New Details

🏥 Identifying biomedical named entities from clinical narratives has a great interest in the scientific community due to its importance in treatment improvements, drug development research, and patient record analysis.

💪 Traditional approaches often focus on recognizing a single entity type (such as chemicals), yet recent advancements emphasize the necessity of addressing multi-class scenarios.

🧠 We present a multi-head neural network model for multi-class entity recognition in Spanish clinical documents.

💡 By combining four diverse datasets, SympTEMIST, MedProcNER, DisTEMIST, and PharmaCoNER, we expand the scope of entity recognition to encompass five classes: symptoms, medical procedures, diseases, chemicals, and proteins.

Authored by:
– Richard A. A. Jonker
– Tiago Almeida
– Rui Antunes
– João R. Almeida
– Sérgio Matos

Publication’s DOI:
https://doi.org/10.1093/database/baae068

GitHub repository:
https://github.com/ieeta-pt/Multi-Head-CRF

Supported by:
– IEETA, Institute of Electronics and Informatics Engineering of Aveiro.
– FCT, Foundation for Science and Technology. This work was funded in the context of the projects DSAIPA/AI/0088/2020 and UIDB/00127/2020 (https://doi.org/10.54499/UIDB/00127/2020), and the grants 2020.05784.BD (https://doi.org/10.54499/2020.05784.BD) and PRT/BD/154792/2023.

#BiomedicalNLP #SpanishClinicalText #NamedEntityRecognition #BiomedicalInformationExtraction