A Device Agnostic Approach to Predict Children's Activity from Consumer Wearable Accelerometer Data: A Proof-of-Concept Study.

INTRODUCTION: This study examined the potential of a device agnostic approach for predicting physical activity from consumer wearable accelerometry compared with a research-grade accelerometry. METHODS: Seventy-five 5- to 12-year-olds (58% male, 63% White) participated in a 60-min protocol. Children wore wrist-placed consumer wearables (Apple Watch Series 7 and Garmin Vivoactive 4) and a research-grade device (ActiGraph GT9X) concurrently with an indirect calorimeter (COSMED K5). Activity intensities (i.e., inactive, light, moderate-to-vigorous physical activity) were estimated via indirect calorimetry (criterion), and the Hildebrand thresholds were applied to the raw accelerometer data from the consumer wearables and research-grade device. Epoch-by-epoch (e.g., weighted sensitivity, specificity) and discrepancy (e.g., mean bias, absolute error) analyses evaluated agreement between accelerometry-derived and criterion estimates. Equivalence testing evaluated the equivalence of estimates produced by the consumer wearables and ActiGraph. RESULTS: Estimates produced by the raw accelerometry data from ActiGraph, Apple, and Garmin produced similar criterion agreement with weighted sensitivity = 68.2% (95% confidence interval (CI), 67.1%-69.3%), 73.0% (95% CI, 71.8%-74.3%), and 66.6% (95% CI, 65.7%-67.5%), respectively, and weighted specificity = 84.4% (95% CI, 83.6%-85.2%), 82.0% (95% CI, 80.6%-83.4%), and 75.3% (95% CI, 74.7%-75.9%), respectively. Apple Watch produced the lowest mean bias (inactive, -4.0 ± 4.5; light activity, 2.1 ± 4.0) and absolute error (inactive, 4.9 ± 3.4; light activity, 3.6 ± 2.7) for inactive and light physical activity minutes. For moderate-to-vigorous physical activity, ActiGraph produced the lowest mean bias (1.0 ± 2.9) and absolute error (2.8 ± 2.4). No ActiGraph and consumer wearable device estimates were statistically significantly equivalent. CONCLUSIONS: Raw accelerometry estimated inactive and light activity from wrist-placed consumer wearables performed similarly to, if not better than, a research-grade device, when compared with indirect calorimetry. This proof-of-concept study highlights the potential of device-agnostic methods for quantifying physical activity intensity via consumer wearables.

Understanding Accelerated Summer Body Mass Index Gain by Tracking Changes in Children's Height, Weight, and Body Mass Index Throughout the Year.

Background: Drivers of summer body mass index (BMI) gain in children remain unclear. The Circadian and Circannual Rhythm Model (CCRM) posits summer BMI gain is biologically driven, while the Structured Days Hypothesis (SDH) proposes it is driven by reduced structure. Objectives: Identify the mechanisms driving children's seasonal BMI gain through the CCRM and SDH. Methods: Children's (N = 147, mean age = 8.2 years) height and weight were measured monthly during the school year, and once in summer (July-August). BMI z-score (zBMI) was calculated using CDC growth charts. Behaviors were measured once per season. Mixed methods regression estimated monthly percent change in children's height (%HΔ), weight (%WΔ), and monthly zBMI for school year vs. summer vacation, seasonally, and during school months with no breaks vs. school months with a break ≥1 week. Results: School year vs. summer vacation analyses showed accelerations in children's %WΔ (Δ = 0.9, Standard Error (SE) = 0.1 vs. Δ = 1.4, SE = 0.1) and zBMI (Δ = -0.01, SE = 0.01 vs. Δ = 0.04, SE = 0.3) during summer vacation, but %HΔ remained relatively constant during summer vacation compared with school (Δ = 0.3, SE = 0.0 vs. Δ = 0.4, SE = 0.1). Seasonal analyses showed summer had the greatest %WΔ (Δ = 1.8, SE = 0.4) and zBMI change (Δ = 0.05, SE = 0.03) while %HΔ was relatively constant across seasons. Compared with school months without a break, months with a break showed higher %WΔ (Δ = 0.7, SE = 0.1 vs. Δ = 1.6, SE = 0.2) and zBMI change (Δ = -0.03, SE = 0.01 vs. Δ = 0.04, SE = 0.01), but %HΔ was constant (Δ = 0.4, SE = 0.0 vs. Δ = 0.3, SE = 0.1). Fluctuations in sleep timing and screen time may explain these changes. Conclusions: Evidence for both the CCRM and SDH was identified but the SDH may more fully explain BMI gain. Interventions targeting consistent sleep and reduced screen time during breaks from school may be warranted no matter the season.

