1
|
Lendt C, Hansen N, Froböse I, Stewart T. Composite activity type and stride-specific energy expenditure estimation model for thigh-worn accelerometry. Int J Behav Nutr Phys Act 2024; 21:99. [PMID: 39256837 DOI: 10.1186/s12966-024-01646-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2024] [Accepted: 08/18/2024] [Indexed: 09/12/2024] Open
Abstract
BACKGROUND Accurately measuring energy expenditure during physical activity outside of the laboratory is challenging, especially on a large scale. Thigh-worn accelerometers have gained popularity due to the possibility to accurately detect physical activity types. The use of machine learning techniques for activity classification and energy expenditure prediction may improve accuracy over current methods. Here, we developed a novel composite energy expenditure estimation model by combining an activity classification model with a stride specific energy expenditure model for walking, running, and cycling. METHODS We first trained a supervised deep learning activity classification model using pooled data from available adult accelerometer datasets. The composite energy expenditure model was then developed and validated using additional data based on a sample of 69 healthy adult participants (49% female; age = 25.2 ± 5.8 years) who completed a standardised activity protocol with indirect calorimetry as the reference measure. RESULTS The activity classification model showed an overall accuracy of 99.7% across all five activity types during validation. The composite model for estimating energy expenditure achieved a mean absolute percentage error of 10.9%. For running, walking, and cycling, the composite model achieved a mean absolute percentage error of 6.6%, 7.9% and 16.1%, respectively. CONCLUSIONS The integration of thigh-worn accelerometers with machine learning models provides a highly accurate method for classifying physical activity types and estimating energy expenditure. Our novel composite model approach improves the accuracy of energy expenditure measurements and supports better monitoring and assessment methods in non-laboratory settings.
Collapse
Affiliation(s)
- Claas Lendt
- Institute of Movement Therapy and Movement-oriented Prevention and Rehabilitation, German Sport University Cologne, Cologne, Germany.
- Human Potential Centre, School of Sport and Recreation, Auckland University of Technology, Auckland, New Zealand.
| | - Niklas Hansen
- Institute of Movement Therapy and Movement-oriented Prevention and Rehabilitation, German Sport University Cologne, Cologne, Germany
| | - Ingo Froböse
- Institute of Movement Therapy and Movement-oriented Prevention and Rehabilitation, German Sport University Cologne, Cologne, Germany
| | - Tom Stewart
- Human Potential Centre, School of Sport and Recreation, Auckland University of Technology, Auckland, New Zealand
| |
Collapse
|
2
|
Vähä-Ypyä H, Husu P, Sievänen H, Vasankari T. Measurement of Sedentary Behavior-The Outcomes of the Angle for Posture Estimation (APE) Method. SENSORS (BASEL, SWITZERLAND) 2024; 24:2241. [PMID: 38610452 PMCID: PMC11014150 DOI: 10.3390/s24072241] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Revised: 03/28/2024] [Accepted: 03/29/2024] [Indexed: 04/14/2024]
Abstract
Hip-worn accelerometers are commonly used to assess habitual physical activity, but their accuracy in precisely measuring sedentary behavior (SB) is generally considered low. The angle for postural estimation (APE) method has shown promising accuracy in SB measurement. This method relies on the constant nature of Earth's gravity and the assumption that walking posture is typically upright. This study investigated how cardiorespiratory fitness (CRF) and body mass index (BMI) are related to APE output. A total of 3475 participants with adequate accelerometer wear time were categorized into three groups according to CRF or BMI. Participants in low CRF and high BMI groups spent more time in reclining and lying postures (APE ≥ 30°) and less time in sitting and standing postures (APE < 30°) than the other groups. Furthermore, the strongest partial Spearman correlation with CRF (r = 0.284) and BMI (r = -0.320) was observed for APE values typical for standing. The findings underscore the utility of the APE method in studying associations between SB and health outcomes. Importantly, this study emphasizes the necessity of reserving the term "sedentary behavior" for studies wherein the classification of SB is based on both intensity and posture.
Collapse
Affiliation(s)
- Henri Vähä-Ypyä
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland; (P.H.); (H.S.); (T.V.)
| | - Pauliina Husu
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland; (P.H.); (H.S.); (T.V.)
| | - Harri Sievänen
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland; (P.H.); (H.S.); (T.V.)
| | - Tommi Vasankari
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland; (P.H.); (H.S.); (T.V.)
