With the growing number of electronic health record data, clinical NLP tasks have become increasingly relevant to unlock valuable information from unstructured clinical text. Although the performance of downstream NLP tasks, such as named-entity recognition (NER), in English corpus has recently improved by contextualised language models, less research is available for clinical texts in low resource languages. Our goal is to assess a deep contextual embedding model for Portuguese, so called BioBERTpt, to support clinical and biomedical NER. We transfer learned information encoded in a multilingual-BERT model to a corpora of clinical narratives and biomedical-scientific papers in Brazilian Portuguese. To evaluate the performance of BioBERTpt, we ran NER experiments on two annotated corpora containing clinical narratives and compared the results with existing BERT models. Our in-domain model outperformed the baseline model in F1-score by 2.72%, achieving higher performance in 11 out of 13 assessed entities. We demonstrate that enriching contextual embedding models with domain literature can play an important role in improving performance for specific NLP tasks. The transfer learning process enhanced the Portuguese biomedical NER model by reducing the necessity of labeled data and the demand for retraining a whole new model.

Automatic detection of negated content is often a prerequisite in information extraction systems in various domains. In the biomedical domain especially, this task is important because negation plays an important role. In this work, two main contributions are proposed. First, we work with languages which have been poorly addressed up to now: Brazilian Portuguese and French. Thus, we developed new corpora for these two languages which have been manually annotated for marking up the negation cues and their scope. Second, we propose automatic methods based on supervised machine learning approaches for the automatic detection of negation marks and of their scopes. The methods show to be robust in both languages (Brazilian Portuguese and French) and in cross-domain (general and biomedical languages) contexts. The approach is also validated on English data from the state of the art: it yields very good results and outperforms other existing approaches. Besides, the application is accessible and usable online. We assume that, through these issues (new annotated corpora, application accessible online, and cross-domain robustness), the reproducibility of the results and the robustness of the NLP applications will be augmented.

Unstructured data in electronic health records, represented by clinical texts, are a vast source of healthcare information because they describe a patient's journey, including clinical findings, procedures, and information about the continuity of care. The publication of several studies on temporal relation extraction from clinical texts during the last decade and the realization of multiple shared tasks highlight the importance of this research theme. Therefore, we propose a review of temporal relation extraction in clinical texts. We analyzed 105 articles and verified that relations between events and document creation time, a coarse temporality type, were addressed with traditional machine learning–based models with few recent initiatives to push the state-of-the-art with deep learning–based models. For temporal relations between entities (event and temporal expressions) in the document, factors such as dataset imbalance because of candidate pair generation and task complexity directly affect the system's performance. The state-of-the-art resides on attention-based models, with contextualized word representations being fine-tuned for temporal relation extraction. However, further experiments and advances in the research topic are required until real-time clinical domain applications are released. Furthermore, most of the publications mainly reside on the same dataset, hindering the need for new annotation projects that provide datasets for different medical specialties, clinical text types, and even languages.

Objective: to reflect on the use of computational tools in the cross-mapping method between clinical terminologies. Method: reflection study. Results: the cross-mapping method consists of obtaining a list of terms through extraction and normalization; the connection between the terms of the list and those of the reference base, by means of predefined rules; and grouping of the terms into categories: exact or partial combination or, in more detail, similar term, more comprehensive term, more restricted term and non-agreeing term. Performed manually in many studies, it can be automated with the use of the Unified Medical Language System (UMLS). Obtaining the terms list can occur automatically by natural language processing algorithms, being that the use of rules to identify information in texts allows the expert's knowledge to be coupled to the algorithm, and it can be performed by techniques based on Machine Learning. When it comes to mapping terms using the 7-Axis model of the International Classification for Nursing Practice (ICNP®), the process can also be automated through natural language processing algorithms such as POS-tagger and the syntactic parser. Conclusion: the cross-mapping method can be intensified by the use of natural language processing algorithms. However, even in cases of automatic mapping, the validation of the results by specialists should not be discarded.

Considering the difficulties of extracting entities from Electronic Health Records (EHR) texts in Portuguese, we explore the Conditional Random Fields (CRF) algorithm to build a Named Entity Recognition (NER) system based on a corpus of clinical Portuguese data annotated by experts. We acquaint the challenges and methods to classify Abbreviations, Disorders, Procedures and Chemicals within the texts. By selecting a meaningful set of features, and parameters with the best performance the results demonstrate that the method is promising and may support other biomedical tasks, nonetheless, further experiments with more features, different architectures and sophisticated preprocessing steps are needed.