Jerks are Useful: Extracting pulse rate from wrist-placed accelerometry jerk during sleep in children.

STUDY OBJECTIVES: Evaluate wrist-placed accelerometry predicted heartrate compared to electrocardiogram (ECG) heartrate in children during sleep. METHODS: Children (n=82, 61% male, 43.9% Black) wore a wrist-placed Apple Watch Series 7 (AWS7) and ActiGraph GT9X during a polysomnogram. 3-Axis accelerometry data was extracted from AWS7 and the GT9X. Accelerometry heartrate estimates were derived from jerk (the rate of acceleration change), computed using the peak magnitude frequency in short time Fourier Transforms of Hilbert transformed jerk computed from acceleration magnitude. Heartrates from ECG traces were estimated from R-R intervals using R-pulse detection. Lin's Concordance Correlation Coefficient (CCC), mean absolute error (MAE) and mean absolute percent error (MAPE) assessed agreement with ECG estimated heartrate. Secondary analyses explored agreement by polysomnography sleep stage and a signal quality metric. RESULTS: The developed scripts are available on Github. For the GT9X, CCC was poor at -0.11 and MAE and MAPE were high at 16.8 (SD=14.2) beats/minute and 20.4% (SD=18.5%). For AWS7, CCC was moderate at 0.61 while MAE and MAPE were lower at 6.4 (SD=9.9) beats/minute and 7.3% (SD=10.3%). Accelerometry estimated heartrate for AWS7 was more closely related to ECG heartrate during N2, N3 and REM sleep than lights on, wake, and N1 and when signal quality was high. These patterns were not evident for the GT9X. CONCLUSIONS: Raw accelerometry data extracted from AWS7, but not the GT9X, can be used to estimate heartrate in children while they sleep. Future work is needed to explore the sources (i.e., hardware, software, etc.) of the GT9X's poor performance.

Comparison of raw accelerometry data from ActiGraph, Apple Watch, Garmin, and Fitbit using a mechanical shaker table.

The purpose of this study was to evaluate the reliability and validity of the raw accelerometry output from research-grade and consumer wearable devices compared to accelerations produced by a mechanical shaker table. Raw accelerometry data from a total of 40 devices (i.e., n = 10 ActiGraph wGT3X-BT, n = 10 Apple Watch Series 7, n = 10 Garmin Vivoactive 4S, and n = 10 Fitbit Sense) were compared to reference accelerations produced by an orbital shaker table at speeds ranging from 0.6 Hz (4.4 milligravity-mg) to 3.2 Hz (124.7mg). Two-way random effects absolute intraclass correlation coefficients (ICC) tested inter-device reliability. Pearson product moment, Lin's concordance correlation coefficient (CCC), absolute error, mean bias, and equivalence testing were calculated to assess the validity between the raw estimates from the devices and the reference metric. Estimates from Apple, ActiGraph, Garmin, and Fitbit were reliable, with ICCs = 0.99, 0.97, 0.88, and 0.88, respectively. Estimates from ActiGraph, Apple, and Fitbit devices exhibited excellent concordance with the reference CCCs = 0.88, 0.83, and 0.85, respectively, while estimates from Garmin exhibited moderate concordance CCC = 0.59 based on the mean aggregation method. ActiGraph, Apple, and Fitbit produced similar absolute errors = 16.9mg, 21.6mg, and 22.0mg, respectively, while Garmin produced higher absolute error = 32.5mg compared to the reference. ActiGraph produced the lowest mean bias 0.0mg (95%CI = -40.0, 41.0). Equivalence testing revealed raw accelerometry data from all devices were not statistically significantly within the equivalence bounds of the shaker speed. Findings from this study provide evidence that raw accelerometry data from Apple, Garmin, and Fitbit devices can be used to reliably estimate movement; however, no estimates were statistically significantly equivalent to the reference. Future studies could explore device-agnostic and harmonization methods for estimating physical activity using the raw accelerometry signals from the consumer wearables studied herein.

Evaluation of a device-agnostic approach to predict sleep from raw accelerometry data collected by Apple Watch Series 7, Garmin Vivoactive 4, and ActiGraph GT9X Link in children with sleep disruptions.

