Cargando…
Zero-shot interpretable phenotyping of postpartum hemorrhage using large language models
Many areas of medicine would benefit from deeper, more accurate phenotyping, but there are limited approaches for phenotyping using clinical notes without substantial annotated data. Large language models (LLMs) have demonstrated immense potential to adapt to novel tasks with no additional training...
Autores principales: | Alsentzer, Emily, Rasmussen, Matthew J., Fontoura, Romy, Cull, Alexis L., Beaulieu-Jones, Brett, Gray, Kathryn J., Bates, David W., Kovacheva, Vesela P. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10689487/ https://www.ncbi.nlm.nih.gov/pubmed/38036723 http://dx.doi.org/10.1038/s41746-023-00957-x |
Ejemplares similares
-
The unreasonable effectiveness of large language models in zero-shot semantic annotation of legal texts
por: Savelka, Jaromir, et al.
Publicado: (2023) -
Detecting Errors with Zero-Shot Learning
por: Wu, Xiaoyu, et al.
Publicado: (2022) -
System alignment supports cross-domain learning and zero-shot generalisation
por: Aho, Kaarina, et al.
Publicado: (2022) -
A fast blind zero-shot denoiser
por: Lequyer, Jason, et al.
Publicado: (2022) -
Zero-shot stance detection: Paradigms and challenges
por: Allaway, Emily, et al.
Publicado: (2023)