AI Model Intelligence Evaluation - 3 Models for Emergency Triage
EIMLIA-3M-TEU is a multidimensional comparative evaluation study of the three AI architectures developed in TIAEU. This project combines Process Mining, Discrete Event Simulation (DES), and Multi-Agent Systems to create a digital twin of the emergency department.
Hybrid DES + Multi-Agent Systems simulation
Automated patient pathway extraction
TRIAGEMASTER (NLP)
URGENTIAPARSE (LLM)
EMERGINET (JEPA)
Length of stay, mortality, resource allocation
Unsupervised text analysis with vector representations of verbatims.
Pre-trained LLM with fusion of textual embeddings and vital signs.
JEPA architecture with specialized encoders and latent space learning.
Accuracy, sensitivity, specificity, AUC-ROC, F1-score
Length of stay, waiting time, room occupancy
Under-triage rate, simulated mortality
Cost per patient, resource optimization
MR-004 methodology with declaration N° 27797006 to the Health Data Hub.