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

Structural connectome analysis using a graph-based deep model for prediction of non-imaging variables.

Frontiers in neuroscience·2026

Same author

The Epidemiology and Clinical Presentation of the Acute Imbalance Syndrome (AIS)-A Systematic Review and Meta-Analysis.

European journal of neurology·2026

Same author

Prevalence and direct costs of vestibular disease in France - matched case-control study results from the 2022 and 2023 french health data system.

Cost effectiveness and resource allocation : C/E·2026

Same author

Confirmatory factor analysis and Rasch analysis of the German revised version of the Niigata PPPD questionnaire: NPQ-R.

Frontiers in neurology·2026

Same author

Detection of Focal Lesions in Epilepsy with [<sup>18</sup>F]UCB-H Synaptic Vesicle Protein 2A PET Imaging.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026

Same author

Superior oblique myokymia: diagnostic criteria and long-term outcome.

Journal of neurology·2026

Search research articles

Related Experiment Video

Updated: Nov 2, 2025

Basics of Multivariate Analysis in Neuroimaging Data

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Simultaneous imputation and classification using Multigraph Geometric Matrix Completion (MGMC): Application to

Gerome Vivar¹, Anees Kazi², Hendrik Burwinkel²

¹Department of Computer Aided Medical Procedures (CAMP), Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching, Germany; German Center for Vertigo and Balance Disorders (DSGZ), Ludwig-Maximilians University (LMU), Fraunhoferstr. 20, 82152, Planegg, Germany.

Artificial Intelligence in Medicine

|June 15, 2021

Summary

This study introduces Multi-graph Geometric Matrix Completion (MGMC), an innovative machine learning method for handling incomplete medical data. MGMC accurately imputes missing features and improves disease prediction, outperforming existing approaches.

Keywords:

CADx Computer-aided diagnosis Deep learning Multimodal medical data Population-based studies

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

Related Experiment Videos

Last Updated: Nov 2, 2025

Basics of Multivariate Analysis in Neuroimaging Data

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment

Published on: August 7, 2017

Area of Science:

Medical Informatics
Machine Learning
Data Science

Background:

Large-scale population studies are crucial for medical advancements, including computer-aided diagnosis (CADx).
Existing machine learning (ML) methods for CADx often struggle with incomplete clinical data, leading to bias and reduced performance.
Current methods for handling missing data, such as removal or imputation, can negatively impact classification accuracy.

Purpose of the Study:

To develop an end-to-end learning approach for imputing missing data and predicting diseases in incomplete medical datasets.
To introduce Multi-graph Geometric Matrix Completion (MGMC) as a novel solution for multimodal and incomplete medical data.
To enhance the robustness and accuracy of CADx systems by effectively managing missing clinical information.

Main Methods:

Proposed an end-to-end learning framework called Multi-graph Geometric Matrix Completion (MGMC).
Utilized multiple recurrent graph convolutional networks, with each graph modeling a population based on clinical meta-features (e.g., age, sex).
Employed graph signal aggregation and multi-graph signal fusion via self-attention for regularization and improved performance.

Main Results:

MGMC demonstrated superior performance in both imputing class-relevant features and classifying diseases on two public medical datasets.
The approach achieved accurate and robust classification, outperforming state-of-the-art methods in empirical evaluations.
Successfully enabled disease prediction using multimodal and incomplete medical datasets.

Conclusions:

MGMC offers a powerful solution for disease prediction in incomplete medical datasets, addressing a significant limitation in current CADx systems.
The method effectively handles missing data, improving both imputation and classification accuracy.
MGMC provides a strong baseline for future research in CADx utilizing incomplete clinical data.