Intelligent Triage at Emergency Entry
TIAEU is a single-center retrospective study including 657 patients at Lille University Hospital over 7 months (2024). This study demonstrated the superiority of 3 AI models (NLP-TRIAGEMASTER, LLM-URGENTIAPARSE, JEPA-EMERGINET) over standard nursing triage. Concordance with final medical decision (FRENCH scale) reached 90% for the best AI vs 30% for standard nursing triage (p<0.001).
Evaluate AI model performance for ED triage compared to standard nursing triage using FRENCH scale
Single-center retrospective study (CHU Lille) including 657 patients with 10-fold cross-validation
AI concordance: 78% vs Nurse: 30% (p<0.001)
Under-triage: 11% vs 18% (RR=0.61)
IEEE/ACM BDCAT 2025
Nantes, France
Exact concordance: 90%
Concordance ±1 class: 89%
Weighted Kappa: 0.80
URGENTIAPARSE (LLM)
AUC-ROC: 0.879
F1-score macro: 0.894
Lansiaux E, Azzouz R, Chazard E, Vromant A, Wiel E.