Abbreviation Identification and Disambiguation in Real-World Clinical Narratives

The use of non-standardized and context-dependent abbreviations in clinical narratives introduces critical challenges for natural language processing models, limiting the accuracy of information extraction, affecting semantic interpretation, and posing risks to clinical decision-making and patient safety. This paper presents a solution to identify and expand abbreviations in Brazilian Portuguese clinical narratives, dealing with a critical challenge in the interpretation of medical texts. The method, which uses the SemClinBr dataset of 1,000 anonymous real-world clinical texts and a low-resource approach that combines the GPT model, prompt engineering and few-shot learning techniques, achieved a success rate of 83.2 % in identification and 93.04 % in correct expansion. Despite the inherent challenges of real-world data and manual evaluation, the results, which are comparable to established international benchmarks, highlight the potential of large language models (LLMs) to provide efficient comprehension of medical documents, especially for languages with limited data.