NER of medications

This model aims to demonstrate an extraction of entities from from medical texts. It gets the name of the doctor, his registration code (CRM), the substance and the dose prescribed in Pt_BR.

Model Description

• Developed by: [Nilton Seixas]
• Language(s) (NLP): [Brazilian portuguese]
• License: [More Information Needed]
• Finetuned from model [optional]: [neuralmind/bert-large-portuguese-cased]

Model Sources [optional]

• Repository: [niltonseixas/NER]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

from transformers import AutoTokenizer, AutoModelForTokenClassification

from transformers import pipeline

tokenizer = AutoTokenizer.from_pretrained("niltonseixas/NER_tokenizer")

model = AutoModelForTokenClassification.from_pretrained("niltonseixas/NER")

nlp = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy = "average")

example = "dra. Nayara Barbosa, CRM 12345 receitou Amoxilina 50 mg"

ner_results = nlp(example)

print(ner_results)