Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2242916,
author = {Zelina, Petr and Halámková, Jana and Nováček, Vít},
address = {USA},
booktitle = {Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
doi = {http://dx.doi.org/10.1109/BIBM55620.2022.9995229},
keywords = {NLP; EHR; Clinical Notes; Information Extraction; Text Classification},
howpublished = {elektronická verze "online"},
language = {eng},
location = {USA},
isbn = {978-1-6654-6820-6},
pages = {1362-1368},
publisher = {IEEE},
title = {Unsupervised extraction, labelling and clustering of segments from clinical notes},
url = {https://arxiv.org/abs/2211.11799},
year = {2022}
}
TY - JOUR
ID - 2242916
AU - Zelina, Petr - Halámková, Jana - Nováček, Vít
PY - 2022
TI - Unsupervised extraction, labelling and clustering of segments from clinical notes
PB - IEEE
CY - USA
SN - 9781665468206
KW - NLP
KW - EHR
KW - Clinical Notes
KW - Information Extraction
KW - Text Classification
UR - https://arxiv.org/abs/2211.11799
N2 - This work is motivated by the scarcity of tools for accurate, unsupervised information extraction from unstructured clinical notes in computationally underrepresented languages, such as Czech. We introduce a stepping stone to a broad array of downstream tasks such as summarisation or integration of individual patient records, extraction of structured information for national cancer registry reporting or building of semi-structured semantic patient representations for computing patient embeddings. More specifically, we present a method for unsupervised extraction of semantically-labelled textual segments from clinical notes and test it out on a dataset of Czech breast cancer patients, provided by Masaryk Memorial Cancer Institute (the largest Czech hospital specialising in oncology). Our goal was to extract, classify (i.e. label) and cluster segments of the free-text notes that correspond to specific clinical features (e.g., family background, comorbidities or toxicities). The presented results demonstrate the practical relevance of the proposed approach for building more sophisticated extraction and analytical pipelines deployed on Czech clinical notes.
ER -
ZELINA, Petr, Jana HALÁMKOVÁ and Vít NOVÁČEK. Unsupervised extraction, labelling and clustering of segments from clinical notes. Online. In \textit{Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}. USA: IEEE, 2022, p.~1362-1368. ISBN~978-1-6654-6820-6. Available from: https://dx.doi.org/10.1109/BIBM55620.2022.9995229.
|