- Faculty of Medicine and Health Technology, Tampere University, 33014 Tampere, Finland
| |
Collapse
|
3
|
Tam RM, Zablocki RW, Liu C, Narayan HK, Natarajan L, LaCroix AZ, Dillon L, Sakoulas E, Hartman SJ. Feasibility of a Health Coach Intervention to Reduce Sitting Time and Improve Physical Functioning Among Breast Cancer Survivors: Pilot Intervention Study. JMIR Cancer 2023; 9:e49934. [PMID: 38113082 PMCID: PMC10762618 DOI: 10.2196/49934] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 11/16/2023] [Accepted: 11/23/2023] [Indexed: 12/21/2023] Open
Abstract
BACKGROUND Sedentary behavior among breast cancer survivors is associated with increased risk of poor physical function and worse quality of life. While moderate to vigorous physical activity can improve outcomes for cancer survivors, many are unable to engage in that intensity of physical activity. Decreasing sitting time may be a more feasible behavioral target to potentially mitigate the impact of cancer and its treatments. OBJECTIVE The purpose of this study was to investigate the feasibility and preliminary impact of an intervention to reduce sitting time on changes to physical function and quality of life in breast cancer survivors, from baseline to a 3-month follow-up. METHODS Female breast cancer survivors with self-reported difficulties with physical function received one-on-one, in-person personalized health coaching sessions aimed at reducing sitting time. At baseline and follow-up, participants wore the activPAL (thigh-worn accelerometer; PAL Technologies) for 3 months and completed physical function tests (4-Meter Walk Test, Timed Up and Go, and 30-Second Chair Stand) and Patient-Reported Outcomes Measurement Information System (PROMIS) self-reported outcomes. Changes in physical function and sedentary behavior outcomes were assessed by linear mixed models. RESULTS On average, participants (n=20) were aged 64.5 (SD 9.4) years; had a BMI of 30.4 (SD 4.5) kg/m2; and identified as Black or African American (n=3, 15%), Hispanic or Latina (n=4, 20%), and non-Hispanic White (n=14, 55%). Average time since diagnosis was 5.8 (SD 2.2) years with participants receiving chemotherapy (n=8, 40%), radiotherapy (n=18, 90%), or endocrine therapy (n=17, 85%). The intervention led to significant reductions in sitting time: activPAL average daily sitting time decreased from 645.7 (SD 72.4) to 532.7 (SD 142.1; β=-112.9; P=.001) minutes and average daily long sitting bouts (bout length ≥20 min) decreased from 468.3 (SD 94.9) to 366.9 (SD 150.4; β=-101.4; P=.002) minutes. All physical function tests had significant improvements: on average, 4-Meter Walk Test performance decreased from 4.23 (SD 0.95) to 3.61 (SD 2.53; β=-.63; P=.002) seconds, Timed Up and Go performance decreased from 10.30 (SD 3.32) to 8.84 (SD 1.58; β=-1.46; P=.003) seconds, and 30-Second Chair Stand performance increased from 9.75 (SD 2.81) to 13.20 completions (SD 2.53; β=3.45; P<.001). PROMIS self-reported physical function score improved from 44.59 (SD 4.40) to 47.12 (SD 5.68; β=2.53; P=.05) and average fatigue decreased from 52.51 (SD 10.38) to 47.73 (SD 8.43; β=-4.78; P=.02). CONCLUSIONS This 3-month pilot study suggests that decreasing time spent sitting may be helpful for breast cancer survivors experiencing difficulties with physical function and fatigue. Reducing sitting time is a novel and potentially more feasible approach to improving health and quality of life in cancer survivors.
Collapse
Affiliation(s)
- Rowena M Tam
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
| | - Rong W Zablocki
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
| | - Chenyu Liu
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
| | - Hari K Narayan
- Department of Pediatrics, University of California, San Diego, La Jolla, CA, United States
- UC San Diego Moores Cancer Center, University of California San Diego, La Jolla, CA, United States
| | - Loki Natarajan
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
- UC San Diego Moores Cancer Center, University of California San Diego, La Jolla, CA, United States
| | - Andrea Z LaCroix
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
| | - Lindsay Dillon
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
| | - Eleanna Sakoulas
- UC San Diego Moores Cancer Center, University of California San Diego, La Jolla, CA, United States
| | - Sheri J Hartman
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California, San Diego, La Jolla, CA, United States
- UC San Diego Moores Cancer Center, University of California San Diego, La Jolla, CA, United States
| |
Collapse
|
4
|
Hibbing PR, Carlson JA, Steel C, Greenwood-Hickman MA, Nakandala S, Jankowska MM, Bellettiere J, Zou J, LaCroix AZ, Kumar A, Katzmarzyk PT, Natarajan L. Low movement, deep-learned sitting patterns, and sedentary behavior in the International Study of Childhood Obesity, Lifestyle and the Environment (ISCOLE). Int J Obes (Lond) 2023; 47:1100-1107. [PMID: 37580374 PMCID: PMC10714872 DOI: 10.1038/s41366-023-01364-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Revised: 07/27/2023] [Accepted: 08/08/2023] [Indexed: 08/16/2023]
Abstract
BACKGROUND/OBJECTIVES Sedentary behavior (SB) has both movement and postural components, but most SB research has only assessed low movement, especially in children. The purpose of this study was to compare estimates and health associations of SB when derived from a standard accelerometer cut-point, a novel sitting detection technique (CNN Hip Accelerometer Posture for Children; CHAP-Child), and both combined. METHODS Data were from the International Study of Childhood Obesity, Lifestyle, and the Environment (ISCOLE). Participants were 6103 children (mean ± SD age 10.4 ± 0.56 years) from 12 countries who wore an ActiGraph GT3X+ accelerometer on the right hip for approximately one week. We calculated SB time, mean SB bout duration, and SB breaks using a cut-point (SBmovement), CHAP-Child (SBposture), and both methods combined (SBcombined). Mixed effects regression was used to test associations of SB variables with pediatric obesity variables (waist circumference, body fat percentage, and body mass index z-score). RESULTS After adjusting for MVPA, SBposture showed several significant obesity associations favoring lower mean SB bout duration (b = 0.251-0.449; all p < 0.001) and higher SB breaks (b = -0.005--0.052; all p < 0.001). Lower total SB was unexpectedly related to greater obesity (b = -0.077--0.649; p from <0.001-0.02). For mean SB bout duration and SB breaks, more associations were observed for SBposture (n = 5) than for SBmovement (n = 3) or SBcombined (n = 1), and tended to have larger magnitude as well. CONCLUSIONS Using traditional measures of low movement as a surrogate for SB may lead to underestimated or undetected adverse associations between SB and obesity. CHAP-Child allows assessment of sitting posture using hip-worn accelerometers. Ongoing work is needed to understand how low movement and posture are related to one another, as well as their potential health implications.
