Deep Learning Transformer Models for Building a Comprehensive and Real-time Trauma Observatory: Development and Validation Study
| dc.rights.license | open | en_US |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | CHENAIS, Gabrielle | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | GIL-JARDINE, Cedric
ORCID: 0000-0001-5329-6405 IDREF: 159039223 | |
| hal.structure.identifier | Statistics In System biology and Translational Medicine [SISTM] | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | TOUCHAIS, Helene | |
| hal.structure.identifier | Statistics In System biology and Translational Medicine [SISTM] | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | AVALOS FERNANDEZ, Marta | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | CONTRAND, Benjamin | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | TELLIER, Eric | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | COMBES, Xavier | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | BOURDOIS, Loick | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | REVEL, Philippe | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | LAGARDE, Emmanuel | |
| dc.date.accessioned | 2023-03-07T16:12:17Z | |
| dc.date.available | 2023-03-07T16:12:17Z | |
| dc.date.issued | 2023-01-12 | |
| dc.identifier.issn | 2817-1705 | en_US |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/172204 | |
| dc.description.abstractEn | 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. | |
| dc.language.iso | EN | en_US |
| dc.rights | Attribution 3.0 United States | * |
| dc.rights.uri | http://creativecommons.org/licenses/by/3.0/us/ | * |
| dc.subject.en | Deep learning | |
| dc.subject.en | Public health | |
| dc.subject.en | Trauma | |
| dc.subject.en | Emergencies | |
| dc.subject.en | Natural language processing | |
| dc.subject.en | Transformers | |
| dc.title.en | Deep Learning Transformer Models for Building a Comprehensive and Real-time Trauma Observatory: Development and Validation Study | |
| dc.type | Article de revue | en_US |
| dc.identifier.doi | 10.2196/40843 | en_US |
| dc.subject.hal | Sciences du Vivant [q-bio]/Santé publique et épidémiologie | en_US |
| bordeaux.journal | JMIR AI | en_US |
| bordeaux.page | e40843 | en_US |
| bordeaux.volume | 2 | en_US |
| bordeaux.hal.laboratories | Bordeaux Population Health Research Center (BPH) - UMR 1219 | en_US |
| bordeaux.issue | 1 | en_US |
| bordeaux.institution | Université de Bordeaux | en_US |
| bordeaux.institution | INSERM | en_US |
| bordeaux.team | AHEAD_BPH | en_US |
| bordeaux.team | SISTM_BPH | en_US |
| bordeaux.peerReviewed | oui | en_US |
| bordeaux.inpress | non | en_US |
| hal.export | false | |
| dc.rights.cc | Pas de Licence CC | en_US |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=JMIR%20AI&rft.date=2023-01-12&rft.volume=2&rft.issue=1&rft.spage=e40843&rft.epage=e40843&rft.eissn=2817-1705&rft.issn=2817-1705&rft.au=CHENAIS,%20Gabrielle&GIL-JARDINE,%20Cedric&TOUCHAIS,%20Helene&AVALOS%20FERNANDEZ,%20Marta&CONTRAND,%20Benjamin&rft.genre=article |
