Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test

Abstract The heterogeneity of Parkinson’s disease (PD) presents considerable challenges for accurate diagnosis, particularly during early-stage disease, when the symptoms may be extremely subtle. This study aimed to assess the accuracy of a convolutional neural network (CNN) technique based on the 6...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyejin Choi, Changhong Youm, Hwayoung Park, Bohyun Kim, Juseon Hwang, Sang-Myung Cheon, Sungtae Shin
Format: Article
Language:English
Published: Nature Portfolio 2024-09-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-72648-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203605171175424
author Hyejin Choi
Changhong Youm
Hwayoung Park
Bohyun Kim
Juseon Hwang
Sang-Myung Cheon
Sungtae Shin
author_facet Hyejin Choi
Changhong Youm
Hwayoung Park
Bohyun Kim
Juseon Hwang
Sang-Myung Cheon
Sungtae Shin
author_sort Hyejin Choi
collection DOAJ
description Abstract The heterogeneity of Parkinson’s disease (PD) presents considerable challenges for accurate diagnosis, particularly during early-stage disease, when the symptoms may be extremely subtle. This study aimed to assess the accuracy of a convolutional neural network (CNN) technique based on the 6-min walk test (6MWT) measured using wearable sensors to distinguish patients with early-stage PD (n = 78) from healthy controls (n = 50). The participants wore six sensors, and performed the 6MWT. The time-series data were converted into new images. The results revealed that the gyroscopic vertical component of the lumbar spine displayed the highest classification accuracy of 83.5%, followed by those of the thoracic spine (83.1%) and right thigh (79.5%) segment. These findings suggest that the 6MWT and CNN models may facilitate earlier diagnosis and monitoring of PD symptoms, enabling clinicians to provide timely treatment during the critical transition from normal to pathologic gait patterns.
format Article
id doaj-art-f6dd2f264e74431999bed55ea8bfac2a
institution OA Journals
issn 2045-2322
language English
publishDate 2024-09-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-f6dd2f264e74431999bed55ea8bfac2a2025-08-20T02:11:28ZengNature PortfolioScientific Reports2045-23222024-09-0114111510.1038/s41598-024-72648-wConvolutional neural network based detection of early stage Parkinson’s disease using the six minute walk testHyejin Choi0Changhong Youm1Hwayoung Park2Bohyun Kim3Juseon Hwang4Sang-Myung Cheon5Sungtae Shin6Department of Health Sciences, The Graduate School of Dong-A UniversityDepartment of Health Sciences, The Graduate School of Dong-A UniversityBiomechanics Laboratory, Dong-A UniversityDepartment of Health Sciences, The Graduate School of Dong-A UniversityDepartment of Health Sciences, The Graduate School of Dong-A UniversityDepartment of Neurology, School of Medicine, Dong-A UniversityDepartment of Mechanical Engineering, College of Engineering, Dong-A UniversityAbstract The heterogeneity of Parkinson’s disease (PD) presents considerable challenges for accurate diagnosis, particularly during early-stage disease, when the symptoms may be extremely subtle. This study aimed to assess the accuracy of a convolutional neural network (CNN) technique based on the 6-min walk test (6MWT) measured using wearable sensors to distinguish patients with early-stage PD (n = 78) from healthy controls (n = 50). The participants wore six sensors, and performed the 6MWT. The time-series data were converted into new images. The results revealed that the gyroscopic vertical component of the lumbar spine displayed the highest classification accuracy of 83.5%, followed by those of the thoracic spine (83.1%) and right thigh (79.5%) segment. These findings suggest that the 6MWT and CNN models may facilitate earlier diagnosis and monitoring of PD symptoms, enabling clinicians to provide timely treatment during the critical transition from normal to pathologic gait patterns.https://doi.org/10.1038/s41598-024-72648-wParkinson’s diseaseDetectionArtificial intelligenceDeep learningConvolutional neural networkSix-minute walk test
spellingShingle Hyejin Choi
Changhong Youm
Hwayoung Park
Bohyun Kim
Juseon Hwang
Sang-Myung Cheon
Sungtae Shin
Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
Scientific Reports
Parkinson’s disease
Detection
Artificial intelligence
Deep learning
Convolutional neural network
Six-minute walk test
title Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
title_full Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
title_fullStr Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
title_full_unstemmed Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
title_short Convolutional neural network based detection of early stage Parkinson’s disease using the six minute walk test
title_sort convolutional neural network based detection of early stage parkinson s disease using the six minute walk test
topic Parkinson’s disease
Detection
Artificial intelligence
Deep learning
Convolutional neural network
Six-minute walk test
url https://doi.org/10.1038/s41598-024-72648-w
work_keys_str_mv AT hyejinchoi convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT changhongyoum convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT hwayoungpark convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT bohyunkim convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT juseonhwang convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT sangmyungcheon convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest
AT sungtaeshin convolutionalneuralnetworkbaseddetectionofearlystageparkinsonsdiseaseusingthesixminutewalktest