Clustering Nursing Sentences-Comparing Three Sentence Embedding Methods

Hans Moen*, Henry Suhonen, Sanna Salanterä, Tapio Salakoski, Laura Maria Peltonen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

1 Citation (Scopus)
57 Downloads (Pure)


In health sciences, high-quality text embeddings may augment qualitative data analysis of large amounts of text by enabling, e.g., searching and clustering of health information. This study aimed to evaluate three different sentence-level embedding methods in clustering sentences in nursing narratives from individual patients' hospital care episodes. Two of these embeddings are generated from language models based on the BERT framework, and the third on the Sent2Vec method. These embedding methods were used to cluster sentences from 20 patient care episodes and the results were manually evaluated. Findings suggest that the best clusters were produced by the embeddings from a BERT model fine-tuned for the proxy task of predicting subject headings for nursing text.

Original languageEnglish
Title of host publicationChallenges of Trustable AI and Added-Value on Health - Proceedings of MIE 2022
EditorsBrigitte Seroussi, Patrick Weber, Ferdinand Dhombres, Cyril Grouin, Jan-David Liebe, Jan-David Liebe, Jan-David Liebe, Sylvia Pelayo, Andrea Pinna, Bastien Rance, Bastien Rance, Lucia Sacchi, Adrien Ugon, Adrien Ugon, Arriel Benis, Parisis Gallos
PublisherIOS Press
Number of pages5
ISBN (Electronic)978-1-64368-284-6
Publication statusPublished - 25 May 2022
MoE publication typeA4 Conference publication
EventMedical Informatics Europe Conference - Nice, France
Duration: 27 May 202230 May 2022
Conference number: 32

Publication series

NameStudies in Health Technology and Informatics
PublisherIOS Press
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365


ConferenceMedical Informatics Europe Conference
Abbreviated titleMIE


  • electronic health records
  • natural language processing
  • nursing documentation
  • sentence embeddings
  • Text clustering


Dive into the research topics of 'Clustering Nursing Sentences-Comparing Three Sentence Embedding Methods'. Together they form a unique fingerprint.

Cite this