Terminologies augmented recurrent neural network model for clinical named entity recognition

https://doi.org/10.1016/j.jbi.2019.103356Get rights and content
Under an Elsevier user license
open archive

Highlights

  • We have built APcNER, a French corpus for clinical named-entity recognition.

  • It includes a large variety of document types, and required 28 hours of annotation.

  • We achieved on average 84% non-exact F-measure on five types of clinical entities.

  • We give insight into the complementarity of terminology with a supervised model.

Abstract

Objective

We aimed to enhance the performance of a supervised model for clinical named-entity recognition (NER) using medical terminologies. In order to evaluate our system in French, we built a corpus for 5 types of clinical entities.

Methods

We used a terminology-based system as baseline, built upon UMLS and SNOMED. Then, we evaluated a biGRU-CRF, and a hybrid system using the prediction of the terminology-based system as feature for the biGRU-CRF. In French, we built APcNER, a corpus of 147 documents annotated for 5 entities (Drug names, Signs or symptoms, Diseases or disorders, Diagnostic procedures or lab tests and Therapeutic procedures). We evaluated each NER systems using exact and partial match definition of F-measure for NER. The APcNER contains 4,837 entities, which took 28 h to annotate. The inter-annotator agreement as measured by Cohen’s Kappa was substantial for non-exact match (Κ = 0.61) and moderate considering exact match (Κ = 0.42). In English, we evaluated the NER systems on the i2b2-2009 Medication Challenge for Drug name recognition, which contained 8,573 entities for 268 documents, and i2b2-small a version reduced to match APcNER number of entities.

Results

For drug name recognition on both i2b2-2009 and APcNER, the biGRU-CRF performed better that the terminology-based system, with an exact-match F-measure of 91.1% versus 73% and 81.9% versus 75% respectively. For i2b2-small and APcNER, the hybrid system outperformed the biGRU-CRF, with an exact-match F-measure of 87.8% versus 85.6% and 86.4% versus 81.9% respectively. On APcNER corpus, the micro-average F-measure of the hybrid system on the 5 entities was 69.5% in exact match and 84.1% in non-exact match.

Conclusion

APcNER is a French corpus for clinical-NER of five types of entities which covers a large variety of document types. The extension of the supervised model with terminology has allowed an easy increase in performance, especially for rare entities, and established near state of the art results on the i2b2-2009 corpus.

Keywords

Clinical natural language processing
Named entity recognition
Information extraction
Machine learning
APcNER

Abbreviations

NER
named entity recognition
biGRU-CRF
bidirectional - Gated Recurrent Unit - Conditional Random Field
AP-HP
Assistance Publique - Hôpitaux de Paris
IOB
inside outside beginning
ATC
Anatomical Therapeutic Chemical Classification System
BPDM
Base publique du médicament
CCAM
Classification commune des actes médicaux
CIM-10
Classification internationale des maladies
DRC
Dictionnaire des Resultats de Consultation
SNOMED
Systematized Nomenclature of Medicine Clinical Terms

Cited by (0)