Unsupervised extraction, classification and visualization of
clinical note segments using the MIMIC-III dataset

D 2023

Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset

ZELINA, Petr, Jana HALÁMKOVÁ a Vít NOVÁČEK

Základní údaje

Originální název

Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset

Autoři

ZELINA, Petr (203 Česká republika, domácí), Jana HALÁMKOVÁ (203 Česká republika) a Vít NOVÁČEK (203 Česká republika, domácí)

Vydání

Istanbul, Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM), od s. 4172-4178, 7 s. 2023

Nakladatel

IEEE

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Kód RIV

RIV/00216224:14330/23:00133337

Organizační jednotka

Fakulta informatiky

ISBN

979-8-3503-3748-8

ISSN

DOI

http://dx.doi.org/10.1109/BIBM58861.2023.10385342

Klíčová slova anglicky

NLP; EHR; Clinical Notes; Information Extraction; Text Classification

Změněno: 8. 4. 2024 22:05, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

This paper presents a text-mining approach to extracting and organizing segments from unstructured clinical notes in an unsupervised way. Our work is motivated by the real challenge of poor semantic integration between clinical notes produced by different doctors, departments, or hospitals. This can lead to clinicians overlooking important information, especially for patients with long and varied medical histories. This work extends a previous approach developed for Czech breast cancer patients and validates it on the publicly accessible MIMIC-III English dataset, demonstrating its universal and language-independent applicability. Our work is a stepping stone to a broad array of downstream tasks, such as summarizing or integrating patient records, extracting structured information, or computing patient embeddings. Additionally, the paper presents a clustering analysis of the latent space of note segment types, using hierarchical clustering and an interactive treemap visualization. The presented results demonstrate that this approach generalizes well for MIMIC and English.

Návaznosti

MUNI/G/1763/2020, interní kód MU

Název: AIcope - AI support for Clinical Oncology and Patient Empowerment (Akronym: AIcope)

Investor: Masarykova univerzita, AIcope - AI support for Clinical Oncology and Patient Empowerment, INTERDISCIPLINARY - Mezioborové výzkumné projekty

Citovat

ZELINA, Petr, Jana HALÁMKOVÁ a Vít NOVÁČEK. Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset. Online. In Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM). Istanbul: IEEE, 2023, s. 4172-4178. ISBN 979-8-3503-3748-8. Dostupné z: https://dx.doi.org/10.1109/BIBM58861.2023.10385342.

@inproceedings{2368016,
   author = {Zelina, Petr and Halámková, Jana and Nováček, Vít},
   address = {Istanbul},
   booktitle = {Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
   doi = {http://dx.doi.org/10.1109/BIBM58861.2023.10385342},
   keywords = {NLP; EHR; Clinical Notes; Information Extraction; Text Classification},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Istanbul},
   isbn = {979-8-3503-3748-8},
   pages = {4172-4178},
   publisher = {IEEE},
   title = {Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset},
   year = {2023}
}

TY  - JOUR
ID  - 2368016
AU  - Zelina, Petr - Halámková, Jana - Nováček, Vít
PY  - 2023
TI  - Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset
PB  - IEEE
CY  - Istanbul
SN  - 9798350337488
KW  - NLP
KW  - EHR
KW  - Clinical Notes
KW  - Information Extraction
KW  - Text Classification
N2  - This paper presents a text-mining approach to extracting and organizing segments from unstructured clinical notes in an unsupervised way. Our work is motivated by the real challenge of poor semantic integration between clinical notes produced by different doctors, departments, or hospitals. This can lead to clinicians overlooking important information, especially for patients with long and varied medical histories. This work extends a previous approach developed for Czech breast cancer patients and validates it on the publicly accessible MIMIC-III English dataset, demonstrating its universal and language-independent applicability. Our work is a stepping stone to a broad array of downstream tasks, such as summarizing or integrating patient records, extracting structured information, or computing patient embeddings. Additionally, the paper presents a clustering analysis of the latent space of note segment types, using hierarchical clustering and an interactive treemap visualization. The presented results demonstrate that this approach generalizes well for MIMIC and English.
ER  -

ZELINA, Petr, Jana HALÁMKOVÁ a Vít NOVÁČEK. Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset. Online. In \textit{Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}. Istanbul: IEEE, 2023, s.~4172-4178. ISBN~979-8-3503-3748-8. Dostupné z: https://dx.doi.org/10.1109/BIBM58861.2023.10385342.

Podrobný výpis o publikaci