Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

HeXEHRS: Design and Implementation of a FHIR-Based Cloud EHR and Client for Depopulated Regions with AI and Digital-Twin Integration.

Studies in health technology and informatics·2026

Same author

Machine Learning Models Incorporating Nursing Care Needs to Predict 180-Day Prognosis in Patients With Heart Failure: Validation With Discrimination and Calibration Analyses.

Circulation reports·2026

Same author

Natural Language Processing-Based Visualization Framework for Adverse Events Extracted from Clinical Narratives: Towards Enhancing Clinical Interpretability.

Biological & pharmaceutical bulletin·2026

Same author

Generating Counterfactual Patient Timelines from Real-World Data.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Same author

Efficient medical NER with limited data: Enhancing LLM performance through annotation guidelines.

International journal of medical informatics·2025

Same author

A scalable natural language processing framework for drug repurposing in chemotherapy-induced adverse events from clinical narrative records.

European journal of cancer (Oxford, England : 1990)·2025

Search research articles

Related Experiment Video

Updated: Jul 5, 2025

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts

Published on: September 20, 2024

Clinical Feature Vector Generation using Unsupervised Graph Representation Learning from Heterogeneous Medical

Tomohisa Seki¹, Yoshimasa Kawazoe², Kazuhiko Ohe³

¹Department of Healthcare Information Management, The University of Tokyo Hospital, Tokyo, Japan.

AMIA ... Annual Symposium Proceedings. AMIA Symposium

|January 15, 2024

Summary

This study used unsupervised graph representation learning to convert diverse electronic medical record data into fixed-length vectors. The resulting vectors successfully retained clinical information, predicting patient readmission risks.

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

Related Experiment Videos

Last Updated: Jul 5, 2025

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts

Author Spotlight: Integrated Multi-Omics Analysis for Unveiling Multicellular Immune Signatures in Clinical Heart Attack Cohorts

Published on: September 20, 2024

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

Area of Science:

Medical Informatics
Machine Learning
Data Science

Background:

Electronic medical records (EMRs) contain diverse patient information, posing challenges for data analysis.
Converting unstructured EMR data into fixed-length vectors that preserve clinical characteristics is difficult.

Purpose of the Study:

To apply unsupervised graph representation learning to transform unstructured inpatient EMR data into fixed-length vectors.
To evaluate if these vectors retain clinically relevant information.

Main Methods:

Utilized the Infograph algorithm, an unsupervised graph representation learning method.
Applied Infograph to graphed inpatient information from EMRs to generate embedded vectors.
Assessed the clinical information preservation within the generated embedded vectors.

Main Results:

The study successfully generated fixed-length embedded vectors from unstructured EMR data.
These embedded vectors were found to contain clinically relevant information.
The vectors demonstrated predictive power for 30-day patient readmission.

Conclusions:

Unsupervised graph representation learning is a feasible method for transforming patient information from EMRs into fixed-length vectors.
This approach effectively retains crucial clinical characteristics within the vectors.
The method shows promise for improving EMR data analysis and predictive modeling.