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

ZELINA, Petr, Jana HALÁMKOVÁ and 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, p. 4172-4178. ISBN 979-8-3503-3748-8. Available from: https://dx.doi.org/10.1109/BIBM58861.2023.10385342.

Basic information

• Original name: Unsupervised extraction, classification and visualization of clinical note segments using the MIMIC-III dataset
• Authors: ZELINA, Petr (203 Czech Republic, belonging to the institution), Jana HALÁMKOVÁ (203 Czech Republic) and Vít NOVÁČEK (203 Czech Republic, belonging to the institution).
• Edition: Istanbul, Proceedings of IEEE International Conference on Bioinformatics and Biomedicine (BIBM), p. 4172-4178, 7 pp. 2023.
• Publisher: IEEE

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: United States of America
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: electronic version available online
• RIV identification code: RIV/00216224:14330/23:00133337
• Organization unit: Faculty of Informatics
• ISBN: 979-8-3503-3748-8
• ISSN: 2156-1133
• Doi: http://dx.doi.org/10.1109/BIBM58861.2023.10385342
• Keywords in English: NLP; EHR; Clinical Notes; Information Extraction; Text Classification

Abstract

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.

Links

• MUNI/G/1763/2020, interní kód MU: Name: AIcope - AI support for Clinical Oncology and Patient Empowerment (Acronym: AIcope)

Investor: Masaryk University, INTERDISCIPLINARY - Interdisciplinary research projects