research-article

1D-convolutional transformer for Parkinson disease diagnosis from gait

Authors:

Wassim Bouachir,

Guillaume-Alexandre BilodeauAuthors Info & Claims

Neural Computing and Applications, Volume 36, Issue 4

Pages 1947 - 1957

https://doi.org/10.1007/s00521-023-09193-6

Published: 18 November 2023 Publication History

Abstract

This paper presents an efficient deep neural network model for diagnosing Parkinson’s disease from gait. More specifically, we introduce a hybrid ConvNet-Transformer architecture to accurately diagnose the disease by detecting the severity stage. The proposed architecture exploits the strengths of both convolutional neural networks and Transformers in a single end-to-end model, where the former is able to extract relevant local features from Vertical Ground Reaction Force (VGRF) signal, while the latter allows to capture long-term spatio-temporal dependencies in data. In this manner, our hybrid architecture achieves an improved performance compared to using either models individually. Our experimental results show that our approach is effective for detecting the different stages of Parkinson’s disease from gait data, with a final accuracy of 88%, outperforming other state-of-the-art AI methods on the Physionet gait dataset. Moreover, our method can be generalized and adapted for other classification problems to jointly address the feature relevance and spatio-temporal dependency problems in 1D signals. Our source code and pre-trained models are publicly available at https://github.com/SafwenNaimi.

References

[1]

Parkinson J An essay on the shaking palsy JAMA Neurol 1969 20 441-445

[2]

Stoker TB and Barker RA Recent developments in the treatment of Parkinson’s disease F1000Research 2020

[3]

Goetz CG, Tilley BC, Shaftman SR, Stebbins GT, Fahn S, Martínez-Martín P, Poewe W, Sampaio C, Stern MB, Dodel R, Dubois B, Holloway RG, Jankovic J, Kulisevsky J, Lang AE, Lees AJ, Leurgans SE, LeWitt P, Nyenhuis D, Olanow CW, Rascol O, Schrag AE, Teresi JA, Hilten JJ, and Lapelle N Movement disorder society-sponsored revision of the unified Parkinson’s disease rating scale (mds-updrs): scale presentation and clinimetric testing results Mov Disord 2008 23 2129-2170

[4]

Bhidayasiri R, Tarsy D (2012) Parkinson’s disease: Hoehn and yahr scale

[5]

Parkinson’s Disease MDSTF The unified Parkinson’s disease rating scale (updrs): status and recommendations Mov Disors 2003 18 738-750

[6]

Hoehn MM and Yahr MD Parkinsonism: onset, progression, and mortality. 1967 Neurology 1998 57 10 Suppl 3 11-26

[7]

Heida T, Wentink EC, and Marani E Power spectral density analysis of physiological, rest and action tremor in Parkinson’s disease patients treated with deep brain stimulation J NeuroEng Rehabilit 2013 10 70-70

[8]

Patel M, Nilsson MH, Rehncrona S, Tjernström F, Magnusson M, Johansson R, and Fransson P-A Spectral analysis of body movement during deep brain stimulation in Parkinson’s disease Gait Post 2021 86 217-225

[9]

Chang K-H, French IT, Liang W-K, Lo Y-S, Wang Y-R, Cheng M-L, Huang NE, Wu H-C, Lim S-N, Chen CM, and Juan C-H Evaluating the different stages of Parkinson’s disease using electroencephalography with Holo-Hilbert spectral analysis Front Aging Neurosci 2022 14

[10]

Rizvi SQA, Wang G, Xing X (2019) Early detection of Parkinson disease using wavelet transform along with fourier transform. In: iSCI

[11]

Ertugrul ÖF, Kaya Y, Tekin R, and Almali MN Detection of Parkinson’s disease by shifted one dimensional local binary patterns from gait Expert Syst Appl 2016 56 156-163

[12]

Xia Y, Gao Q, and Ye Q Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: experiments with statistical features and different classification models Biomed Sign Process Control 2015 18 254-262

[13]

Mannini A, Trojaniello D, Cereatti A, and Sabatini AM A machine learning framework for gait classification using inertial sensors: application to elderly, post-stroke and Huntington’s disease patients Sensors (Basel, Switzerland) 2016 16 134

[14]

Burges CJC A tutorial on support vector machines for pattern recognition Data Min Knowl Discov 1998 2 121-167

[15]

Nanni L, Ghidoni S, and Brahnam S Handcrafted versus non-handcrafted features for computer vision classification Patt Recognit 2017 71 158-172

[16]

Caramia C, Torricelli D, Schmid M, Muñoz-Gonzalez A, González-Vargas J, Grandas F, and Pons JL Imu-based classification of Parkinson’s disease from gait: a sensitivity analysis on sensor location and feature selection IEEE J Biomed Health Inform 2018 22 1765-1774

[17]

Veeraragavan S, Gopalai AA, Gouwanda D, and Ahmad SA Parkinson’s disease diagnosis and severity assessment using ground reaction forces and neural networks Front Physiol 2020 11 587057

[18]

Maâchi IE, Bilodeau G-A, and Bouachir W Deep 1d-convnet for accurate Parkinson disease detection and severity prediction from gait Expert Syst Appl 2019 143 113075

[19]

Keller TS, Weisberger AM, Ray JL, Hasan SS, Shiavi RG, and Spengler DM Relationship between vertical ground reaction force and speed during walking, slow jogging, and running Clin Biomech 1996 11 5 253-259

[20]

Takahashi T, Ishida K, Hirose D, Nagano Y, Okumiya K, Nishinaga M, Doi Y, and Yamamoto H Vertical ground reaction force shape is associated with gait parameters, timed up and go, and functional reach in elderly females J Rehabilit Med 2004 36 1 42-5

