This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors
by
Mustafa Shuqair
Mustafa Shuqair
Mustafa Shuqair is pursuing his Ph.D. in the Department of Electrical Engineering and Computer at in [...]
Mustafa Shuqair is pursuing his Ph.D. in the Department of Electrical Engineering and Computer Science at Florida Atlantic University in the United States. Before this, he earned an M.Sc. in Mechatronics from the University of Siegen in Germany. Since 2020, Mustafa has been actively involved as a research and teaching assistant at Florida Atlantic University. His research focuses on machine learning, learning systems, wearables, and biomedical signal analysis within the Sensing and Embedded Network Systems Engineering Lab. His contributions in these areas have led to several publications in journals and conferences.
1
,
Joohi Jimenez-Shahed
Joohi Jimenez-Shahed 2
and
Behnaz Ghoraani
Behnaz Ghoraani
Prof. Behnaz Ghoraani currently serves as a Faculty Fellow at the Institute for Sensing and Embedded [...]
Prof. Behnaz Ghoraani currently serves as a Faculty Fellow at the Institute for Sensing and Embedded Network Systems Engineering at Florida Atlantic University. She is also the founder and director of the Biomedical Signal and Image Analysis (BSIA) Lab at FAU. Prof. Behnaz Ghoraani completed her Ph.D. in Electrical and Computer Engineering at Ryerson University, Toronto, Canada, in 2010, followed by a Postdoctoral Fellow period with the Faculty of Medicine, University of Toronto, Toronto, Canada. Prof. Behnaz Ghoraani's main research areas are biomedical signal analysis, machine learning, wearable and assistive rehabilitation devices, and remote home monitoring. She and her students recently filed two patent applications for developing methods for guiding sensing catheters to locate cardiac arrhythmia sources.
1,*
1
Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USA
2
Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
*
Author to whom correspondence should be addressed.
Bioengineering 2024, 11(7), 689; https://doi.org/10.3390/bioengineering11070689 (registering DOI)
Submission received: 25 May 2024
/
Revised: 28 June 2024
/
Accepted: 3 July 2024
/
Published: 7 July 2024
Abstract
The Unified Parkinson’s Disease Rating Scale (UPDRS) is used to recognize patients with Parkinson’s disease (PD) and rate its severity. The rating is crucial for disease progression monitoring and treatment adjustment. This study aims to advance the capabilities of PD management by developing an innovative framework that integrates deep learning with wearable sensor technology to enhance the precision of UPDRS assessments. We introduce a series of deep learning models to estimate UPDRS Part III scores, utilizing motion data from wearable sensors. Our approach leverages a novel Multi-shared-task Self-supervised Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) framework that processes raw gyroscope signals and their spectrogram representations. This technique aims to refine the estimation accuracy of PD severity during naturalistic human activities. Utilizing 526 min of data from 24 PD patients engaged in everyday activities, our methodology demonstrates a strong correlation of 0.89 between estimated and clinically assessed UPDRS-III scores. This model outperforms the benchmark set by single and multichannel CNN, LSTM, and CNN-LSTM models and establishes a new standard in UPDRS-III score estimation for free-body movements compared to recent state-of-the-art methods. These results signify a substantial step forward in bioengineering applications for PD monitoring, providing a robust framework for reliable and continuous assessment of PD symptoms in daily living settings.
Share and Cite
MDPI and ACS Style
Shuqair, M.; Jimenez-Shahed, J.; Ghoraani, B.
Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors. Bioengineering 2024, 11, 689.
https://doi.org/10.3390/bioengineering11070689
AMA Style
Shuqair M, Jimenez-Shahed J, Ghoraani B.
Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors. Bioengineering. 2024; 11(7):689.
https://doi.org/10.3390/bioengineering11070689
Chicago/Turabian Style
Shuqair, Mustafa, Joohi Jimenez-Shahed, and Behnaz Ghoraani.
2024. "Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors" Bioengineering 11, no. 7: 689.
https://doi.org/10.3390/bioengineering11070689
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.