Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements
Tremor is one of the main symptoms of Parkinson’s Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the pati...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/19/4215 |
_version_ | 1811212919153623040 |
---|---|
author | Murtadha D. Hssayeni Joohi Jimenez-Shahed Michelle A. Burack Behnaz Ghoraani |
author_facet | Murtadha D. Hssayeni Joohi Jimenez-Shahed Michelle A. Burack Behnaz Ghoraani |
author_sort | Murtadha D. Hssayeni |
collection | DOAJ |
description | Tremor is one of the main symptoms of Parkinson’s Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the patients’ tremor experience in their day-to-day life. Our objective in this paper was to develop algorithms that, combined with wearable sensors, can estimate total Parkinsonian tremor as the patients performed a variety of free body movements. We developed two methods: an ensemble model based on gradient tree boosting and a deep learning model based on long short-term memory (LSTM) networks. The developed methods were assessed on gyroscope sensor data from 24 PD subjects. Our analysis demonstrated that the method based on gradient tree boosting provided a high correlation (<i>r</i> = 0.96 using held-out testing and <i>r</i> = 0.93 using subject-based, leave-one-out cross-validation) between the estimated and clinically assessed tremor subscores in comparison to the LSTM-based method with a moderate correlation (<i>r</i> = 0.84 using held-out testing and <i>r</i> = 0.77 using subject-based, leave-one-out cross-validation). These results indicate that our approach holds great promise in providing a full spectrum of the patients’ tremor from continuous monitoring of the subjects’ movement in their natural environment. |
first_indexed | 2024-04-12T05:37:30Z |
format | Article |
id | doaj.art-208138ef64764558ba96e4d380af19a3 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-12T05:37:30Z |
publishDate | 2019-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-208138ef64764558ba96e4d380af19a32022-12-22T03:45:47ZengMDPI AGSensors1424-82202019-09-011919421510.3390/s19194215s19194215Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body MovementsMurtadha D. Hssayeni0Joohi Jimenez-Shahed1Michelle A. Burack2Behnaz Ghoraani3Department of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USAIcahn School of Medicine at Mount Sinai, New York, NY 10029, USADepartment of Neurology, University of Rochester Medical Center, Rochester, NY 14642, USADepartment of Computer and Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL 33431, USATremor is one of the main symptoms of Parkinson’s Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the patients’ tremor experience in their day-to-day life. Our objective in this paper was to develop algorithms that, combined with wearable sensors, can estimate total Parkinsonian tremor as the patients performed a variety of free body movements. We developed two methods: an ensemble model based on gradient tree boosting and a deep learning model based on long short-term memory (LSTM) networks. The developed methods were assessed on gyroscope sensor data from 24 PD subjects. Our analysis demonstrated that the method based on gradient tree boosting provided a high correlation (<i>r</i> = 0.96 using held-out testing and <i>r</i> = 0.93 using subject-based, leave-one-out cross-validation) between the estimated and clinically assessed tremor subscores in comparison to the LSTM-based method with a moderate correlation (<i>r</i> = 0.84 using held-out testing and <i>r</i> = 0.77 using subject-based, leave-one-out cross-validation). These results indicate that our approach holds great promise in providing a full spectrum of the patients’ tremor from continuous monitoring of the subjects’ movement in their natural environment.https://www.mdpi.com/1424-8220/19/19/4215parkinsonian tremorcontinuous monitoringwearable sensorsgradient tree boostingdeep learninglstm |
spellingShingle | Murtadha D. Hssayeni Joohi Jimenez-Shahed Michelle A. Burack Behnaz Ghoraani Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements Sensors parkinsonian tremor continuous monitoring wearable sensors gradient tree boosting deep learning lstm |
title | Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements |
title_full | Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements |
title_fullStr | Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements |
title_full_unstemmed | Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements |
title_short | Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements |
title_sort | wearable sensors for estimation of parkinsonian tremor severity during free body movements |
topic | parkinsonian tremor continuous monitoring wearable sensors gradient tree boosting deep learning lstm |
url | https://www.mdpi.com/1424-8220/19/19/4215 |
work_keys_str_mv | AT murtadhadhssayeni wearablesensorsforestimationofparkinsoniantremorseverityduringfreebodymovements AT joohijimenezshahed wearablesensorsforestimationofparkinsoniantremorseverityduringfreebodymovements AT michelleaburack wearablesensorsforestimationofparkinsoniantremorseverityduringfreebodymovements AT behnazghoraani wearablesensorsforestimationofparkinsoniantremorseverityduringfreebodymovements |