A survey of automated methods for biomedical text simplification

Abstract

Objective Plain language in medicine has long been advocated as a way to improve patient understanding and engagement. As the field of Natural Language Processing has progressed, increasingly sophisticated methods have been explored for the automatic simplification of existing biomedical text for consumers. We survey the literature in this area with the goals of characterizing approaches and applications, summarizing existing resources, and identifying remaining challenges. Materials and Methods We search English language literature using lists of synonyms for both the task (eg, “text simplification”) and the domain (eg, “biomedical”), and searching for all pairs of these synonyms using Google Scholar, Semantic Scholar, PubMed, ACL Anthology, and DBLP. We expand search terms based on results and further include any pertinent papers not in the search results but cited by those that are. Results We find 45 papers that we deem relevant to the automatic simplification of biomedical text, with data spanning 7 natural languages. Of these (nonexclusively), 32 describe tools or methods, 13 present data sets or resources, and 9 describe impacts on human comprehension. Of the tools or methods, 22 are chiefly procedural and 10 are chiefly neural. Conclusions Though neural methods hold promise for this task, scarcity of parallel data has led to continued development of procedural methods. Various low-resource mitigations have been proposed to advance neural methods, including paragraph-level and unsupervised models and augmentation of neural models with procedural elements drawing from knowledge bases. However, high-quality parallel data will likely be crucial for developing fully automated biomedical text simplification.

Expanding Interdisciplinarity: A bibliometric study of medical education using the MEJ-24

“…For example, the citing of business, economics and management journals may provide evidence of the increasing complexity of healthcare systems and medical education researchers’ efforts to inform education with topics like leadership [23, 24] and healthcare cost consciousness [25, 26]. Additionally, the inclusion of linguistics may be a nod towards the rise in electronic medical records and the novel language analysis methods used to mine them [27, 28].…”

Expanding Interdisciplinarity: A Bibliometric Study of Medical Education Using the Medical Education Journal List-24 (MEJ-24)

“…For example, the citing of business, economics and management journals may provide evidence of the increasing complexity of healthcare systems and medical education researchers’ efforts to inform education with topics like leadership [ 28 29 ] and healthcare cost consciousness [ 30 31 ]. Additionally, the inclusion of linguistics may be a nod towards the rise in electronic medical records and the novel language analysis methods used to mine them [ 32 33 ]. When considering the top 10 categories, which represented the majority of citations, it is notable that the categories of Education and Educational Research, Surgery, and Nursing were increasingly cited in the more recent years (e.g., between 2016–2020).…”

Multiple Automated Health Literacy Assessments of Written Health Information: Development of the SHeLL (Sydney Health Literacy Lab) Health Literacy Editor v1

“…As another example, the value of the thesaurus function is largely driven by the number, quality, and relevance of the thesaurus entries. This could be further enhanced by leveraging large existing (manually developed) medical dictionaries and by incorporating machine learning methods that have "mined" pairs of jargon and lay terms using multiple corpora [17,[58][59][60]. The uncommon language feature may be further improved by using the "SciSpaCy" variant that has been adapted to biomedical texts, as this may result in improved identification of medically named entities.…”

“…With recent advances in computer science, web-based software may be able to address this issue. For example, Ondov and colleagues [ 17 ] recently identified 45 papers investigating simplification for biomedical texts, including 32 tools or methods. Of these, 22 tools took a procedural (rules-based) approach; 10 primarily used a machine learning approach, that is, through natural language processing.…”