Collapse
Affiliation(s)
- Paul R Hibbing
- Department of Kinesiology and Nutrition, University of Illinois Chicago, Chicago, IL, USA.
- Center for Children's Healthy Lifestyles & Nutrition, Children's Mercy Kansas City, Kansas City, MO, USA.
| | - Jordan A Carlson
- Center for Children's Healthy Lifestyles & Nutrition, Children's Mercy Kansas City, Kansas City, MO, USA
- Department of Pediatrics, University of Missouri Kansas City, Kansas City, MO, USA
| | - Chelsea Steel
- Center for Children's Healthy Lifestyles & Nutrition, Children's Mercy Kansas City, Kansas City, MO, USA
| | | | - Supun Nakandala
- Databricks Inc, San Francisco, CA, USA
- Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA
| | - Marta M Jankowska
- Beckman Research Institute, Population Sciences, City of Hope, Duarte, CA, USA
| | - John Bellettiere
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA, USA
| | - Jingjing Zou
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA, USA
| | - Andrea Z LaCroix
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA, USA
| | - Arun Kumar
- Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA
| | | | - Loki Natarajan
- Herbert Wertheim School of Public Health and Human Longevity Science, University of California San Diego, La Jolla, CA, USA
| |
Collapse
|
5
|
Vähä-Ypyä H, Bretterhofer J, Husu P, Windhaber J, Vasankari T, Titze S, Sievänen H. Performance of Different Accelerometry-Based Metrics to Estimate Oxygen Consumption during Track and Treadmill Locomotion over a Wide Intensity Range. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23115073. [PMID: 37299803 DOI: 10.3390/s23115073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Revised: 05/20/2023] [Accepted: 05/23/2023] [Indexed: 06/12/2023]
Abstract
Accelerometer data can be used to estimate incident oxygen consumption (VO2) during physical activity. Relationships between the accelerometer metrics and VO2 are typically determined using specific walking or running protocols on a track or treadmill. In this study, we compared the predictive performance of three different metrics based on the mean amplitude deviation (MAD) of the raw three-dimensional acceleration signal during maximal tests performed on a track or treadmill. A total of 53 healthy adult volunteers participated in the study, 29 performed the track test and 24 the treadmill test. During the tests, the data were collected using hip-worn triaxial accelerometers and metabolic gas analyzers. Data from both tests were pooled for primary statistical analysis. For typical walking speeds at VO2 less than 25 mL/kg/min, accelerometer metrics accounted for 71-86% of the variation in VO2. For typical running speeds starting from VO2 of 25 mL/kg/min up to over 60 mL/kg/min, 32-69% of the variation in VO2 could be explained, while the test type had an independent effect on the results, except for the conventional MAD metrics. The MAD metric is the best predictor of VO2 during walking, but the poorest during running. Depending on the intensity of locomotion, the choice of proper accelerometer metrics and test type may affect the validity of the prediction of incident VO2.
Collapse
Affiliation(s)
- Henri Vähä-Ypyä
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland
| | - Jakob Bretterhofer
- Institute of Human Movement Science, Sport and Health, University of Graz, 8010 Graz, Austria
| | - Pauliina Husu
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland
| | - Jana Windhaber
- Sports Medicine Performance and Movement Analysis, Medical University of Graz, 8010 Graz, Austria
| | - Tommi Vasankari
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland
| | - Sylvia Titze
- Institute of Human Movement Science, Sport and Health, University of Graz, 8010 Graz, Austria
| | - Harri Sievänen
- The UKK Institute for Health Promotion Research, 33500 Tampere, Finland
| |
Collapse
|