Rule-Based Natural Language Processing Pipeline to Detect Medication-Related Named Entities: Insights for Transfer Learning.
Stud Health Technol Inform
; 310: 584-588, 2024 Jan 25.
Article
en En
| MEDLINE
| ID: mdl-38269876
ABSTRACT
We document the procedure and performance of a rule-based NLP system that, using transfer learning, automatically extracts essential named entities related to drug errors from Japanese free-text incident reports. Subsequently, we used the rule-based annotated data to fine-tune a pre-trained BERT model and examined the performance of medication-related incident report prediction. The rule-based pipeline achieved a macro-F1-score of 0.81 in an internal dataset and the BERT model fine-tuned with rule-annotated data achieved a macro-F1-score of 0.97 and 0.75 for named entity recognition and relation extraction tasks, respectively. The model can be deployed to other, similar problems in medication-related clinical texts.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Lenguaje Natural
/
Aprendizaje
Tipo de estudio:
Prognostic_studies
Límite:
Humans
Idioma:
En
Revista:
Stud Health Technol Inform
/
Stud. health technol. inform.
/
Studies in health technology and informatics (Online)
Asunto de la revista:
INFORMATICA MEDICA
/
PESQUISA EM SERVICOS DE SAUDE
Año:
2024
Tipo del documento:
Article
País de afiliación:
Japón