Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task

Abstract This study proposes a synthetic data generation model to create a classification framework for cerebellar ataxia patients using trajectory data from the visuomotor adaptation task. The classification objectives include patients with cerebellar ataxia, age-matched normal individuals, and you...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinah Kim, Sung-Ho Woo, Taekyung Kim, Won Tae Yoon, Jung Hwan Shin, Jee-Young Lee, Jeh-Kwang Ryu
Format: Article
Language:English
Published: BMC 2024-11-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-024-02720-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846165217362313216
author Jinah Kim
Sung-Ho Woo
Taekyung Kim
Won Tae Yoon
Jung Hwan Shin
Jee-Young Lee
Jeh-Kwang Ryu
author_facet Jinah Kim
Sung-Ho Woo
Taekyung Kim
Won Tae Yoon
Jung Hwan Shin
Jee-Young Lee
Jeh-Kwang Ryu
author_sort Jinah Kim
collection DOAJ
description Abstract This study proposes a synthetic data generation model to create a classification framework for cerebellar ataxia patients using trajectory data from the visuomotor adaptation task. The classification objectives include patients with cerebellar ataxia, age-matched normal individuals, and young healthy subjects. Synthetic data for the three classes is generated based on class conditions and random noise by leveraging a combination of conditional adversarial generative neural networks and reconstruction networks. This synthetic data, alongside real data, is utilized as training data for the patient classification model to enhance classification accuracy. The fidelity of the synthetic data is assessed visually to measure the validity and diversity of the generated data qualitatively while quantitatively evaluating distribution similarity to real data. Furthermore, the clinical efficacy of the patient classification model employing synthetic data is demonstrated by showcasing improved classification accuracy through a comparative analysis between results obtained using solely real data and those obtained when both real and synthetic data are utilized. This methodological approach holds promise in addressing data insufficiency in the digital healthcare domain, employing deep learning methodologies, and developing early disease diagnosis tools.
format Article
id doaj-art-d0f7152faac7434cad983033a7f457e9
institution Kabale University
issn 1472-6947
language English
publishDate 2024-11-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-d0f7152faac7434cad983033a7f457e92024-11-17T12:31:44ZengBMCBMC Medical Informatics and Decision Making1472-69472024-11-0124111510.1186/s12911-024-02720-yDevelopment of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation taskJinah Kim0Sung-Ho Woo1Taekyung Kim2Won Tae Yoon3Jung Hwan Shin4Jee-Young Lee5Jeh-Kwang Ryu6Coastal Disaster Research Center, Korea Institute of Ocean Science and TechnologyInstitute of Interdisciplinary Brain Science, Dongguk University College of MedicineCoastal Disaster Research Center, Korea Institute of Ocean Science and TechnologyDepartment of Neurology, Samsung Kangbuk Hospital, Sungkyunkwan University School of MedicineDepartment of Neurology, Seoul National University Hospital, Seoul National University College of MedicineDepartment of Neurology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul National University College of MedicineLaboratory for Natural and Artificial Kinästhese, Convergence Research Center for Artificial Intelligence, Dongguk UniversityAbstract This study proposes a synthetic data generation model to create a classification framework for cerebellar ataxia patients using trajectory data from the visuomotor adaptation task. The classification objectives include patients with cerebellar ataxia, age-matched normal individuals, and young healthy subjects. Synthetic data for the three classes is generated based on class conditions and random noise by leveraging a combination of conditional adversarial generative neural networks and reconstruction networks. This synthetic data, alongside real data, is utilized as training data for the patient classification model to enhance classification accuracy. The fidelity of the synthetic data is assessed visually to measure the validity and diversity of the generated data qualitatively while quantitatively evaluating distribution similarity to real data. Furthermore, the clinical efficacy of the patient classification model employing synthetic data is demonstrated by showcasing improved classification accuracy through a comparative analysis between results obtained using solely real data and those obtained when both real and synthetic data are utilized. This methodological approach holds promise in addressing data insufficiency in the digital healthcare domain, employing deep learning methodologies, and developing early disease diagnosis tools.https://doi.org/10.1186/s12911-024-02720-yCerebellar ataxia diagnosisVisuomotor adaptation taskConditional generative adversarial networkSynthetic dataDigital healthcare
spellingShingle Jinah Kim
Sung-Ho Woo
Taekyung Kim
Won Tae Yoon
Jung Hwan Shin
Jee-Young Lee
Jeh-Kwang Ryu
Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
BMC Medical Informatics and Decision Making
Cerebellar ataxia diagnosis
Visuomotor adaptation task
Conditional generative adversarial network
Synthetic data
Digital healthcare
title Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
title_full Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
title_fullStr Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
title_full_unstemmed Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
title_short Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task
title_sort development of a cerebellar ataxia diagnosis model using conditional gan based synthetic data generation for visuomotor adaptation task
topic Cerebellar ataxia diagnosis
Visuomotor adaptation task
Conditional generative adversarial network
Synthetic data
Digital healthcare
url https://doi.org/10.1186/s12911-024-02720-y
work_keys_str_mv AT jinahkim developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT sunghowoo developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT taekyungkim developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT wontaeyoon developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT junghwanshin developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT jeeyounglee developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask
AT jehkwangryu developmentofacerebellarataxiadiagnosismodelusingconditionalganbasedsyntheticdatagenerationforvisuomotoradaptationtask