Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders
Smartwatches provide technology-based assessments in Parkinson’s disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A compar...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/9/3139 |
_version_ | 1797535604796293120 |
---|---|
author | Julian Varghese Catharina Marie van Alen Michael Fujarski Georg Stefan Schlake Julitta Sucker Tobias Warnecke Christine Thomas |
author_facet | Julian Varghese Catharina Marie van Alen Michael Fujarski Georg Stefan Schlake Julitta Sucker Tobias Warnecke Christine Thomas |
author_sort | Julian Varghese |
collection | DOAJ |
description | Smartwatches provide technology-based assessments in Parkinson’s disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders. |
first_indexed | 2024-03-10T11:47:47Z |
format | Article |
id | doaj.art-fddf2d23f8274b7eacea001c324f65a7 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T11:47:47Z |
publishDate | 2021-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-fddf2d23f8274b7eacea001c324f65a72023-11-21T18:00:40ZengMDPI AGSensors1424-82202021-04-01219313910.3390/s21093139Sensor Validation and Diagnostic Potential of Smartwatches in Movement DisordersJulian Varghese0Catharina Marie van Alen1Michael Fujarski2Georg Stefan Schlake3Julitta Sucker4Tobias Warnecke5Christine Thomas6Institute of Medical Informatics, University of Münster, 48149 Münster, GermanyInstitute of Geophysics, University of Münster, 48149 Münster, GermanyInstitute of Medical Informatics, University of Münster, 48149 Münster, GermanyInstitute of Medical Informatics, University of Münster, 48149 Münster, GermanyInstitute of Medical Informatics, University of Münster, 48149 Münster, GermanyDepartment of Neurology, University Hospital Münster, 48149 Münster, GermanyInstitute of Geophysics, University of Münster, 48149 Münster, GermanySmartwatches provide technology-based assessments in Parkinson’s disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders.https://www.mdpi.com/1424-8220/21/9/3139smartwatchesartificial intelligencemovement disordersParkinson’s disease |
spellingShingle | Julian Varghese Catharina Marie van Alen Michael Fujarski Georg Stefan Schlake Julitta Sucker Tobias Warnecke Christine Thomas Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders Sensors smartwatches artificial intelligence movement disorders Parkinson’s disease |
title | Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders |
title_full | Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders |
title_fullStr | Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders |
title_full_unstemmed | Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders |
title_short | Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders |
title_sort | sensor validation and diagnostic potential of smartwatches in movement disorders |
topic | smartwatches artificial intelligence movement disorders Parkinson’s disease |
url | https://www.mdpi.com/1424-8220/21/9/3139 |
work_keys_str_mv | AT julianvarghese sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT catharinamarievanalen sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT michaelfujarski sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT georgstefanschlake sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT julittasucker sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT tobiaswarnecke sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders AT christinethomas sensorvalidationanddiagnosticpotentialofsmartwatchesinmovementdisorders |