pmaitra/en_biobert_ner_symptom

Fine-tuned BioBERT based NER model for detecting medical symptoms from clinical notes.

Feature	Description
Name	en_biobert_ner_symptom
Version	1.0.0
spaCy	>=3.5.1,<3.6.0
Default Pipeline	transformer, ner
Components	transformer, ner
Vectors	0 keys, 0 unique vectors (0 dimensions)
Sources	n/a
License	MIT
Author	Sena Chae, Pratik Maitra, Padmini Srinivasan

Model Description

The model was trained on a combined maccrobat and i2c2 dataset and is based on biobert. If you use this model kindly cite the paper below:

Uncovering Hidden Symptom Clusters in Patients with Acute Myeloid Leukemia using Natural Language Processing - Sena Chae, Jaewon Bae , Pratik Matira, Karen Dunn Lopez, Barbara Rakel

Model Usage

The model can be loaded using spacy after installing the model.

!pip install https://huggingface.co/pmaitra/en_biobert_ner_symptom/resolve/main/en_biobert_ner_symptom-any-py3-none-any.whl

A sample use-case is presented below:

import spacy
nlp = spacy.load("en_biobert_ner_symptom")

doc = nlp("He complained of dizziness and nausea during the Iowa trip.")

for ent in doc.ents:
  print(ent)

Accuracy

Type	Score
ENTS_F	99.96
ENTS_P	99.97
ENTS_R	99.94
TRANSFORMER_LOSS	20456.83
NER_LOSS	38920.06