STaR-AI

Systems for Triage and Response with AI

Innovative research group dedicated to improving emergency triage and patient care through Artificial Intelligence. Led by Dr Edouard Lansiaux, we develop solutions that save lives.

Discover our projects

7

Research projects

2000+

Patients enrolled

90%

AI concordance

10

Partner centers

Our Research Projects

A progressive and complementary approach to revolutionize emergency triage

Pilot study - Published

TIAEU

Intelligent Triage at Emergency Entry

Single-center retrospective study (n=657, Lille University Hospital) demonstrating superiority of 3 AI models (NLP, LLM, JEPA) over standard nursing triage. Concordance of 90% vs 30% (p<0.001).

Publication: IEEE BDCAT 2025, JMIR Medical Informatics

Ongoing

TIAEU-2

Prospective multicenter extension

External validation across 5 centers (CHU Lille, CH Douai, Denain, Maubeuge, Tenon AP-HP) with several thousand patients. Period: January-February 2026.

Type: Prospective observational study

Funding pending

TRIADE

AI-Assisted Triage for Informed Decision-Making

Prospective cluster-randomized bicentric trial (CHU Lille, CH Maubeuge) evaluating AI assistance under real-world conditions. Objective: concordance increase from 68% to 76%.

Funding requested: PHRC-I & doctoral grant

Ongoing

EIMLIA-3M-TEU

AI Model Intelligence Evaluation

Multidimensional comparative evaluation of three AI architectures (NLP, LLM, JEPA) for emergency triage, with hybrid Process Mining simulation and digital twins.

Approach: DES Simulation + Multi-Agent Systems

International collaboration

REDIRECT-AI

AI-assisted patient redirection

Redirection application integrating AI to identify cases suitable for primary care. Estimated 15-20% reduction in emergency department overcrowding.

Partners: CHU Quebec, Mila, IVADO

Ongoing

HARMONIA

Humans vs AI in Emergency Medical Dispatch

Prospective study comparing a GPT model against call dispatchers and dispatch physicians at the SAS-Centre 15 on 60 simulated scenarios. Double-blind design with complete crossover evaluation.

Center: SAS-Centre 15, Lille University Hospital

International collaboration

3/4trics

Triage effectiveness metrics

International multicenter federated study evaluating an innovative triage effectiveness metric in emergency departments. Federated analysis with row-level data processed locally.

Partners: Lund Univ. 🇸🇪, Yale 🇺🇸, UVA 🇺🇸

Publications & Communications

Scientific Articles

YouTube Videos - AI & Triage

Watch our video presentations on artificial intelligence applied to emergency triage on Dr Edouard Lansiaux's YouTube channel:

Media Coverage

Our Team

Dr Edouard Lansiaux

Principal Investigator
Emergency Physician
AI Engineer
Lille University Hospital

Dr Ramy Azzouz

Co-director
Hospital Practitioner
Poison Control Center CHU Lille
AI in Healthcare Director

Dr Roch Joly

Clinical Director
Department Head
Emergency Department
Lille University Hospital

Pr Eric Wiel

Scientific Director
Professor of Emergency Medicine
Lille University Hospital

Pr Emmanuel Chazard

Methodology & Biostatistics
Professor of Public Health
METRICS ULR 2694
Lille University Hospital

Pr Daniel Balouek

Cloud Computing & Edge AI Expert
IMT Atlantique

Pr Hayfa Zgaya-Biau

Process Mining Expert
METRICS ULR 2694 & CRIStAL UMR 9189

Pr Mehdi Ammi

Man-Machine Interface Expert
LIASD

Our Impact

🎯

Triage accuracy improvement from 30% to 90%

⏱️

Reduction of dangerous under-triage for patients

🏥

Optimization of hospital resources

🌍

International collaborations France-Canada-Sweden-USA