GOAL AND AIMS: Evaluate the performance of a sleep scoring algorithm applied to raw accelerometry data collected from research-grade and consumer wearable actigraphy devices against polysomnography. FOCUS METHOD/TECHNOLOGY: Automatic sleep/wake classification using the Sadeh algorithm applied to raw accelerometry data from ActiGraph GT9X Link, Apple Watch Series 7, and Garmin Vivoactive 4. REFERENCE METHOD/TECHNOLOGY: Standard manual PSG sleep scoring. SAMPLE: Fifty children with disrupted sleep (M = 8.5 years, range = 5-12 years, 42% Black, 64% male). DESIGN: Participants underwent to single night lab polysomnography while wearing ActiGraph, Apple, and Garmin devices. CORE ANALYTICS: Discrepancy and epoch-by-epoch analyses for sleep/wake classification (devices vs. polysomnography). ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES: Equivalence testing for sleep/wake classification (research-grade actigraphy vs. commercial devices). CORE OUTCOMES: Compared to polysomnography, accuracy, sensitivity, and specificity were 85.5, 87.4, and 76.8, respectively, for Actigraph; 83.7, 85.2, and 75.8, respectively, for Garmin; and 84.6, 86.2, and 77.2, respectively, for Apple. The magnitude and trend of bias for total sleep time, sleep efficiency, sleep onset latency, and wake after sleep were similar between the research and consumer wearable devices. IMPORTANT ADDITIONAL OUTCOMES: Equivalence testing indicated that total sleep time and sleep efficiency estimates from the research and consumer wearable devices were statistically significantly equivalent. CORE CONCLUSION: This study demonstrates that raw acceleration data from consumer wearable devices has the potential to be harnessed to predict sleep in children. While further work is needed, this strategy could overcome current limitations related to proprietary algorithms for predicting sleep in consumer wearable devices.

Contextual influences on implementation of online behavioral obesity treatment in primary care: formative evaluation guided by the consolidated framework for implementation research.

Online behavioral obesity treatment is a promising first-line approach to weight management in primary care. However, little is known about contextual influences on implementation. Understand qualitative contextual factors that affect the implementation process, as experienced by key primary care stakeholders implementing the program. Online behavioral obesity treatment was implemented across a 60-clinic primary care practice network. Patients were enrolled by nurse care managers (NCMs; N = 14), each serving 2-5 practices. NCMs were randomized to one of two implementation conditions-"Basic" (standard implementation) or "Enhanced" (i.e., with added patient tracking features and more implementation strategies employed). NCMs completed qualitative interviews guided by the Consolidated Framework for Implementation Research (CFIR). Interviews were transcribed and analyzed via directed content analysis. Emergent categories were summarized by implementation condition and assigned a valence according to positive/negative influence. Individuals in the Enhanced condition viewed two aspects of the intervention as more positively influencing than Basic NCMs: Design Quality & Packaging (i.e., online program aesthetics), and Cost (i.e., no-cost program, clinician time savings). In both conditions, strongly facilitating factors included: Compatibility between intervention and clinical context; Intervention Source (from a trusted local university); and Evidence Strength & Quality supporting effectiveness. Findings highlight the importance of considering stakeholders' perspectives on the most valued types of evidence when introducing a new intervention, ensuring the program aligns with organizational priorities, and considering how training resources and feedback on patient progress can improve implementation success for online behavioral obesity treatment in primary care.

Primary care clinicians' perspectives on clinical decision support to enhance outcomes of online obesity treatment in primary care: A qualitative formative evaluation.

OBJECTIVE: Online behavioral treatment for obesity produces clinically-meaningful weight losses among many primary care patients. However, some patients experience poor outcomes (i.e., failure to enroll post-referral, poor weight loss, or premature disengagement). This study sought to understand primary care clinicians' perceived utility of a clinical decision support system (CDSS) that would alert clinicians to patients' risk for poor outcome and guide clinician-delivered rescue interventions to reduce risk. METHODS: Qualitative formative evaluation was conducted in the context of an ongoing pragmatic clinical trial implementing online obesity treatment in primary care. Interviews were conducted with 14 nurse care managers (NCMs) overseeing patients' online obesity treatment. Interviews inquired about the potential utility of CDSS in primary care, desired alert frequency/format, and priorities for alert types (non-enrollment, poor weight loss, and/or early disengagement). We used matrix analysis to generate common themes across interviews. RESULTS: Nearly all NCMs viewed CDSS as potentially helpful in clinical practice. Alerts for patients at risk for disengagement were of highest priority, though all alert types were generally viewed as desirable. Regarding frequency and delivery mode of patient alerts, NCMs wanted to balance the need for prompt patient intervention with minimizing clinician burden. Concerns about CDSS emerged, including insufficient time to respond promptly and adequately to alerts and the need to involve other support staff for patients requiring ongoing rescue intervention. CONCLUSIONS: NCMs view CDSS for online obesity treatment as potentially feasible and clinically useful. For optimal implementation in primary care, CDSS must minimize clinician burden and facilitate collaborative care.