Publications

Application of Transformer Neural Networks for Data Cleaning in Emergency Room Logs: A Case Study From the Bordeaux University Hospital

Russon D, Gil-Jardiné C, Marcel L, Chanel L, Faure S, Maury B, Chenais G, Lagarde E

IEEE Journal of Biomedical and Health Informatics · 29(11):8484–8496

Transformer-based reconstruction of emergency activity logs at Bordeaux University Hospital, evaluated against an expert-annotated gold standard.

doi.org/10.1109/JBHI.2025.3586325 PMID 40627474 Copy citation

Harnessing Moderate-Sized Language Models for Reliable Patient Data Deidentification in Emergency Department Records: Algorithm Development, Validation, and Implementation Study

Dorémus O, Russon D, Contrand B, Guerra-Adames A, Avalos-Fernandez M, Gil-Jardiné C, Lagarde E

JMIR AI · 4:e57828

Reliable deidentification of emergency records using language models compact enough to be deployed on the hospital's own servers.

doi.org/10.2196/57828 PMID 40605780 Copy citation

Evaluating pedestrian crossing safety: Implementing and evaluating a convolutional neural network model trained on paired aerial and subjective perspective images

Russon D, Guennec A, Naredo-Turrado J, Xu B, Boussuge C, Battaglia V, Hiron B, Lagarde E

Heliyon · 11(4):e42428

Automated scoring of nine risk factors on French pedestrian crossings, from paired aerial and street-level imagery.

Published corrigendum Heliyon 11(14):e43902

doi.org/10.1016/j.heliyon.2025.e42428 PMID 40028551 Copy citation

Balancing Predictive Performance and Explainability for COVID-19 Data

Rodriguez-Idiazabal L, Avalos M, Russon D, Barrio I, Quintana-López JM

65th ISI World Statistics Congress

The trade-off between predictive performance and explainability on COVID-19 data.

inria.hal.science Copy citation

Serious games to address cognitive bias and patient flow in emergency departments

Avalos M, Elorga-Castagnet N, Russon D, Larrue F, Gil-Jardiné C

5th ENLIGHT Teaching & Learning Conference, Uppsala

Serious games to address cognitive bias and patient flow with clinicians in training.

inria.hal.science Copy citation

Detecting Human Bias in Emergency Triage Using LLMs: Literature Review, Preliminary Study, and Experimental Plan

Avalos M, Cohen D, Russon D, Davids M, Dorémus O, Chenais G, Tellier E, Gil-Jardiné C, Lagarde E

FLAIRS-37 · 37(1)

Review and experimental protocol on using language models to surface human bias — gender, age, socioeconomic status — in emergency triage.

doi.org/10.32473/flairs.37.1.135586 Copy citation

AI-Driven Emergency Patient Flow Optimization is Both an Unmissable Opportunity and a Risk of Systematizing Health Disparities

Russon D, Avalos M, Guerra-Adames A, Gil-Jardiné C, Lagarde E

FLAIRS-37

A position piece: optimising patient flow means deciding who waits — and an average gain can hide a loss for particular groups.

doi.org/10.32473/flairs.37 Copy citation

Réflexions pour la conception d’un protocole expérimental de détection des biais dans le triage d’urgence hospitalière à l’aide de modèles de langage

Guerra-Adames A, Avalos M, Cohen D, Russon D, Davids M, Dorémus O, Chenais G, Tellier E, Gil-Jardiné C, Lagarde E

EvalLLM 2024, Toulouse

Designing an experimental protocol for detecting triage bias with language models.

hal.science Copy citation

Health Effects of Wildfires Reported in Emergency Medical Communication Centres: An Ecological Study in Gironde District, France, during the Summer of 2022

Eklöf S, Lagarde E, Tellier E, Russon D, Pradeau C, Laflamme L, Gil-Jardiné C

Preprints.org

Ecological study of emergency medical calls before, during and after the 2022 Gironde wildfires.

doi.org/10.20944/preprints202311.0133.v1 Copy citation