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

arXiv: https://arxiv.org/abs/2603.26510 · HTML: https://mlsanity.com/paper/2603.26510/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [A Network Perspective on Stratification of Multi-Label Data](https://mlsanity.com/paper/1704.08756/) (2017)
- [SemClinBr -- a multi institutional and multi specialty semantically annotated corpus for Portuguese clinical NLP tasks](https://mlsanity.com/paper/2001.10071/) (2020)
- [Evaluating Named Entity Recognition: A comparative analysis of mono- and multilingual transformer models on a novel Brazilian corporate earnings call transcripts dataset](https://mlsanity.com/paper/2403.12212/) (2024)
- [Multilingual Clinical NER for Diseases and Medications Recognition in Cardiology Texts using BERT Embeddings](https://mlsanity.com/paper/2510.17437/) (2025)

## Abstract (arXiv)

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.