Clinical Errors From Acronym Use in Electronic Health Record: A Review of NLP-Based Disambiguation Techniques

The adoption of Electronic Health Record (EHR) and other e-health infrastructures over the years has been characterized by an increase in medical errors. This is primarily a result widespread usage acronyms abbreviations with multiple possible senses (i.e., ambiguous acronyms). advent Artificial Intelligence (AI) technology, specifically Natural Language Processing (NLP), presented promising avenue for tackling intricate issue automatic sense resolution acronyms. Notably, application Machine Learning (ML) techniques proven to be highly effective development systems aimed at this objective, garnering significant attention interest within research industry domains recent years. significance automating acronym cannot overstated, especially context modern healthcare delivery use EHR. However, it disheartening note that comprehensive studies examining global EHR, assessing impact on errors EHR systems, reporting latest trends advancements ML-based NLP solutions disambiguating remain severely limited. In current study, we present detailed overview error, its origins, unintended effects, EHR-related as subclass clinical error. Furthermore, paper investigates developed developing nations, well review concludes examination various artificial intelligence techniques, particularly machine learning algorithms abbreviation disambiguation EHRs.