Title | ||
---|---|---|
A contextual multi-task neural approach to medication and adverse events identification from clinical text |
Abstract | ||
---|---|---|
•We design an end-to-end neural model to enhance medication and Adverse Drug Events (ADE) identification.•propose uniting contextual language models and multi-task learning from diverse clinical NER datasets.•We verify the model using two publicly available BERT models (BioClinicalBERT, PubMedBERT) on several real-world datasets (n2c2 2018, n2c2 2009, ADE benchmark corpus).•The proposed method significantly outperformed in the precise recognition of challenging medication entities such as Adverse Drug Events. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.jbi.2021.103960 | Journal of Biomedical Informatics |
Keywords | DocType | Volume |
Medication Extraction,Biomedical Named Entity Recognition,Clinical Decision Support,Multi-task Learning,Pharmacovigilance,Adverse Drug Events | Journal | 125 |
ISSN | Citations | PageRank |
1532-0464 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sankaran Narayanan | 1 | 0 | 1.35 |
Kaivalya Mannam | 2 | 0 | 0.34 |
Pradeep Achan | 3 | 0 | 0.68 |
Ramesh Maneesha | 4 | 63 | 22.44 |
P Venkat Rangan | 5 | 0 | 0.68 |
Sreeranga P Rajan | 6 | 0 | 0.68 |