The CNN Hip Accelerometer Posture (CHAP) Method for Classifying Sitting Patterns from Hip Accelerometers: A Validation Study

Greenwood-Hickman, Mikael Anne; Nakandala, Supun; Jankowska, Marta M.; Rosenberg, Dori E.; Tuz-Zahra, Fatima; Bellettiere, John; Carlson, Jordan; Hibbing, Paul R.; Zou, Jingjing; LaCroix, Andrea Z.; Kumar, Arun

doi:10.1249/mss.0000000000002705

Cited by 19 publications

(32 citation statements)

References 50 publications

(73 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although similar methods for estimating sedentary patterns from ActiGraph data have been developed in adults [20,21], CHAP-child is the only such method developed specifically for use in children and appeared to perform better than these previous adult methods in their target populations. This shows the value of deep learning approaches, consistent with findings for other CHAP models that have been developed for adults and older adults [22]. All of these CHAP models have shown similar validity, though some indicators were lower for children than adults and/or older adults.…”

Section: Discussionsupporting

confidence: 84%

“…Details of the machine learning architecture and training procedures have been previously published [22,36], with additional information available at https:// github. com/ ADALa bUCSD/ DeepP ostur es.…”

Section: Chap-child Model Developmentmentioning

confidence: 99%

“…To accelerate this field of research, methods are needed that can improve posture classification from hip-worn accelerometers and be applied to existing and future datasets. Existing research in this area has shown that it is feasible to develop such methods, though the small number of previous studies have been limited to adults [20][21][22]. Thus, there is a need to develop hipworn accelerometer posture classification methods for children to improve the quality of research investigating health impacts of children's sedentary time and patterns [3,[6][7][8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CHAP-child: an open source method for estimating sit-to-stand transitions and sedentary bout patterns from hip accelerometers among children

Carlson

Ridgers

Nakandala

et al. 2022

Int J Behav Nutr Phys Act

Self Cite

View full text Add to dashboard Cite

Background Hip-worn accelerometer cut-points have poor validity for assessing children’s sedentary time, which may partly explain the equivocal health associations shown in prior research. Improved processing/classification methods for these monitors would enrich the evidence base and inform the development of more effective public health guidelines. The present study aimed to develop and evaluate a novel computational method (CHAP-child) for classifying sedentary time from hip-worn accelerometer data. Methods Participants were 278, 8–11-year-olds recruited from nine primary schools in Melbourne, Australia with differing socioeconomic status. Participants concurrently wore a thigh-worn activPAL (ground truth) and hip-worn ActiGraph (test measure) during up to 4 seasonal assessment periods, each lasting up to 8 days. activPAL data were used to train and evaluate the CHAP-child deep learning model to classify each 10-s epoch of raw ActiGraph acceleration data as sitting or non-sitting, creating comparable information from the two monitors. CHAP-child was evaluated alongside the current practice 100 counts per minute (cpm) method for hip-worn ActiGraph monitors. Performance was tested for each 10-s epoch and for participant-season level sedentary time and bout variables (e.g., mean bout duration). Results Across participant-seasons, CHAP-child correctly classified each epoch as sitting or non-sitting relative to activPAL, with mean balanced accuracy of 87.6% (SD = 5.3%). Sit-to-stand transitions were correctly classified with mean sensitivity of 76.3% (SD = 8.3). For most participant-season level variables, CHAP-child estimates were within ± 11% (mean absolute percent error [MAPE]) of activPAL, and correlations between CHAP-child and activPAL were generally very large (> 0.80). For the current practice 100 cpm method, most MAPEs were greater than ± 30% and most correlations were small or moderate (≤ 0.60) relative to activPAL. Conclusions There was strong support for the concurrent validity of the CHAP-child classification method, which allows researchers to derive activPAL-equivalent measures of sedentary time, sit-to-stand transitions, and sedentary bout patterns from hip-worn triaxial ActiGraph data. Applying CHAP-child to existing datasets may provide greater insights into the potential impacts and influences of sedentary time in children.

show abstract

Section: Discussionsupporting

confidence: 84%

Section: Chap-child Model Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

CHAP-child: an open source method for estimating sit-to-stand transitions and sedentary bout patterns from hip accelerometers among children

Carlson

Ridgers

Nakandala

et al. 2022

Int J Behav Nutr Phys Act

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, it should be noted that waist-worn ActiGraph accelerometers are limited in measuring stationary behavior, as the device does not measure posture or context, as defined by the consensus definition provided by the Sedentary Behaviour Research Network (SBRN) ( Tremblay et al, 2017 ). Further investigation of sedentary behavior findings is warranted and would be enhanced with the inclusion of devices that capture postural positions or by classifying sedentary patterns and sedentary behavior from hip-worn ActiGraph devices using machine learning algorithms ( Greenwood-Hickman et al, 2021 ).…”

Section: Discussionmentioning

confidence: 99%

Daily and hourly patterns of physical activity and sedentary behavior of older adults: Atherosclerosis risk in communities (ARIC) study

Dooley

Pompeii

Palta

et al. 2022

Preventive Medicine Reports

View full text Add to dashboard Cite

“…The ability to gather activity data has forged ahead of the human ability to easily understand the relevance and importance of that data. Critically, the data are neither standardised nor interoperable, arising from a broad range of devices and software which quantify SB and activity differently while also providing a multitude of diversely quantifiable variables [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. In this data-rich but information-poor environment [ 29 ], what to measure and report is challenging, often arbitrary and ineffective for research synthesis.…”

Section: Introductionmentioning

confidence: 99%

A Standardised Core Outcome Set for Measurement and Reporting Sedentary Behaviour Interventional Research: The CROSBI Consensus Study

Curran

Dowd²,

Peiris

et al. 2022

IJERPH

View full text Add to dashboard Cite

Heterogeneity of descriptors and outcomes measured and reported in sedentary behaviour (SB) research hinder the meta-analysis of data and accumulation of evidence. The objective of the Core Research Outcomes for Sedentary Behaviour Interventions (CROSBI) consensus study was to identify and validate, a core outcome set (COS) to report (what, how, when to measure) in interventional sedentary behaviour studies. Outcomes, extracted from a systematic literature review, were categorized into domains and data items (COS v0.0). International experts (n = 5) provided feedback and identified additional items, which were incorporated into COS v0.1. A two round online Delphi survey was conducted to seek consensus from a wider stakeholder group and outcomes that achieved consensus in the second round COS (v0.2), were ratified by the expert panel. The final COS (v1.0) contains 53 data items across 12 domains, relating to demographics, device details, wear-time criteria, wear-time measures, posture-related measures, sedentary breaks, sedentary bouts and physical activity. Notably, results indicate that sedentary behaviour outcomes should be measured by devices that include an inclinometry or postural function. The proposed standardised COS is available openly to enhance the accumulation of pooled evidence in future sedentary behaviour intervention research and practice.

show abstract

The CNN Hip Accelerometer Posture (CHAP) Method for Classifying Sitting Patterns from Hip Accelerometers: A Validation Study

Abstract: Supplemental digital content is available in the text.

Cited by 19 publications

References 50 publications

CHAP-child: an open source method for estimating sit-to-stand transitions and sedentary bout patterns from hip accelerometers among children

CHAP-child: an open source method for estimating sit-to-stand transitions and sedentary bout patterns from hip accelerometers among children

Daily and hourly patterns of physical activity and sedentary behavior of older adults: Atherosclerosis risk in communities (ARIC) study

A Standardised Core Outcome Set for Measurement and Reporting Sedentary Behaviour Interventional Research: The CROSBI Consensus Study

Contact Info

Product

Resources

About