Medical language – a unique linguistic phenomenon

Džuganová, Božena

doi:10.21860/j.10.1.7

Cited by 9 publications

(2 citation statements)

References 12 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Namely, medical records differ considerably in their language usage. They contain a magnitude of medical terms: e.g., symptoms, names of diseases and treatments, devices, and instruments [ 7 ], which occur only seldom in books, news articles and on the web (which are frequently used for training NLP models). Furthermore, the records are often written in a time-efficient manner, resulting in—amongst others—unintentional grammatical and spelling mistakes, and intentionally omitting function words and using domain-specific abbreviations.…”

Section: Introductionmentioning

confidence: 99%

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

et al. 2023

View full text Add to dashboard Cite

Understanding the diagnostic goal of medical reports is valuable information for understanding patient flows. This work focuses on extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring. We investigate the performance of domain-dependent and general state-of-the-art language models and their alignment with domain expertise. To this end, eXplainable Artificial Intelligence (XAI) techniques are used to acquire insight into the inner workings of the model, which are verified on their trustworthiness. The verified XAI explanations are then compared with explanations from a domain expert, to indirectly determine the reliability of the model. BERTje, a Dutch Bidirectional Encoder Representations from Transformers (BERT) model, outperforms RobBERT and MedRoBERTa.nl in both accuracy and reliability. The latter model (MedRoBERTa.nl) is a domain-specific model, while BERTje is a generic model, showing that domain-specific models are not always superior. Our validation of BERTje in a small prospective study shows promising results for the potential uptake of the model in a practical setting.

show abstract

Section: Introductionmentioning

confidence: 99%

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Many mistakes come not only from the lack of lexical or grammatical knowledge but are made due to misunderstanding of speech produced by native speakers in an authentic situation. Moreover, a huge amount of new information in the field of Medicine requires active participation in the international conferences (Antić, 2009;Milosavljević, 2008;Mićić, 2013;Džuganová, 2019). Put in other words, good listening skills in English for Medical Purposes (EMP) improve understanding as well as increase communicative competence of every learner.…”

Section: Introductionmentioning

confidence: 99%

Teaching Medical English through Professional Captioning Videos

Džuganová

2019

Journal of Language and Cultural Education

Self Cite

View full text Add to dashboard Cite

Since the Barcelona objective released on 16 March 2002, European Union met an ambitious goal: to promote learning of “at least two foreign languages from an early age” (European Commission 2019). Thus, bilingualism, multilingualism, and linguistic diversity became a part of European policy (Pokrivčáková 2013a; Pokrivčáková 2013b; Schunz 2012). Nevertheless, English language is still considered to be the global language, used as lingua franca. English is the language of international dialogue facilitating further educational and professional development, it is the language of international communication, science, academia, and the Internet (Dearden 2014). English is the first foreign language taught in Slovakia, and therefore majority of Slovak medical students chose the course of Medical English during their study. To develop communicative competence and performance in students, it is necessary to offer a very wide range of stimulating activities in English classes. Videos published on the Internet offer enormous potential for foreign or second language (L2) acquisition at every level according to Common European Framework of Reference for Languages (CEFR) in almost all learning phases, covering a significant variety of authentic topics (Barnau, Džuganová, Malinovská 2018). Our study is particularly aimed at watching of YouTube professional medical videos with/without captions and their effect on English language skills, especially listening comprehension in medical students at Jessenius Faculty of Medicine in Martin, Comenius University in Bratislava, Slovakia (JFM UC).

show abstract

Linguistic and semantic characteristics of articles and peer review reports in Social Sciences and Medical and Health Sciences: analysis of articles published in Open Research Central

et al. 2023

View full text Add to dashboard Cite

We aimed to examine the differences in articles, peer review and editorial processes in Medical and Health Sciences vs. Social Sciences. Our data source was Open Research Central (ORC) portal, which hosts several journal platforms for post-publication peer review, allowing the analysis of articles from their submission, regardless of the publishing outcome. The study sample included 51 research articles that had Social Sciences tag only and 361 research articles with Medical and Health Sciences tag only. Levenshtein distance analysis showed that text changes over article versions in social science papers were statistically significant in the Introduction section. Articles from Social Sciences had longer Introduction and Conclusion sections and higher percentage of articles with merged Discussion and Conclusion sections. Articles from Medical and Health Sciences followed the Introduction-Methods-Results-Discussion (IMRaD) structure more frequently and contained fewer declarations and non IMRaD sections, but more figures. Social Sciences articles had higher Word Count, higher Clout, and less positive Tone. Linguistic analysis revealed a more positive Tone for peer review reports for articles in Social Sciences and higher Achievement and Research variables. Peer review reports were significantly longer for articles in Social Sciences but the two disciplines did not differ in the characteristics of the peer review process at all stages between the submitted and published version. This may be due to the fact that they were published on the same publication platform, which uses uniform policies and procedures for both types of articles.

show abstract

Medical language – a unique linguistic phenomenon

Cited by 9 publications

References 12 publications

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models

Teaching Medical English through Professional Captioning Videos

Linguistic and semantic characteristics of articles and peer review reports in Social Sciences and Medical and Health Sciences: analysis of articles published in Open Research Central

Contact Info

Product

Resources

About