Authors:
Émilien Arnaud
1
;
Mahmoud Elbattah
2
;
3
;
Maxime Gignon
1
and
Gilles Dequen
3
Affiliations:
1
Emergency Department, Amiens-Picardy University, Amiens, France
;
2
Faculty of Environment and Technology, University of the West of England, Bristol, U.K.
;
3
Laboratoire MIS, Université de Picardie Jules Verne, Amiens, France
Keyword(s):
Natural Language Processing, BERT, Transformers, Clustering, Healthcare Analytics.
Abstract:
The advent of transformer models has allowed for tremendous progress in the Natural Language Processing (NLP) domain. Pretrained transformers could successfully deliver the state-of-the-art performance in a myriad of NLP tasks. This study presents an application of transformers to learn contextual embeddings from free-text triage notes, widely recorded at the emergency department. A large-scale retrospective cohort of triage notes of more than 260K records was provided by the University Hospital of Amiens-Picardy in France. We utilize a set of Bidirectional Encoder Representations from Transformers (BERT) for the French language. The quality of embeddings is empirically examined based on a set of clustering models. In this regard, we provide a comparative analysis of popular models including CamemBERT, FlauBERT, and mBART. The study could be generally regarded as an addition to the ongoing contributions of applying the BERT approach in the healthcare context.