Clustering Nursing Sentences-Comparing Three Sentence Embedding Methods

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2022-05-25

Major/Subject

Mcode

Degree programme

Language

en

Pages

5
854-858

Series

Challenges of Trustable AI and Added-Value on Health - Proceedings of MIE 2022, Studies in Health Technology and Informatics, Volume 294

Abstract

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.

Description

Funding Information: Acknowledgements: This work was supported by the Academy of Finland (grants 315376, 336033, 315896), Business Finland (grant 884/31/2018), and EU H2020 (grant 101016775). We thank Jari Björne for helping with fine-tuning the BERT model. Publisher Copyright: © 2022 European Federation for Medical Informatics (EFMI) and IOS Press. | openaire: EC/H2020/101016775/EU//INTERVENE

Keywords

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

Other note

Citation

Moen, H, Suhonen, H, Salanterä, S, Salakoski, T & Peltonen, L M 2022, Clustering Nursing Sentences-Comparing Three Sentence Embedding Methods . in B Seroussi, P Weber, F Dhombres, C Grouin, J-D Liebe, J-D Liebe, J-D Liebe, S Pelayo, A Pinna, B Rance, B Rance, L Sacchi, A Ugon, A Ugon, A Benis & P Gallos (eds), Challenges of Trustable AI and Added-Value on Health - Proceedings of MIE 2022 . Studies in Health Technology and Informatics, vol. 294, IOS Press, pp. 854-858, Medical Informatics Europe Conference, Nice, France, 27/05/2022 . https://doi.org/10.3233/SHTI220606