Deep Learning Transformer Models for Building a Comprehensive and Real-time Trauma Observatory: Development and Validation Study

Abstract

Background: Public health surveillance relies on the collection of data, often in near-real time. Recent advances in natural language processing make it possible to envisage an automated system for extracting information from electronic health records.

Objective: To study the feasibility of setting up a national trauma observatory in France, we compared the performance of several automatic language processing methods in a multiclass classification task of unstructured clinical notes.

Methods: A total of 69,110 free-text clinical notes related to visits to the emergency departments of the University Hospital of Bordeaux, France, between 2012 and 2019 were manually annotated. Among these clinical notes, 32.5% (22,481/69,110) were traumas. We trained 4 transformer models (deep learning models that encompass attention mechanism) and compared them with the term frequency-inverse document frequency associated with the support vector machine method.

Results: The transformer models consistently performed better than the term frequency-inverse document frequency and a support vector machine. Among the transformers, the GPTanam model pretrained with a French corpus with an additional autosupervised learning step on 306,368 unlabeled clinical notes showed the best performance with a micro F₁-score of 0.969.

Conclusions: The transformers proved efficient at the multiclass classification of narrative and medical data. Further steps for improvement should focus on the expansion of abbreviations and multioutput multiclass classification.

Keywords: deep learning; emergencies; natural language processing; public health; transformers; trauma.

Figure 1

F1-score curves for CamemBERT, FlauBERT, BelGPT2 and GPTanam on the validation dataset.

Figure 2

Plot of micro F1-scores of all models for each class for both the complete test data set (blue bars) and the test data set without potentially ambiguous content as regard to its classification (pink bars). TF-IDF: term frequency–inverse document frequency.