Université Bourgogne Europe

2 related articles

Subscribe to updates

researchsquare.com Oct 26, 2026
Clinical history-taking stops following a fixed questionnaire: an explicit state picks each question, lifting BERTScore F1 from 0.68 to 0.84
Automated history-taking in telemedicine must collect a structured record over many turns while adapting to what the patient answers. MedAgent-RAG keeps an explicit clinical state of filled slots, a ranked differential diagnosis, questions already asked and red flags detected, selects every question from that state, and grounds its final assessment in clinical guidelines retrieved by a parent–child retrieval-augmented pipeline. Evaluated on the MediTOD corpus with a language-model patient simulator, it raises BERTScore F1 from 0.68 for a single-shot baseline built on the same language model to 0.84, at a cost of 15.8 turns on average.
Automated history-taking in telemedicine must collect a structured record over many turns while adapting to what the patient answers. MedAgent-RAG keeps an explicit clinical state of filled slots, a ranked differential diagnosis, questions already asked and red flags detected, selects every question from that state, and grounds its final assessment in clinical guidelines retrieved by a parent–child retrieval-augmented pipeline. Evaluated on the MediTOD corpus with a language-model patient simulator, it raises BERTScore F1 from 0.68 for a single-shot baseline built on the same language model to 0.84, at a cost of 15.8 turns on average.
Université Bourgogne Europe Centre National de la Recherche Scientifique
Samir Jabbar（First author, Corresponding author）
MedAgent-RAG Clinical History-Taking Retrieval-Augmented Generation Symptom–diagnosis network
arXiv Oct 13, 2026
Influential nodes in complex networks no longer rely on one scale: local, community and global structure learned together, ranking beats centrality and GNN baselines
Influential-node identification in complex networks now has a cross-scale approach. Centrality-based and learning-based methods often integrate structural information across network scales only to a limited degree, so local, community-level and global patterns are not used together. CSBA-Net extracts structural representations at the three scales, models dependencies between them with a BiGRU and multi-head self-attention, and learns node influence scores by regression against SIR diffusion simulations; on 24 real and 12 synthetic networks its ranking metrics exceed the compared centrality, CNN and GNN baselines.
Influential-node identification in complex networks now has a cross-scale approach. Centrality-based and learning-based methods often integrate structural information across network scales only to a limited degree, so local, community-level and global patterns are not used together. CSBA-Net extracts structural representations at the three scales, models dependencies between them with a BiGRU and multi-head self-attention, and learns node influence scores by regression against SIR diffusion simulations; on 24 real and 12 synthetic networks its ranking metrics exceed the compared centrality, CNN and GNN baselines.
Université Bourgogne Europe Centre Universitaire de Mila
Rihab Boukheche（First author）
CSBA-Net Multi-scale structural representation learning Influential node identification

You’re all caught up

Clinical history-taking stops following a fixed questionnaire: an explicit state picks each question, lifting BERTScore F1 from 0.68 to 0.84

Influential nodes in complex networks no longer rely on one scale: local, community and global structure learned together, ranking beats centrality and GNN baselines