Skip to content
MedeviRequest access

News

Publications and presentations.

Peer-reviewed papers, protocols, conference talks and project updates from the Medevi team.

PresentationICAM 2026 · Apr 2026 · Ottawa, ON

Medevi: Large Language Model-Assisted Critical Appraisal for Medical Education Research

LLM-assisted appraisal reached substantial agreement with human reviewers on MERSQI (ICC 0.755) at under a minute and $0.10–$0.57 per paper, while NOS-E agreement remained fair (ICC 0.345).

David Nguyen, Andrew Ganea, Minh Hoang Ton, Matthew Sibbald, Medevi Team

Read the summary Slides (PDF)
  • Two Medevi team members on stage presenting the slide "Why automate critical appraisal assessments?" to a seated audience.
  • Medevi team members at the podium presenting a slide of Medevi's AI-enabled data extraction pipeline.
  • Three conference attendees standing together in front of the AFMC and ICAM 2026 backdrop.

Opening our ICAM 2026 talk: why critical appraisal needs rigorous, validated automation.

1 / 3

All news

Apr 2026ICAM 2026
Medevi: Large Language Model-Assisted Critical Appraisal for Medical Education ResearchDavid Nguyen, Andrew Ganea, Minh Hoang Ton, Matthew Sibbald, Medevi Team
Presentation
Nov 2025T-CAIREM 2025
Medevi-RoB: Benchmarking Large Language Models for Automated Risk-of-Bias (RoB 2) AssessmentDavid Nguyen, Medevi Team
Presentation
15 Sep 2025OSF Registries
Protocol for Cross-Domain Benchmark for Automated Risk of Bias 2 (RoB 2) Assessment in Randomized Trials using Large Language Models (Medevi-RoB)David L. Nguyen, Andrew Ganea, Dylan Kwan, Nathan Lai, Minh Hoang Ton, Dena Zeraatkar
Publication · Protocol
Subscribe via RSS