Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior
<strong>Background</strong>: Recent evidence suggests that physical activity (PA) and sedentary behavior (SB) exert independent effects on health. Therefore, measurement methods that can accurately assess both constructs are needed. <strong>Objective</strong>: To compare the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2016-05-01
|
| Series: | AIMS Public Health |
| Subjects: | |
| Online Access: | http://www.aimspress.com/aimsph/article/783/fulltext.html |
| _version_ | 1818135819719802880 |
|---|---|
| author | Alexander H.K. Montoye James M. Pivarnik Lanay M. Mudd Subir Biswas Karin A. Pfeiffer |
| author_facet | Alexander H.K. Montoye James M. Pivarnik Lanay M. Mudd Subir Biswas Karin A. Pfeiffer |
| author_sort | Alexander H.K. Montoye |
| collection | DOAJ |
| description | <strong>Background</strong>: Recent evidence suggests that physical activity (PA) and sedentary behavior (SB) exert independent effects on health. Therefore, measurement methods that can accurately assess both constructs are needed. <strong>Objective</strong>: To compare the accuracy of accelerometers placed on the hip, thigh, and wrists, coupled with machine learning models, for measurement of PA intensity category (SB, light-intensity PA [LPA], and moderate- to vigorous-intensity PA [MVPA]) and breaks in SB. <strong>Methods</strong>: Forty young adults (21 female; age 22.0 ± 4.2 years) participated in a 90-minute semi-structured protocol, performing 13 activities (three sedentary, 10 non-sedentary) for 3–10 minutes each. Participants chose activity order, duration, and intensity. Direct observation (DO) was used as a criterion measure of PA intensity category, and transitions from SB to a non-sedentary activity were breaks in SB. Participants wore four accelerometers (right hip, right thigh, and both wrists), and a machine learning model was created for each accelerometer to predict PA intensity category. Sensitivity and specificity for PA intensity category classification were calculated and compared across accelerometers using repeated measures analysis of variance, and the number of breaks in SB was compared using repeated measures analysis of variance. <strong>Results</strong>: Sensitivity and specificity values for the thigh-worn accelerometer were higher than for wrist- or hip-worn accelerometers, > 99% for all PA intensity categories. Sensitivity and specificity for the hip-worn accelerometer were 87–95% and 93–97%. The left wrist-worn accelerometer had sensitivities and specificities of > 97% for SB and LPA and 91–95% for MVPA, whereas the right wrist-worn accelerometer had sensitivities and specificities of 93–99% for SB and LPA but 67–84% for MVPA. The thigh-worn accelerometer had high accuracy for breaks in SB; all other accelerometers overestimated breaks in SB. <strong>Conclusion</strong>: Coupled with machine learning modeling, the thigh-worn accelerometer should be considered when objectively assessing PA and SB. |
| first_indexed | 2024-12-11T09:30:34Z |
| format | Article |
| id | doaj.art-2788678c18bc43eaa0d9b1efccb057cb |
| institution | Directory Open Access Journal |
| issn | 2327-8994 |
| language | English |
| last_indexed | 2024-12-11T09:30:34Z |
| publishDate | 2016-05-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Public Health |
| spelling | doaj.art-2788678c18bc43eaa0d9b1efccb057cb2022-12-22T01:13:01ZengAIMS PressAIMS Public Health2327-89942016-05-013229831210.3934/publichealth.2016.2.298publichealth-03-00298Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary BehaviorAlexander H.K. Montoye0James M. Pivarnik1Lanay M. Mudd2Subir Biswas3Karin A. Pfeiffer4Clinical Exercise Physiology Program, School of Kinesiology, Ball State University, Muncie, IN, USHuman Energy Research Laboratory, Department of Kinesiology, Michigan State University, East Lansing, MI, USHuman Energy Research Laboratory, Department of Kinesiology, Michigan State University, East Lansing, MI, USNetworked Embedded & Wireless Systems Laboratory, Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USHuman Energy Research Laboratory, Department of Kinesiology, Michigan State University, East Lansing, MI, US<strong>Background</strong>: Recent evidence suggests that physical activity (PA) and sedentary behavior (SB) exert independent effects on health. Therefore, measurement methods that can accurately assess both constructs are needed. <strong>Objective</strong>: To compare the accuracy of accelerometers placed on the hip, thigh, and wrists, coupled with machine learning models, for measurement of PA intensity category (SB, light-intensity PA [LPA], and moderate- to vigorous-intensity PA [MVPA]) and breaks in SB. <strong>Methods</strong>: Forty young adults (21 female; age 22.0 ± 4.2 years) participated in a 90-minute semi-structured protocol, performing 13 activities (three sedentary, 10 non-sedentary) for 3–10 minutes each. Participants chose activity order, duration, and intensity. Direct observation (DO) was used as a criterion measure of PA intensity category, and transitions from SB to a non-sedentary activity were breaks in SB. Participants wore four accelerometers (right hip, right thigh, and both wrists), and a machine learning model was created for each accelerometer to predict PA intensity category. Sensitivity and specificity for PA intensity category classification were calculated and compared across accelerometers using repeated measures analysis of variance, and the number of breaks in SB was compared using repeated measures analysis of variance. <strong>Results</strong>: Sensitivity and specificity values for the thigh-worn accelerometer were higher than for wrist- or hip-worn accelerometers, > 99% for all PA intensity categories. Sensitivity and specificity for the hip-worn accelerometer were 87–95% and 93–97%. The left wrist-worn accelerometer had sensitivities and specificities of > 97% for SB and LPA and 91–95% for MVPA, whereas the right wrist-worn accelerometer had sensitivities and specificities of 93–99% for SB and LPA but 67–84% for MVPA. The thigh-worn accelerometer had high accuracy for breaks in SB; all other accelerometers overestimated breaks in SB. <strong>Conclusion</strong>: Coupled with machine learning modeling, the thigh-worn accelerometer should be considered when objectively assessing PA and SB.http://www.aimspress.com/aimsph/article/783/fulltext.htmlmachine learningartificial neural networkpattern recognitionactivity monitoractivity trackerenergy expenditure |
| spellingShingle | Alexander H.K. Montoye James M. Pivarnik Lanay M. Mudd Subir Biswas Karin A. Pfeiffer Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior AIMS Public Health machine learning artificial neural network pattern recognition activity monitor activity tracker energy expenditure |
| title | Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior |
| title_full | Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior |
| title_fullStr | Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior |
| title_full_unstemmed | Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior |
| title_short | Validation and Comparison of Accelerometers Worn on the Hip, Thigh, and Wrists for Measuring Physical Activity and Sedentary Behavior |
| title_sort | validation and comparison of accelerometers worn on the hip thigh and wrists for measuring physical activity and sedentary behavior |
| topic | machine learning artificial neural network pattern recognition activity monitor activity tracker energy expenditure |
| url | http://www.aimspress.com/aimsph/article/783/fulltext.html |
| work_keys_str_mv | AT alexanderhkmontoye validationandcomparisonofaccelerometerswornonthehipthighandwristsformeasuringphysicalactivityandsedentarybehavior AT jamesmpivarnik validationandcomparisonofaccelerometerswornonthehipthighandwristsformeasuringphysicalactivityandsedentarybehavior AT lanaymmudd validationandcomparisonofaccelerometerswornonthehipthighandwristsformeasuringphysicalactivityandsedentarybehavior AT subirbiswas validationandcomparisonofaccelerometerswornonthehipthighandwristsformeasuringphysicalactivityandsedentarybehavior AT karinapfeiffer validationandcomparisonofaccelerometerswornonthehipthighandwristsformeasuringphysicalactivityandsedentarybehavior |