Instructions to use kormilitzin/en_core_med7_trf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- spaCy
How to use kormilitzin/en_core_med7_trf with spaCy:
!pip install https://huggingface.co/kormilitzin/en_core_med7_trf/resolve/main/en_core_med7_trf-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("en_core_med7_trf") # Importing as module. import en_core_med7_trf nlp = en_core_med7_trf.load() - Notebooks
- Google Colab
- Kaggle
| Feature | Description |
|---|---|
| Name | en_core_med7_trf |
| Version | 3.4.2.1 |
| spaCy | >=3.4.2,<3.5.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 514157 keys, 514157 unique vectors (300 dimensions) |
| Sources | n/a |
| License | MIT |
| Author | Andrey Kormilitzin |
Label Scheme
View label scheme (7 labels for 1 components)
| Component | Labels |
|---|---|
ner |
DOSAGE, DRUG, DURATION, FORM, FREQUENCY, ROUTE, STRENGTH |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
90.33 |
ENTS_P |
88.22 |
ENTS_R |
92.54 |
TRANSFORMER_LOSS |
2502627.06 |
NER_LOSS |
114576.77 |
BibTeX entry and citation info
@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}
}
- Downloads last month
- 728
Spaces using kormilitzin/en_core_med7_trf 3
π
abhibisht89/Med7
π
thalpha/kormilitzin-en_core_med7_trf
π»
shreya150804/backend_mediscript
Evaluation results
- NER Precisionself-reported0.882
- NER Recallself-reported0.925
- NER F Scoreself-reported0.903