README.md

metadata

license: apache-2.0
datasets:
  - rigonsallauka/portugese_ner_dataset
language:
  - pt
metrics:
  - f1
  - precision
  - recall
  - confusion_matrix
base_model:
  - google-bert/bert-base-cased
pipeline_tag: token-classification
tags:
  - NER
  - medical
  - symptoms
  - extraction
  - portugese

Portugese Medical NER

Use

• Primary Use Case: This model is designed to extract medical entities such as symptoms, diagnostic tests, and treatments from clinical text in the Portugese language.
• Applications: Suitable for healthcare professionals, clinical data analysis, and research into medical text processing.
• Supported Entity Types:
  • PROBLEM: Diseases, symptoms, and medical conditions.
  • TEST: Diagnostic procedures and laboratory tests.
  • TREATMENT: Medications, therapies, and other medical interventions.

Training Data

• Data Sources: Annotated datasets, including clinical data and translations of English medical text into Portugese.
• Data Augmentation: The training dataset underwent data augmentation techniques to improve the model's ability to generalize to different text structures.
• Dataset Split:
  • Training Set: 80%
  • Validation Set: 10%
  • Test Set: 10%

Model Training

• Training Configuration:
  • Optimizer: AdamW
  • Learning Rate: 3e-5
  • Batch Size: 64
  • Epochs: 200
  • Loss Function: Focal Loss to handle class imbalance
• Frameworks: PyTorch, Hugging Face Transformers, SimpleTransformers

Evaluation metrics

• eval_loss = 0.34290624315439794
• f1_score = 0.7720704622812219
• precision = 0.7724936121316581
• recall = 0.7716477757556993

How to Use

You can easily use this model with the Hugging Face transformers library. Here's an example of how to load and use the model for inference:

from transformers import AutoTokenizer, AutoModelForTokenClassification
import torch

model_name = "rigonsallauka/portugese_medical_ner"

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Sample text for inference
text = "O paciente reclamou de fortes dores de cabeça e náusea que persistiram por dois dias. Para aliviar os sintomas, foi prescrito paracetamol e recomendado descansar e beber bastante líquidos."

# Tokenize the input text
inputs = tokenizer(text, return_tensors="pt")