Personalised Accelerometer Cut-point Prediction for Older Adults’ Movement Behaviours using a Machine Learning approach

Nnamoko, Nonso; Cabrera-Diego, Luis Adrián; Campbell, Daniel George; Sanders, George; Fairclough, Stuart J.; Korkontzelos, Ioannis

doi:10.1016/j.cmpb.2021.106165

Cited by 4 publications

(4 citation statements)

References 61 publications

(116 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the findings presented in this study are for wrist-worn acceleration data; although the methodology presented should, in principle, be applicable to other body placements, specific detailed thresholds and findings reported herein would be different for acceleration data recorded elsewhere (e.g., on the hip), as previous work has shown [15,24,49]. Finally, we did not consider age-, gender-, and motor-competence-specific analyses due to the relatively limited sample size to perform these detailed stratifications: there is some work that suggests that these affect accelerometer outputs, calling for more personalized threshold-based methods [50,51].…”

Section: Discussionmentioning

confidence: 86%

Investigating Wrist-Based Acceleration Summary Measures across Different Sample Rates towards 24-Hour Physical Activity and Sleep Profile Assessment

Tsanas

2022

Sensors

View full text Add to dashboard Cite

Wrist-worn wearable sensors have attracted considerable research interest because of their potential in providing continuous, longitudinal, non-invasive measurements, leading to insights into Physical Activity (PA), sleep, and circadian variability. Three key practical considerations for research-grade wearables are as follows: (a) choosing an appropriate sample rate, (b) summarizing raw three-dimensional accelerometry data for further processing (accelerometry summary measures), and (c) accurately estimating PA levels and sleep towards understanding participants’ 24-hour profiles. We used the CAPTURE-24 dataset, where 148 participants concurrently wore a wrist-worn three-dimensional accelerometer and a wearable camera over approximately 24 h to obtain minute-by-minute labels: sleep; and sedentary light, moderate, and vigorous PA. We propose a new acceleration summary measure, the Rate of Change Acceleration Movement (ROCAM), and compare its performance against three established approaches summarizing three-dimensional acceleration data towards replicating the minute-by-minute labels. Moreover, we compare findings where the acceleration data was sampled at 10, 25, 50, and 100 Hz. We demonstrate the competitive advantage of ROCAM towards estimating the five labels (80.2% accuracy) and building 24-hour profiles where the sample rate of 10 Hz is fully sufficient. Collectively, these findings provide insights facilitating the deployment of large-scale longitudinal actigraphy data processing towards 24-hour PA and sleep-profile assessment.

show abstract

Section: Discussionmentioning

confidence: 86%

Investigating Wrist-Based Acceleration Summary Measures across Different Sample Rates towards 24-Hour Physical Activity and Sleep Profile Assessment

Tsanas

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the descriptive data presented in this manuscript can be compared in the future with as many alternative cut-points as needed, for example if the VO 2net age-equivalent cut-points were expanded to the whole human lifespan [ 38 ]. In the same vein, research in the area of cut-point-based metrics is moving towards post-data collection approaches such as personalized accelerometer cut-points using machine learning [ 10 ].…”

Section: Discussionmentioning

confidence: 99%

“…Despite recent efforts determining cut-points in people above 70 years of age, there are no established cut-points for 100-year-old or frail individuals. The use of cut-points validated in younger older adults would result in a floor effect when applied to centenarians, with the time spent by centenarians in LiPA or MVPA being under-estimated due to the inappropriateness of the “one size fits all” approach [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Physical Activity in Centenarians beyond Cut-Point-Based Accelerometer Metrics

Hernández-Vicente

Marín-Puyalto

Pueyo

et al. 2022

IJERPH

View full text Add to dashboard Cite

This study described and compared physical activity (PA) characteristics at the end of the human lifespan using conventional cut-point-based versus cut-point-free accelerometer metrics. Eighteen institutionalized centenarians (101.5 ± 2.1 years, 72.2% female, 89% frail) wore the wrist GENEActiv accelerometer for 7 days. Conventional metrics, such as time spent in light-intensity PA (LiPA) and moderate-to-vigorous intensity PA (MVPA) were calculated according to published cut-points for adults and older adults. The following cut-point-free metrics were evaluated: average acceleration, intensity gradient and Mx metrics. Depending on the cut-point, centenarians accumulated a median of 15–132 min/day of LiPA and 3–15 min/day of MVPA. The average acceleration was 9.2 mg [Q1: 6.7 mg–Q3: 12.6 mg] and the intensity gradient was −3.19 [−3.34–−3.12]. The distribution of Z-values revealed positive skew for MVPA, indicating a potential floor effect, whereas the skew magnitude was attenuated for cut-point-free metrics such as intensity gradient or M5. However, both cut-point-based and cut-point-free metrics were similarly positively associated with functional independence, cognitive and physical capacities. This is the first time that PA has been described in centenarians using cut-point-free metrics. Our results suggest that new analytical approaches could overcome cut-point limitations when studying the oldest-old. Future studies using these new cut-point-free PA metrics are warranted to provide more complete and comparable information across groups and populations.

show abstract

“…For instance, Van Kuppevelt et al [6] used the HSMM model to establish accelerometer cut-point thresholds, while Montoye et al [7] utilized DL algorithms to search for cut-points of various activity intensities based on human basic characteristics. Additionally, Nnamoko's team [8] predicted personalized accelerometer cut-points for the elderly's exercise behavior through machine learning and compared the cut-point prediction effects of various models on wrist-worn and hip-worn accelerometers. The results revealed that machine learning models outperformed traditional fixed cut-points, and customized optimized models exhibited superior performance compared to generic models [9] .…”

Section: Introductionmentioning

confidence: 99%