documentation QA across 13 hospital sites, 42 tracked physician complaints, and 1,089 optimization iterations.

medRxiv preprint Open

ScribeBench

A clinical documentation fidelity benchmark for narrative quality, source fidelity, leak detection, dangerous fabrication, and rubric-based review.

Public benchmark Open

ed-chest-pain-analytics

Chest pain risk support around ambient encounter data, differential framing, physician-authored decision traces, AIMI presentation, and AMIA 2026 podium abstract #15227.

Public Stanford MCiM control repo Open

clinical-ai-learning-os

A Stanford MCiM learning and proof system for clinical AI, model validation, research inventory, quizzes, and post-graduation technical depth.

Private progress system, public shell Open

clinical-nlp-patterns

Patterns for clinical documentation systems, extraction-first prompting, validation design, and QA loops.

Public architecture notes Open

diag2icd10

Diagnosis-to-ICD-10 code selection using California HCAI frequency data, frequency-aware retrieval, constrained LLM selection, and error analysis.

Private research/software

human-in-the-loop procedural guidance

Computer-vision procedural telemetry for airway guidance: a public 30-run manikin evidence-package audit with video-linked structured JSON, QC status, app/model metadata, and package checks.

medRxiv preprint and public evidence package Open

intublade-procedural-guidance-paper-public

Public repository for the IntuBlade airway telemetry preprint, including the frozen evidence package, protocol files, package checks, QC records, and figure-generation materials.

Public reproducibility repo Open

pediatric-vl-cea

Pediatric video laryngoscopy cost-effectiveness analysis with manuscript draft, field-data strategy, and budget-impact appendix path.

Private manuscript buildout

Public evidence links 9 sources

Computer-Vision Procedural Telemetry for Airway Guidance

First-author medRxiv preprint. Public 30-run manikin evidence-package audit for video-linked airway telemetry, QC status, app/model metadata, and bounded traceability claims.

Open

IntuBlade Procedural Guidance Evidence Package

Public repository for the airway telemetry preprint, including the frozen evidence package, protocol files, package checks, QC records, and figure-generation materials.

Open

Closed-Loop Quality Assurance for Production Clinical AI Documentation

First-author medRxiv preprint. Closed-loop production documentation QA using physician complaints across 13 hospital sites, 42 complaints, and 1,089 optimization iterations.

Open

Scribe-Bench

Public fidelity benchmark for clinical documentation AI. Narrative quality, source fidelity, leak detection, dangerous fabrication, and rubric-based review.

Open

ED Chest Pain Analytics

Stanford MCiM control repo for ED chest pain risk support from paired ambient encounter data and physician-authored decision traces. AIMI poster presented. AMIA 2026 abstract #15227 accepted.

Open

Clinical AI Learning OS

Private Stanford MCiM learning and proof system for clinical AI, model validation, and post-graduation technical depth.

Open

Clinical NLP Patterns

Public architecture notes for ambient documentation systems, extraction-first design, validation templates, and QA loops.

Open

Preventing AI Fabrication in Clinical Documentation

Public writing on why clinical documentation systems must stay grounded in what was actually said and done.

Open

Changing Models in Clinical Documentation

Public writing on model migration, regression risk, and why clinical documentation needs evaluation beyond fluency.

Open