Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Clinical named entity recognition in the Portuguese language: a benchmark of modern BERT models and LLMs

Vinicius Anjos de Almeida, Sandro Saorin da Silva, Josimar Chire, Leonardo Vicenzi, Nícolas Henrique Borges, Helena Kociolek, Sarah Miriã de Castro Rocha, Frederico Nassif Gomes, Júlia Cristina Ferreira, Oge Marques, Lucas Emanuel Silva e Oliveira

Abstract

Clinical notes contain valuable unstructured information. Named entity recognition (NER) enables the automatic extraction of medical concepts; however, benchmarks for Portuguese remain scarce. In this study, we aimed to evaluate BERT-based models and large language models (LLMs) for clinical NER in Portuguese and to test strategies for addressing multilabel imbalance. We compared BioBERTpt, BERTimbau, ModernBERT, and mmBERT with LLMs such as GPT-5 and Gemini-2.5, using the public SemClinBr corpus and a private breast cancer dataset. Models were trained under identical conditions and evaluated using precision, recall, and F1-score. Iterative stratification, weighted loss, and oversampling were explored to mitigate class imbalance. The mmBERT-base model achieved the best performance (micro F1 = 0.76), outperforming all other models. Iterative stratification improved class balance and overall performance. Multilingual BERT models, particularly mmBERT, perform strongly for Portuguese clinical NER and can run locally with limited computational resources. Balanced data-splitting strategies further enhance performance.

Clinical named entity recognition in the Portuguese language: a benchmark of modern BERT models and LLMs

Abstract

Clinical notes contain valuable unstructured information. Named entity recognition (NER) enables the automatic extraction of medical concepts; however, benchmarks for Portuguese remain scarce. In this study, we aimed to evaluate BERT-based models and large language models (LLMs) for clinical NER in Portuguese and to test strategies for addressing multilabel imbalance. We compared BioBERTpt, BERTimbau, ModernBERT, and mmBERT with LLMs such as GPT-5 and Gemini-2.5, using the public SemClinBr corpus and a private breast cancer dataset. Models were trained under identical conditions and evaluated using precision, recall, and F1-score. Iterative stratification, weighted loss, and oversampling were explored to mitigate class imbalance. The mmBERT-base model achieved the best performance (micro F1 = 0.76), outperforming all other models. Iterative stratification improved class balance and overall performance. Multilingual BERT models, particularly mmBERT, perform strongly for Portuguese clinical NER and can run locally with limited computational resources. Balanced data-splitting strategies further enhance performance.

Paper Structure

This paper contains 16 sections, 1 figure, 6 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Datasets
  4. SemClinBr
  5. Breast cancer clinical notes
  6. Metrics
  7. Base models
  8. Training setup
  9. Hardware
  10. Results
  11. NER benchmark
  12. Dealing with imbalanced classes
  13. Discussion
  14. Key findings
  15. Strengths and limitations
  16. ...and 1 more sections

Figures (1)

  • Figure 1: Left image: precision-recall curve using random data split. Right image: precision-recall curve using iterative stratification. The iterative stratification results in curves that better approximate the top-right corner of the plot, demonstrating better precision-recall trade-off.