From Annotated Clinical Narratives to Ontology: Structuring Brazilian Portuguese Clinical Data

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Health & Medical Research · Depth: Intermediate, quick

Summary

A new lightweight domain ontology has been developed to structure Brazilian Portuguese clinical data, addressing the current limitations in clinical Natural Language Processing (NLP) for the language. Existing corpora, while providing annotated clinical narratives, suffer from flat annotation schemes that hinder semantic expressiveness and alignment with standardized terminologies. This ontology models clinical entities, contextual qualifiers, and semantic relations within Brazilian Portuguese texts. It is derived from original corpus annotations and conceptually aligned with established standards to improve interoperability, while simultaneously preserving the specific semantics of the corpus. This development provides foundational infrastructure for Portuguese clinical NLP, facilitating tasks like entity normalization, semantic search, and ontology-guided annotation.

Key takeaway

For NLP engineers and research scientists working with Brazilian Portuguese clinical data, this ontology offers a critical resource for overcoming current semantic limitations. Your projects can benefit from enhanced interoperability and more expressive data structures, directly supporting tasks like entity normalization and semantic search. Consider integrating this ontology to improve the accuracy and utility of your clinical NLP applications.

Key insights

A new ontology structures Brazilian Portuguese clinical narratives, enhancing NLP interoperability and semantic expressiveness.

Principles

• Ontologies improve clinical NLP.
• Align with standards for interoperability.

Method

The method involves deriving a lightweight domain ontology from existing corpus annotations and aligning it conceptually with standardized terminologies to model clinical entities, qualifiers, and relations.

In practice

• Use for entity normalization.
• Enable semantic search.
• Support ontology-guided annotation.

Topics

• Brazilian Portuguese
• Clinical NLP
• Domain Ontology
• Clinical Narratives
• Semantic Relations

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Toten: Knowledge-Based Ontological Tokenization Of Physical Quantities And Technical Notation In Brazilian Portuguese — TOTEN offers knowledge-based ontological tokenization for technical text, preserving semantic structure of physical quantities and notation in Brazilian Portuguese.
• A Dataset of Brazilian Portuguese Clinical Notes for Anaphylaxis Detection — A new Brazilian Portuguese clinical note dataset enables NLP-driven anaphylaxis detection for research and health record analysis.
• KliniskVestBERT: BERT Model Specialised to Norwegian Clinical Texts — Domain-specific pre-training significantly enhances BERT models for Norwegian clinical NLP tasks.
• Lexicon-Grammar Web — A web-based interface provides interactive access to a large-scale European Portuguese grammatical database.
• EDEN: A Large-Scale Corpus of Clinical Notes for Italian — EDEN provides the largest Italian clinical note corpus and a CRF-filling benchmark for LLM-based information extraction.
• Predicting relations between SOAP note sections: The value of incorporating a clinical information model — Fine-tuning a RoBERTa-base model on manually annotated clinical data improves NER for SOAP note sections.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.