Contextual word embeddings and the Transformers architecture have reached state-of-the-art results in many natural language processing (NLP) tasks and improved the adaptation of models for multiple domains. Despite the improvement in the reuse and construction of models, few resources are still developed for the Portuguese language, especially in the health domain. Furthermore, the clinical models available for the language are not representative enough for all medical specialties. This work explores deep contextual embedding models for the Portuguese language to support clinical NLP tasks. We transferred learned information from electronic health records of a Brazilian tertiary hospital specialized in cardiology diseases and pre-trained multiple clinical BERT-based models. We evaluated the performance of these models in named entity recognition experiments, fine-tuning them in two annotated corpora containing clinical narratives. Our pre-trained models outperformed previous multilingual and Portuguese BERT-based models for cardiology and multi-specialty environments, reaching the state-of-the-art for analyzed corpora, with 5.5% F1 score improvement in TempClinBr (all entities) and 1.7% in SemClinBr (Disorder entity) corpora. Hence, we demonstrate that data representativeness and a high volume of training data can improve the results for clinical tasks, aligned with results for other languages.
OBJECTIVE: Identify nurses' knowledge about preventing bronchoaspiration in patients undergoing Enteral Nutrition Therapy in a hospital, considering the main procedures addressed in the institutional protocol and the guidelines of the Brazilian Society of Parenteral and Enteral Nutrition (Sociedade Brasileira de Nutrição Parenteral e Enteral – BRASPEN). METHOD: A descriptive cross-sectional study was conducted at a hospital in Campos Gerais in 2025. Staff nurses with more than two months of experience were included. A self-developed structured questionnaire on prevention of bronchoaspiration in enteral nutrition therapy was used regarding the prevention of bronchoaspiration in enteral nutrition therapy, with participants selected based on convenience. Descriptive statistical analysis was performed. RESULTS: 69 professionals participated in the survey, with 75% correct answers to questions related to "catheter confirmation testing" and "monitoring and care of patients receiving enteral nutrition." However, discrepancies were identified regarding the technologies used to confirm catheter position, monitor catheter height marking, and manage stasis, highlighting the need for updated information on these practices. CONCLUSION: Most participants had a satisfying knowledge about nursing care to prevention of bronchoaspiration. However, for a safe, standardized and updated practice, it is essential to follow protocols based on the highest scientific evidence, and to participate in continuous training aimed at improving their skills and knowledge.