Participatory AI Atlas
Public health / clinical predictionhealthcareParticipation documented

Sepsis Watch

Durham, United States

Frontline clinicians shaped workflows and governance from design through real-world integration.

human-centered designsociotechnical integrationparticipatory governanceproblem formulationUI_UX_designdeploymentadoption_use_decisionsgovernance
Project documentationEvidence source
Overview
Region
North America
Lead organization
Duke Health; Duke Institute for Health Innovation
Organization type
university health system
Technology group
deep learning / risk prediction
Activity status
active
Start year
2018
Last updated
Mar 25, 2026
Participation documentation
Participation mode
clinician co-design + governance
Participants
physicians; nurses; rapid response teams
Methods
interviews; workflow co-design; governance committee; monitoring
AI lifecycle stages
problem formulation; UI_UX_design; deployment; adoption_use_decisions; governance
Evidence summary
Frontline clinicians shaped workflows and governance from design through real-world integration.
Atlas assessment
Core · High confidence · evidence grade A
Uncertainty
Public evidence indicates that stakeholders directly shaped AI design, data, deployment, evaluation, or oversight; residual uncertainty concerns the exact degree of shared decision power rather than project existence.
Project details
Participation group
Co Design
Technology description
deep learning / risk prediction
Funding
Not documented
Region of activity
health-system
Verification status
Live Verified
Links
Project documentationOfficial pageEvidence sourceResearch paperRegistry record

Community input

Corrections, annotations, and private disclosure requests.

Sepsis Watch has 0 published community items.

Published corrections

Loading moderation history...

Published annotations

Loading annotations...

Submit a correction

Flag a metadata problem or submit a dispute for Sepsis Watch.

Submit an annotation

Add context without editing the record itself.

Request restricted disclosure

These requests are private and reviewed for later releases.

Related records

Algorithmic governance / public servicesNorth America
AI Failure Cards for Homeless Services

Pittsburgh, United States

Open record
Participatory auditing / LLM safetyNorth America
AI Red Teaming Challenge

Las Vegas, United States

Open record
Governance / auditingNorth America
Algorithmic Equity Toolkit

Seattle, United States

Open record
Social media / contextual NLPNorth America
Artificial Intelligence and Inclusion: Formerly Gang-Involved Youth as Domain Experts

New York City, United States

Open record