Modelpublic

kormilitzin/en_core_spancat_med7_lg

sourceHugging Facemitupdated 4y agoView on Hugging Face

1likes3downloads

Model Card

Feature	Description
Name	`en_core_spancat_med7_lg`
Version	`3.4.2.1`
spaCy	`>=3.4.2,<3.5.0`
Default Pipeline	`tok2vec`, `spancat`
Components	`tok2vec`, `spancat`
Vectors	514157 keys, 514157 unique vectors (300 dimensions)
Sources	n/a
License	`MIT`
Author	Andrey Kormilitzin

Label Scheme

<summary>View label scheme (8 labels for 1 components)</summary>

Component	Labels
`spancat`	`DOSAGE`, `MEDINFO`, `DRUG`, `STRENGTH`, `FREQUENCY`, `ROUTE`, `DURATION`, `FORM`

</details>

Accuracy

Type	Score
`SPANS_SC_F`	85.21
`SPANS_SC_P`	91.52
`SPANS_SC_R`	79.71
`TOK2VEC_LOSS`	260.85
`SPANCAT_LOSS`	282817.13

BibTeX entry and citation info

bibtex

@article{kormilitzin2021med7,
  title={Med7: A transferable clinical natural language processing model for electronic health records},
  author={Kormilitzin, Andrey and Vaci, Nemanja and Liu, Qiang and Nevado-Holgado, Alejo},
  journal={Artificial Intelligence in Medicine},
  volume={118},
  pages={102086},
  year={2021},
  publisher={Elsevier}
}