Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records
Studies in Health Technology and Informatics · 2024
DOI: 10.3233/shti231058 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2024. Verfasst von Tomohisa Seki und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Healthcare Information Management, The University of Tokyo Hospital, Japan. Hauptthemen laut MEDLINE: Medical Records, Records. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Transformation of patient data extracted from a database into fixed-length numerical vectors requires expertise in topical medical knowledge as well as data manipulation—thus, manual feature design is labor-intensive. In this study, we propose a machine learning-based method to for this purpose applicable to electronic medical data recorded during hospitalization, which utilizes unsupervised feature extraction based on graph embedding. Unsupervised learning is performed on a heterogeneous graph using Graph2Vec, and the inclusion of clinically useful data in the obtained embedding representation is evaluated by predicting readmission within 30 days of discharge based on it. The embedded representations are observed to improve predictive performance significantly as the information contained in the graph increases, indicating the suitability of the proposed method for feature design corresponding to clinical information.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Healthcare Information Management, The University of Tokyo Hospital, Japan.
- Artificial Intelligence in Healthcare, Graduate School of Medicine, The University of Tokyo, Japan.
- Department of Biomedical Informatics, Graduate School of Medicine, The University of Tokyo, Japan.
Zitieren
APA
Seki, T., Kawazoe, Y., & Ohe, K. (2024). Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti231058
Vancouver
Seki T, Kawazoe Y, Ohe K. Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records. Studies in Health Technology and Informatics. 2024. doi:10.3233/shti231058
BibTeX
@article{Seki2024,
author = {Seki, Tomohisa and Kawazoe, Yoshimasa and Ohe, Kazuhiko},
title = {Graph Representation Learning-Based Fixed-Length Clinical Feature Vector Generation from Heterogeneous Medical Records},
journal = {Studies in Health Technology and Informatics},
year = {2024},
doi = {10.3233/shti231058}
}
EUVIMED