Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors
Long-term monitoring of real-life physical activity (PA) using wearable devices is increasingly used in clinical and epidemiological studies. The quality of the recorded data is an important issue, as unreliable data may negatively affect the outcome measures. A potential source of bias in PA assess...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/3/1117 |
_version_ | 1797484616882323456 |
---|---|
author | Sara Pagnamenta Karoline Blix Grønvik Kamiar Aminian Beatrix Vereijken Anisoara Paraschiv-Ionescu |
author_facet | Sara Pagnamenta Karoline Blix Grønvik Kamiar Aminian Beatrix Vereijken Anisoara Paraschiv-Ionescu |
author_sort | Sara Pagnamenta |
collection | DOAJ |
description | Long-term monitoring of real-life physical activity (PA) using wearable devices is increasingly used in clinical and epidemiological studies. The quality of the recorded data is an important issue, as unreliable data may negatively affect the outcome measures. A potential source of bias in PA assessment is the non-wearing of a device during the expected monitoring period. Identification of non-wear time is usually performed as a pre-processing step using data recorded by the accelerometer, which is the most common sensor used for PA analysis algorithms. The main issue is the correct differentiation between non-wear time, sleep time, and sedentary wake time, especially in frail older adults or patient groups. Based on the current state of the art, the objectives of this study were to (1) develop robust non-wearing detection algorithms based on data recorded with a wearable device that integrates acceleration and temperature sensors; (2) validate the algorithms using real-world data recorded according to an appropriate measurement protocol. A comparative evaluation of the implemented algorithms indicated better performances (99%, 97%, 99%, and 98% for sensitivity, specificity, accuracy, and negative predictive value, respectively) for an event-based detection algorithm, where the temperature sensor signal was appropriately processed to identify the timing of device removal/non-wear. |
first_indexed | 2024-03-09T23:07:58Z |
format | Article |
id | doaj.art-8aa5e3d0bbf9480284aece0aee30f5e3 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T23:07:58Z |
publishDate | 2022-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-8aa5e3d0bbf9480284aece0aee30f5e32023-11-23T17:50:45ZengMDPI AGSensors1424-82202022-02-01223111710.3390/s22031117Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable SensorsSara Pagnamenta0Karoline Blix Grønvik1Kamiar Aminian2Beatrix Vereijken3Anisoara Paraschiv-Ionescu4Ecole Polytechnique Federale de Lausanne (EPFL), Laboratory of Movement Analysis and Measurement (LMAM), CH-1015 Lausanne, SwitzerlandDepartment of Neuromedicine and Movement Science, Norwegian University of Science and Technology, N-7491 Trondheim, NorwayEcole Polytechnique Federale de Lausanne (EPFL), Laboratory of Movement Analysis and Measurement (LMAM), CH-1015 Lausanne, SwitzerlandDepartment of Neuromedicine and Movement Science, Norwegian University of Science and Technology, N-7491 Trondheim, NorwayEcole Polytechnique Federale de Lausanne (EPFL), Laboratory of Movement Analysis and Measurement (LMAM), CH-1015 Lausanne, SwitzerlandLong-term monitoring of real-life physical activity (PA) using wearable devices is increasingly used in clinical and epidemiological studies. The quality of the recorded data is an important issue, as unreliable data may negatively affect the outcome measures. A potential source of bias in PA assessment is the non-wearing of a device during the expected monitoring period. Identification of non-wear time is usually performed as a pre-processing step using data recorded by the accelerometer, which is the most common sensor used for PA analysis algorithms. The main issue is the correct differentiation between non-wear time, sleep time, and sedentary wake time, especially in frail older adults or patient groups. Based on the current state of the art, the objectives of this study were to (1) develop robust non-wearing detection algorithms based on data recorded with a wearable device that integrates acceleration and temperature sensors; (2) validate the algorithms using real-world data recorded according to an appropriate measurement protocol. A comparative evaluation of the implemented algorithms indicated better performances (99%, 97%, 99%, and 98% for sensitivity, specificity, accuracy, and negative predictive value, respectively) for an event-based detection algorithm, where the temperature sensor signal was appropriately processed to identify the timing of device removal/non-wear.https://www.mdpi.com/1424-8220/22/3/1117activity monitoringwearable devicesnon-wearing timeaccelerometertemperature sensorevent-based detection algorithms |
spellingShingle | Sara Pagnamenta Karoline Blix Grønvik Kamiar Aminian Beatrix Vereijken Anisoara Paraschiv-Ionescu Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors Sensors activity monitoring wearable devices non-wearing time accelerometer temperature sensor event-based detection algorithms |
title | Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors |
title_full | Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors |
title_fullStr | Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors |
title_full_unstemmed | Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors |
title_short | Putting Temperature into the Equation: Development and Validation of Algorithms to Distinguish Non-Wearing from Inactivity and Sleep in Wearable Sensors |
title_sort | putting temperature into the equation development and validation of algorithms to distinguish non wearing from inactivity and sleep in wearable sensors |
topic | activity monitoring wearable devices non-wearing time accelerometer temperature sensor event-based detection algorithms |
url | https://www.mdpi.com/1424-8220/22/3/1117 |
work_keys_str_mv | AT sarapagnamenta puttingtemperatureintotheequationdevelopmentandvalidationofalgorithmstodistinguishnonwearingfrominactivityandsleepinwearablesensors AT karolineblixgrønvik puttingtemperatureintotheequationdevelopmentandvalidationofalgorithmstodistinguishnonwearingfrominactivityandsleepinwearablesensors AT kamiaraminian puttingtemperatureintotheequationdevelopmentandvalidationofalgorithmstodistinguishnonwearingfrominactivityandsleepinwearablesensors AT beatrixvereijken puttingtemperatureintotheequationdevelopmentandvalidationofalgorithmstodistinguishnonwearingfrominactivityandsleepinwearablesensors AT anisoaraparaschivionescu puttingtemperatureintotheequationdevelopmentandvalidationofalgorithmstodistinguishnonwearingfrominactivityandsleepinwearablesensors |