[21]

Muniz AM, Manfio EF, Andrade MC, Nadal J (2006) Principal component analysis of vertical ground reaction force: a powerful method to discriminate normal and abnormal gait and assess treatment. In: 2006 international conference of the ieee engineering in medicine and biology society, pp 2683–2686

[22]

Mirelman A, Frank MBO, Melamed M, Granovsky L, Nieuwboer A, Rochester L, Din SD, Avanzino L, Pelosin E, Bloem BR, Croce UD, Cereatti A, Bonato P, Camicioli R, Ellis T, Hamilton JL, Hass CJ, Almeida QJ, Inbal M, Thaler A, Shirvan JC, Cedarbaum JM, Giladi N, and Hausdorff JM Detecting sensitive mobility features for Parkinson’s disease stages via machine learning Mov Disord 2021 36 2144-2155

[23]

Sabo A, Mehdizadeh S, Ng K-D, Iaboni A, and Taati B Assessment of parkinsonian gait in older adults with dementia via human pose tracking in video data JNeuroEng Rehabilit 2020 17 1-10

[24]

Park J, Lee J-S, and Sim D Low-complexity CNN with 1d and 2d filters for super-resolution J Real-Time Image Process 2020 17 2065-2076

[25]

Lohit S, Wang Q, Turaga PK (2019) Temporal transformer networks: joint learning of invariant and discriminative time warping. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 12418–12427

[26]

Tyagi H, Gärtner B, Krause A (2014) Advances in neural information processing systems (nips)

[27]

LeCun Y, Haffner P, Bottou L, Bengio Y (1999) Object recognition with gradient-based learning. In: Shape, contour and grouping in computer vision

[28]

Yogev G, Giladi N, Peretz C, Springer S, Simon ES, and Hausdorff JM Dual tasking, gait rhythmicity, and Parkinson’s disease: Which aspects of gait are attention demanding? Eur J Neurosci 2005 22 1248-1256

[29]

Hausdorff JM, Lowenthal J, Herman T, Gruendlinger L, Peretz C, and Giladi N Rhythmic auditory stimulation modulates gait variability in Parkinson’s disease Eur J Neurosci 2007 26 2369-2375

[30]

Frenkel-Toledo S, Giladi N, Peretz C, Herman T, Gruendlinger L, and Hausdorff JM Treadmill walking as an external pacemaker to improve gait rhythm and stability in Parkinson’s disease Mov Disord 2005 20 1109-1114

[31]

Physionet Dataset. https://www.physionet.org/content/gaitpdb/1.0.0/ Accessed 25 Nov 2022

[32]

Pratama K and Kang D-K Trainable activation function with differentiable negative side and adaptable rectified point Appl Intell 2020 51 1784-1801

[33]

Dozat T (2016) Incorporating nesterov momentum into adam. In: Proceedings of the 54th annual meeting of the association for computational linguistics (ACL 2016)

[34]

Nguyen DM, Miah M, Bilodeau G-A, Bouachir W (2022) Transformers for 1d signals in Parkinson’s disease detection from gait. In: 2022 26th international conference on pattern recognition (ICPR), pp 5089–5095

Cited By

Uchaipichat NTangjirachaipoka AChamninavakul C(2024)Machine Learning-Based Detection of Parkinson's Disease Using Vertical Ground Reaction Force and Gait AnalysisProceedings of the 2024 9th International Conference on Biomedical Imaging, Signal Processing10.1145/3707172.3707195(153-157)Online publication date: 18-Oct-2024
https://dl.acm.org/doi/10.1145/3707172.3707195

Index Terms

1D-convolutional transformer for Parkinson disease diagnosis from gait
1. Applied computing
  1. Life and medical sciences
    1. Health informatics
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Learning paradigms
      1. Supervised learning
    2. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Deep learning based diagnosis of Parkinson’s disease using convolutional neural network
Abstract
Parkinson’s disease is the second most common degenerative disease caused by loss of dopamine producing neurons. The substantia nigra region is deprived of its neuronal functions causing striatal dopamine deficiency which remains as hallmark in ...
Improvement of Performance in Freezing of Gait detection in Parkinson’s Disease using Transformer networks and a single waist-worn triaxial accelerometer
Abstract
Freezing of gait (FOG) is one of the most incapacitating symptoms in Parkinson’s disease, affecting more than 50% of patients in advanced stages of the disease. The presence of FOG may lead to falls and a loss of independence with a ...
Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait
Highlights
- A novel method for automatic detection of Parkinson disease and severity prediction.
Abstract
Diagnosing Parkinson’s disease is a complex task that requires the evaluation of several motor and non-motor symptoms. During diagnosis, gait abnormalities are among the important symptoms that physicians should consider. However, gait ...

Comments

Information & Contributors

Information

Published In

cover image Neural Computing and Applications

Neural Computing and Applications Volume 36, Issue 4

Feb 2024

593 pages

EISSN:1433-3058

Issue’s Table of Contents

© The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 18 November 2023

Accepted: 20 October 2023

Received: 31 May 2023

Author Tags

Qualifiers

Research-article

Funding Sources

Natural Sciences and Engineering Research Council of Canada (NSERC)

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 28 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Uchaipichat NTangjirachaipoka AChamninavakul C(2024)Machine Learning-Based Detection of Parkinson's Disease Using Vertical Ground Reaction Force and Gait AnalysisProceedings of the 2024 9th International Conference on Biomedical Imaging, Signal Processing10.1145/3707172.3707195(153-157)Online publication date: 18-Oct-2024
https://dl.acm.org/doi/10.1145/3707172.3707195

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents