Reliability of motion phase identification for long-track speed skating using inertial measurement units.

Background: Precise identification of motion phases in long-track speed skating is critical to characterize and optimize performance. This study aimed to estimate the intra- and inter-rater reliability of movement phase identification using inertial measurement units (IMUs) in long-track speed skating. Methods: We analyzed 15 skaters using IMUs attached to specific body locations during a 500m skate, focusing on the stance phase, and identifying three movement events: Onset, Edge-flip, and Push-off. Reliability was assessed using intraclass correlation coefficients (ICC) and Bland-Altman analysis. Results: Results showed high intra- and inter-rater reliability (ICC [1,1]: 0.86 to 0.99; ICC [2,1]: 0.81 to 0.99) across all events. Absolute error ranged from 0.56 to 6.15 ms and from 0.92 to 26.29 ms for intra- and inter-rater reliability, respectively. Minimally detectable change (MDC) ranged from 17.56 to 62.22 ms and from 33.23 to 131.25 ms for intra- and inter-rater reliability, respectively. Discussion: Despite some additive and proportional errors, the overall error range was within acceptable limits, indicating negligible systematic errors. The measurement error range was small, demonstrating the accuracy of IMUs. IMUs demonstrate high reliability in movement phase identification during speed skating, endorsing their application in sports science for enhanced kinematic studies and training.

Swimming through sand: using accelerometers to observe the cryptic, pre-emergence life-stage of sea turtle hatchlings.

Animals that hatch within a subterranean nest, such as turtle hatchlings, expend some of their limited energy reserves digging out through sand or soil to reach the surface. In sea turtles, this emergence process can take the hatchlings 3-7 days. However, we have a poor understanding of this process as it is difficult to observe what is occurring underground. Here, we utilize a novel method to characterize digging-out behaviour: affixing an accelerometer directly to newly hatched green turtles (Chelonia mydas) to record movement until nest emergence. Our data revealed that buried hatchlings maintained a head-up orientation but did not move in the expected left and right swaying motion associated with alternating limb crawling. Rather, they moved using dorsal-ventral heaving and pitching as if swimming vertically through the sand to the surface. Movement activity was irregular and brief, interspersed by many short periods of inactivity, mostly lasting less than 10 min. The first 24 h of head-up activity displayed no diel patterns, but the last 24 h prior to emergence involved more intense movement during night-time hours compared with daytime hours. Thus, our results add valuable new insight, and in some cases change previous assumptions, regarding the digging behaviours during the egg-to-emergence life stage in sea turtles.

Association between physical activity performed at different intensities and cardiovascular health in patients with peripheral artery disease: an observational study.

BACKGROUND: We examined the sedentary behavior and physical activity of 260 patients with peripheral artery disease. Women engaged in more light physical activity than men did. Light physical activity was associated with lower arterial stiffness in men only, while no significant associations were found between sedentary behavior, moderate-vigorous physical activity, and cardiovascular outcomes. BACKGROUND: ◼ Women with peripheral artery disease exhibited higher blood pressure and arterial stiffness than men. BACKGROUND: ◼ Low levels of physical activity, particularly moderate to vigorous activity, were observed in individuals with peripheral artery disease. OBJECTIVE: To analyze the association between the time spent in sedentary behavior and physical activity of different intensities with cardiovascular health in men and women with peripheral artery disease. METHODS: Two hundred and sixty patients with peripheral artery disease and claudication symptoms (65.7% men; 66±1 years; ankle brachial index 0.57±0.18) were evaluated. Physical activity and sedentary behavior were assessed using an accelerometer. Physical activity was classified into light and moderate-vigorous intensities. The cardiovascular outcomes included blood pressure (oscillometric method), cardiac autonomic modulation (heart rate variability), and arterial stiffness (pulse wave velocity). RESULTS: Women spent more time engaged in light physical activity than men (341±14 min/day versus 306±9 min/day; p=0.040, respectively). There was no significant difference in the time spent on sedentary behavior and moderate-vigorous physical activity. Women had a higher systolic blood pressure (p=0.025), higher augmentation index (p<0.001), and lower sympathovagal balance (p=0.047) than men. Pulse wave velocity was only negatively associated with light physical activity (ß= -4.66; 95%CI= -8.57; -0.76) in men. Light and moderate-vigorous physical activity and sedentary behavior were not associated with other cardiovascular outcomes. CONCLUSION: Higher levels of light physical activity were associated with lower arterial stiffness in men with peripheral artery disease.

Feasibility, reliability and validity of self-measurement of knee range-of-motion using an accelerometer-based smartphone application by patients with total knee arthroplasty.

AIMS: Limited knee range-of-motion (ROM) is common following total knee arthroplasty (TKA). It is associated with functional limitations and patient dissatisfaction. Regular knee ROM assessment is important but accurate testing traditionally requires timely access to trained healthcare professionals. Although accelerometer-based smartphone goniometry has shown to provide reliable and valid joint angles, current evidence of its use still positions healthcare providers as end users instead of patients themselves. Therefore, to maximize the impact of smartphone goniometry on post-TKA care, our study aimed to examine the feasibility, reliability, and validity of patients' self-measurement of knee ROM using an accelerometer-based smartphone goniometry application. METHODS: Patients were given standard instructions with a practice trial before the actual measurements. Passive knee flexion and extension ROM was measured on 2 sessions in 30 patients with TKA using 4 block-randomized methods: (i) smartphone self-assessment, (ii) long-arm goniometry by physiotherapist, (iii) smartphone assessment by physiotherapist, and (iv) extendable-arm goniometry by physiotherapist with placement adjudication. Feasibility was assessed by the number of participants who could independently perform the self-measurement. To assess intra- and inter-session reliability, we computed intraclass correlation coefficients (ICCs) from random-effects models. To assess intra- and inter-session agreement, we computed mean absolute differences (MADs) and minimum detectable change (MDC). To assess concurrent validity, we designated extendable-arm goniometry as the "gold standard" and compared other methods against it using ICCs and MADs. RESULTS: All patients were able to comprehend and execute the assessment. 87% (n = 26) found the application easy to administer. Smartphone goniometry by patients showed excellent intra- and inter-session reliability (ICCs>0.97) and minimum variability (MAD = 0.9°-3.9°; MDC95 = 3.1°-9.0°). Smartphone or long-arm goniometry by physiotherapists did not outperform patients' self-assessment (ICC = 0.96-0.99, MAD = 0.7°-3.1°; MDC95 = 2.2°-8.0°). Compared against extendable-arm goniometry, smartphone goniometry by patients measured knee flexion and extension ROM with a MAD of 4.5° (ICC, 0.97) and 2.2° (ICC = 0.98), respectively. CONCLUSION: Our study demonstrates that smartphone goniometry is feasible, reliable and accurate, and can be used with confidence in the self-assessment of knee ROM post-TKA. Future studies should further explore its utility in telemonitored rehabilitation, and its possible integration into mobile health applications to enhance accessibility to care following TKA.

Design of a Temporally Augmented Text Messaging Bot to Improve Adolescents' Physical Activity and Engagement: Proof-of-Concept Study.

BACKGROUND: Digital interventions hold promise for improving physical activity in adolescents. However, a lack of empirical decision points (eg, timing of intervention prompts) is an evidence gap in the optimization of digital physical activity interventions. OBJECTIVE: The study examined the feasibility and acceptability, as well as the technical and functional reliability, of and participant engagement with a digital intervention that aligned its decision points to occur during times when adolescents typically exercise. This study also explored the impact of the intervention on adolescents' moderate to vigorous physical activity (MVPA) levels. Consistent with the Obesity-Related Behavioral Interventions Trials (ORBIT) model, the primary goal of the study was to identify opportunities to refine the intervention for preparation for future trials. METHODS: Ten adolescents completed a 7-day baseline monitoring period and Temporally Augmented Goal Setting (TAGS), a 20-day digital physical activity intervention that included a midday self-monitoring message that occurred when adolescents typically start to exercise (3 PM). Participants wore an accelerometer to measure their MVPA during the intervention. Participants completed questionnaires about the acceptability of the platform. Rates of recruitment and attrition (feasibility), user and technological errors (reliability), and engagement (average number of text message responses to the midday self-monitoring message) were calculated. The investigation team performed multilevel models to explore the effect of TAGS on MVPA levels from preintervention to intervention. In addition, as exploratory analyses, participants were matched to adolescents who previously completed a similar intervention, Network Underwritten Dynamic Goals Engine (NUDGE), without the midday self-monitoring message, to explore differences in MVPA between interventions. RESULTS: The TAGS intervention was mostly feasible, acceptable, and technically and functionally reliable. Adolescents showed adequate levels of engagement. Preintervention to intervention changes in MVPA were small (approximately a 2-minute change). Exploratory analyses revealed no greater benefit of TAGS on MVPA compared with NUDGE. CONCLUSIONS: TAGS shows promise for future trials with additional refinements given its feasibility, acceptability, technical and functional reliability, participants' rates of engagement, and the relative MVPA improvements. Opportunities to strengthen TAGS include reducing the burden of wearing devices and incorporating of other strategies at the 3 PM decision point. Further optimization of TAGS will inform the design of a Just-in-Time Adaptive Intervention for adolescent physical activity and prepare the intervention for more rigorous testing.

High-sensitivity acceleration sensor detecting micro-mechanomyogram and deep learning approach for parkinson's disease classification.

High-sensitivity acceleration sensors have been independently developed by our research group to detect vibrations that are > 10 dB smaller than those detected by conventional commercial sensors. This study is the first to measure high-frequency micro-vibrations in muscle fibers, termed micro-mechanomyogram (MMG) in patients with Parkinson's disease (PwPD) using a high-sensitivity acceleration sensor. We specifically measured the extensor pollicis brevis muscle at the base of the thumb in PwPD and healthy controls (HC) and detected not only low-frequency MMG (< 15 Hz) but also micro-MMG (≥ 15 Hz), which was preciously undetectable using commercial acceleration sensors. Analysis revealed remarkable differences in the frequency characteristics of micro-MMG between PwPD and HC. Specifically, during muscle power output, the low-frequency MMG energy was greater in PwPD than in HC, while the micro-MMG energy was smaller in PwPD compared to HC. These results suggest that micro-MMG detected by the high-sensitivity acceleration sensor provides crucial information for distinguishing between PwPD and HC. Moreover, a deep learning model trained on both low-frequency MMG and micro-MMG achieved a high accuracy (92.19%) in classifying PwPD and HC, demonstrating the potential for a diagnostic system for PwPD using micro-MMG.

Analysis of the association between different domains and intensities of physical activity in adults: An observational and cross-sectional study.

BACKGROUND AND OBJECTIVE: To analyze the association between different domains and intensities of physical activity (PA) in adults. METHODS: 269 participants were randomly selected in a community-dwelling representative sampling process. The habitual PA practice was assessed in different domains (occupational, sports practice, and leisure time/commuting) using Baecke's questionnaire and in different intensities (light, moderate, vigorous, and very vigorous) by accelerometry. Linear regression models analyzed the association between variables. RESULTS: Moderate and moderate-to-vigorous PA was positively associated with the three PA domain scores. Vigorous PA was associated with sports practice and leisure time/commuting PA. Only sports practice was associated with very vigorous-intensity PA (ß = 1.32; 95% CI = 0.29; 2.35). Different associations were observed in stratified analyses according to sex and age groups. Men and younger participants showed an association of domain scores with higher intensity PA than their counterparts. CONCLUSION: The findings suggest that higher intensities of PA were observed primarily in leisure time/commuting PA and sports practice, and this association varied according to sex and age.

24-hour Movement Questionnaire (QMov24h) for adults: development process and measurement properties.

BACKGROUND: Sleep, sedentary behaviour, and physical activity are essential components within the 24-hour time frame. Existing questionnaires used to measure these behaviours have insufficient measurement properties and are unsuitable for assessing compliance with the WHO Physical Activity and 24-hour Movement Guidelines. To describe the development process of the 24-hour Movement Questionnaire (QMov24h) and its testing. The QMov24h was developed to gather detailed information on sleep, sedentary behaviour, and physical activity. METHODS: The sample comprised 117 participants (58% women), aged 30.95 ± 13.56 years. The development process of the QMov24h followed the COSMIN guidelines: (i) Construction of items; (ii) Face validity with end-users; (iii) Content validity with experts; (iv) Criterion validity against accelerometry and convergent validity against diary assessments; and (v) 7-day test-retest reliability. RESULTS: The QMov24h presented adequate content and face validity. The QMov24h showed moderate criterion validity for sleep (rho=0.343;p<0.001), light physical activity (rho=0.31;p=0.002) and total aerobic physical activity (rho=0.343;p<0.001), as well as strong criterion validity for sedentary behaviour (rho=0.428;p<0.001) and aerobic moderate-to-vigorous physical activity (rho=0.534;p<0.001). Reliability varied from poor to excellent (ICC from 0.38 to 0.962;p<0.001) for all questionnaire variables. Regarding compliance of the 24-hour movement guidelines, the questionnaire also showed a strong to almost perfect percentage of agreement with accelerometry (from 69% to 94.3%), and minimal to strong reliability (k from 0.38 to 0.87) between the first and second administrations of the QMov24h. CONCLUSIONS: The QMov24h questionnaire is a valid and reliable tool for assessing levels of movement behaviours and compliance with guidelines in adults. Its measurement properties are comparable to, or even better than, those of existing questionnaires, while posing a similar burden to participants. The QMov24h is useful for research, clinical practice, and public health surveillance. The QMov24h has strong psychometric properties, making it suitable for translation, cultural adaptation, and testing in diverse populations for broader international use.

Do personality profiles contribute to patterns of physical activity and sedentary behavior in adulthood? A prospective cohort study.

BACKGROUND: Despite the observed associations of personality traits with levels of moderate-to-vigorous physical activity (MVPA) and sedentary behavior (SB), studies exploring whether the personality profiles differ in terms of the pattern of accumulation of physical behavior are lacking. The aim of this study was to identify adults' personality profiles and to characterize and investigate how these profiles differ in physical behavior. METHODS: The study utilized the longitudinal data of the participants of the Jyväskylä Longitudinal Study of Personality and Social Development (n = 141-307). Information on the five-factor model of personality, including the traits of neuroticism, extraversion, conscientiousness, openness, and agreeableness, was collected at ages 33, 42, 50, and 61 years, and used to create latent personality profiles. Physical behavior, operationalized as the amount and accumulation of MVPA and SB bouts, was captured using a triaxial accelerometer worn during waking hours at age 61 years. The differences in the behavior between the personality profiles were analyzed using the Kruskal-Wallis test. RESULTS: Five personality profiles were identified: resilient (20.2%), brittle (14.0%), overcontrolled (9.8%), undercontrolled (15.3%), and ordinary (40.7%). Although there were no statistically significant differences between the personality profiles in the time spent in MVPA relative to SB (MVPA per hour of daily SB), individuals with resilient (low in neuroticism and high in other traits) and ordinary (average in each trait) profiles had MVPA-to-SB ratios of 0.12 (7 min) and those with a brittle (high in neuroticism and low in extraversion) profile had a ratio of 0.09 (5.5 min). The individuals in the resilient group exhibited a longer usual MVPA bout duration than those in the overcontrolled (low in extraversion, openness, and agreeableness) (8 min vs. 2 min) and undercontrolled (high in openness and low in conscientiousness) groups (8 min vs. 3 min). They also exhibited a longer usual SB bout duration than those in the ordinary group (29 min vs. 23 min). CONCLUSIONS: The resilient group displayed the most prolonged MVPA and SB bout patterns. The results suggest that personality characteristics may contribute to how MVPA and SB are accumulated.

Validity of the PROMIS® Early Childhood Physical Activity Scale among toddlers.

BACKGROUND: The PROMIS® Early Childhood Physical Activity (PROMIS EC PA) scale is a recently developed PROMIS Early Childhood measure to assess PA among children aged 1-5 years. The purpose of this study was to examine test-retest reliability and convergent validity of the PROMIS EC PA scale among toddlers. METHOD: An ancillary study was conducted in the toddler-mother dyad sample of the Child and Mother Physical Activity Study. Mothers completed the 7-item PROMIS EC PA scale twice: during a study visit (test) and on the last day when their child's wore an ActiGraph accelerometer on the hip for 7 days (retest). The PROMIS EC PA summed score was calculated by totaling scores from items 1-5. Test-retest reliability was assessed using intraclass correlation coefficient (ICC) for test and retest PROMIS EC PA. Convergent validity was assessed using rank correlation coefficients (rho) between PROMIS EC PA scores and accelerometer-measured moderate- and vigorous-intensity PA (MVPA). RESULTS: Among 74 participants (56% female; 19 ± 4 months of mean age with range of 12-30 months), average accelerometer-measured MVPA was 76 ± 24 min/day. The median number of days between PROMIS EC PA test and retest was 8 days (IQR = 6 to 8), with an average PROMIS EC PA summed score of 11.0 ± 3.5 at test and 10.5 ± 3.4 at retest. ICC for the test-retest PROMIS EC PA summed scores was 0.72 (95% CI = 0.59-0.82). The rank correlation between the PROMIS EC PA summed score and accelerometer-measured MVPA was 0.13 (95% CI=-0.10 to 0.35; p = 0.28). CONCLUSION: In a sample of children aged 12-30 months, test-retest reliability for the PROMIS EC PA scale was moderate and its convergent validity against accelerometer-measured MVPA was poor. Prior to a widespread use of the PROMIS EC PA scale in large-scale research and clinical practice, the tool should be further refined and validated to elucidate how young children's lived PA experience as measured in the PROMIS EC PA scale is relevant to their health and wellbeing outcomes.

Raw Photoplethysmography as an Enhancement for Research-Grade Wearable Activity Monitors.

Wearable monitors continue to play a critical role in scientific assessments of physical activity. Recently, research-grade monitors have begun providing raw data from photoplethysmography (PPG) alongside standard raw data from inertial sensors (accelerometers and gyroscopes). Raw PPG enables granular and transparent estimation of cardiovascular parameters such as heart rate, thus presenting a valuable alternative to standard PPG methodologies (most of which rely on consumer-grade monitors that provide only coarse output from proprietary algorithms). The implications for physical activity assessment are tremendous, since it is now feasible to monitor granular and concurrent trends in both movement and cardiovascular physiology using a single noninvasive device. However, new users must also be aware of challenges and limitations that accompany the use of raw PPG data. This viewpoint paper therefore orients new users to the opportunities and challenges of raw PPG data by presenting its mechanics, pitfalls, and availability, as well as its parallels and synergies with inertial sensors. This includes discussion of specific applications to the prediction of energy expenditure, activity type, and 24-hour movement behaviors, with an emphasis on areas in which raw PPG data may help resolve known issues with inertial sensing (eg, measurement during cycling activities). We also discuss how the impact of raw PPG data can be maximized through the use of open-source tools when developing and disseminating new methods, similar to current standards for raw accelerometer and gyroscope data. Collectively, our comments show the strong potential of raw PPG data to enhance the use of research-grade wearable activity monitors in science over the coming years.

Identifying Gravity-Related Artifacts on Ballistocardiography Signals by Comparing Weightlessness and Normal Gravity Recordings (ARTIFACTS): Protocol for an Observational Study.

BACKGROUND: Modern ballistocardiography (BCG) and seismocardiography (SCG) use acceleration sensors to measure oscillating recoil movements of the body caused by the heartbeat and blood flow, which are transmitted to the body surface. Acceleration artifacts occur through intrinsic sensor roll, pitch, and yaw movements, assessed by the angular velocities of the respective sensor, during measurements that bias the signal interpretation. OBJECTIVE: This observational study aims to generate hypotheses on the detection and elimination of acceleration artifacts due to the intrinsic rotation of accelerometers and their differentiation from heart-induced sensor accelerations. METHODS: Multimodal data from 4 healthy participants (3 male and 1 female) using BCG-SCG and an electrocardiogram will be collected and serve as a basis for signal characterization, model modulation, and location vector derivation under parabolic flight conditions from µg to 1.8g. The data will be obtained during a parabolic flight campaign (3 times 30 parabolas) between September 24 and July 25 (depending on the flight schedule). To detect the described acceleration artifacts, accelerometers and gyroscopes (6-degree-of-freedom sensors) will be used for measuring acceleration and angular velocities attributed to intrinsic sensor rotation. Changes in acceleration and angular velocities will be explored by conducting descriptive data analysis of resting participants sitting upright in varying gravitational states. RESULTS: A multimodal data set will serve as a basis for research into a noninvasive and gentle method of BCG-SCG with the aid of low-noise and synchronous 3D gyroscopes and 3D acceleration sensors. Hypotheses will be generated related to detecting and eliminating acceleration artifacts due to the intrinsic rotation of accelerometers and gyroscopes (6-degree-of-freedom sensors) and their differentiation from heart-induced sensor accelerations. Data will be collected entirely and exclusively during the parabolic flights, taking place between September 2024 and July 2025. Thus, as of June 2024, no data have been collected yet. The data will be analyzed until December 2025. The results are expected to be published by June 2026. CONCLUSIONS: The study will contribute to understanding artificial acceleration bias to signal readings. It will be a first approach for a detection and elimination method. TRIAL REGISTRATION: Deutsches Register Klinische Studien DRKS00034402; https://drks.de/search/en/trial/DRKS00034402. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/63306.

Changes in physical activity among Canadian adults more than 6 months into the COVID-19 pandemic: a secondary analysis of the INTERACT cohort study.

OBJECTIVE: To estimate the effect of (a) the COVID-19 pandemic and (b) COVID-19 restriction stringency on daily minutes of device-measured moderate-to-vigorous physical activity (MVPA). DESIGN: Physical activity data were collected from the INTerventions, Equity, Research and Action in Cities Team (INTERACT) cohorts in Montreal, Saskatoon and Vancouver before (May 2018 to February 2019, 'phase 1') and during the pandemic (October 2020 to February 2021, 'phase 2'). We estimated the effect of the two exposures by comparing daily MVPA measured (a) before vs during the pandemic (phase 1 vs phase 2) and (b) at different levels of COVID-19 restriction stringency during phase 2. Separate mixed effects negative binomial regression models were used to estimate the association between each exposure and daily MVPA, with and without controlling for confounders. Analyses were conducted on person-days with at least 600 min of wear time. Effect modification by gender, age, income, employment status, education, children in the home and city was assessed via stratification. SETTING: Montreal (Quebec), Saskatoon (Saskatchewan) and Vancouver (British Columbia), Canada. MAIN OUTCOME MEASURE: Daily minutes of MVPA, as measured using SenseDoc, a research-grade accelerometer device. RESULTS: Daily minutes of MVPA were 21% lower in phase 2 (October 2020 to February 2021) compared with phase 1 (May 2018 to February 2019), controlling for gender, age, employment status, household income, education, city, weather and wear time (rate ratio=0.79, 95% CI 0.69, 0.92). This did not appear to be driven by changes in the sample or timing of data collection between phases. The results suggested effect modification by employment, household income and education. Restriction stringency was not associated with daily MVPA between October 2020 and February 2021 (adjusted rate ratio=0.99, 95% CI 0.96, 1.03). CONCLUSIONS: Between October 2020 and February 2021, daily minutes of MVPA were significantly lower than 2 years prior, but were not associated with daily COVID-19 restriction stringency.

Validation of two novel human activity recognition models for typically developing children and children with Cerebral Palsy.

Human Activity Recognition models have potential to contribute to valuable and detailed knowledge of habitual physical activity for typically developing children and children with Cerebral Palsy. The main objective of the present study was to develop and validate two Human Activity Recognition models. One trained on data from typically developing children (n = 63), the second also including data from children with Cerebral Palsy (n = 16), engaging in standardised activities and free play. Our data was collected using accelerometers and ground truth was established with video annotations. Additionally, we aimed to investigate the influence of window settings on model performance. Utilizing the Extreme gradient boost (XGBoost) classifier, twelve sub-models were created, with 1-,3- and 5-seconds windows, with and without overlap. Both Human Activity Recognition models demonstrated excellent predictive capabilities (>92%) for standardised activities for both typically developing and Cerebral Palsy. From all window sizes, the 1-second window performed best for all test groups. Accuracy was slightly lower (>75%) for the Cerebral Palsy test group performing free play activities. The impact of window size and overlap varied depending on activity. In summary both Human Activity Recognition models effectively predict standardised activities, surpassing prior models for typically developing and children with Cerebral Palsy. Notably, the model trained on combined typically developing children and Cerebral Palsy data performed exemplary across all test groups. Researchers should select window settings aligned with their specific research objectives.

Deep Learning-Based Obesity Identification System for Young Adults Using Smartphone Inertial Measurements.

Obesity recognition in adolescents is a growing concern. This study presents a deep learning-based obesity identification framework that integrates smartphone inertial measurements with deep learning models to address this issue. Utilizing data from accelerometers, gyroscopes, and rotation vectors collected via a mobile health application, we analyzed gait patterns for obesity indicators. Our framework employs three deep learning models: convolutional neural networks (CNNs), long-short-term memory network (LSTM), and a hybrid CNN-LSTM model. Trained on data from 138 subjects, including both normal and obese individuals, and tested on an additional 35 subjects, the hybrid model achieved the highest accuracy of 97%, followed by the LSTM model at 96.31% and the CNN model at 95.81%. Despite the promising outcomes, the study has limitations, such as a small sample and the exclusion of individuals with distorted gait. In future work, we aim to develop more generalized models that accommodate a broader range of gait patterns, including those with medical conditions.

Effectiveness of Hospital Fit on Physical Activity in Hospitalized Patients: A Stepped-Wedge Cluster-Randomized Trial and Process Evaluation.

This study investigates the effectiveness of using Hospital Fit as part of usual care physiotherapy on the physical activity (PA) behavior of hospitalized patients compared to patients who received physiotherapy before implementation of Hospital Fit. In addition, a process evaluation is conducted. A prospective, multi-center, mixed-methods stepped wedge cluster randomized trial was performed at the cardiology and medical oncology departments of two Dutch university medical centers. Patients were included in the non-intervention or intervention phase. During the non-intervention phase, patients received usual care physiotherapy. During the intervention phase, Hospital Fit was additionally used. Mean time spent walking, standing, lying/sitting per day and the number of postural transitions from lying/sitting to standing/walking positions were measured using an accelerometer and analyzed using linear mixed models. A process evaluation was performed using questionnaires and semi-structured interviews with patients and focus-group interviews with healthcare professionals. A total of 77 patients were included, and data from 63 patients were used for data analysis. During the intervention phase, the average time spent walking per day was 20 min (95% confidence interval: -2 to 41 min) higher than during the non-intervention phase (p = 0.075). No significant differences were found for mean time spent standing per day, mean time spent lying/sitting per day, or the number of postural transitions per day either. During the intervention phase, 87% of patients used Hospital Fit at least once, with a median daily use of 2.5 to 4.0 times. Patients and healthcare professionals believed that Hospital Fit improved patients' PA behavior and recovery. Insufficient digital skills and technical issues were described as challenges. Although patients and healthcare professionals described Hospital Fit as an added value, no statistically significant effects were found.

The Use of Triaxial Accelerometers and Machine Learning Algorithms for Behavioural Identification in Domestic Dogs (Canis familiaris): A Validation Study.

Assessing the behaviour and physical attributes of domesticated dogs is critical for predicting the suitability of animals for companionship or specific roles such as hunting, military or service. Common methods of behavioural assessment can be time consuming, labour-intensive, and subject to bias, making large-scale and rapid implementation challenging. Objective, practical and time effective behaviour measures may be facilitated by remote and automated devices such as accelerometers. This study, therefore, aimed to validate the ActiGraph® accelerometer as a tool for behavioural classification. This study used a machine learning method that identified nine dog behaviours with an overall accuracy of 74% (range for each behaviour was 54 to 93%). In addition, overall body dynamic acceleration was found to be correlated with the amount of time spent exhibiting active behaviours (barking, locomotion, scratching, sniffing, and standing; R2 = 0.91, p < 0.001). Machine learning was an effective method to build a model to classify behaviours such as barking, defecating, drinking, eating, locomotion, resting-asleep, resting-alert, sniffing, and standing with high overall accuracy whilst maintaining a large behavioural repertoire.

The Determination of On-Water Rowing Stroke Kinematics Using an Undecimated Wavelet Transform of a Rowing Hull-Mounted Accelerometer Signal.

Boat acceleration profiles can provide valuable information for coaches and practitioners to make meaningful technical interventions and monitor the determinants of success in rowing. Previous studies have used simple feature detection methods to identify key phases within individual strokes, such as drive onset, drive time, drive offset and stroke time. However, based on skill level, technique or boat class, the hull acceleration profile can differ, making robust feature detection more challenging. The current study's purpose is to employ the undecimated wavelet transform (UWT) technique to detect individual features in the stroke acceleration profile from a single rowing hull-mounted accelerometer. In this investigation, the temporal and kinematic values obtained using the AdMosTM sensor in conjunction with the UWT processing approach were strongly correlated with the comparative measures of the Peach™ instrumented oarlock system. The measures for stroke time displayed very strong agreeability between the systems for all boat classes, with ICC values of 0.993, 0.963 and 0.954 for the W8+, W4- and W1x boats, respectively. Similarly, the drive time was also very consistent, with strong to very strong agreeability, producing ICC values of 0.937, 0.901 and 0.881 for the W8+, W4- and W1x boat classes. Further, a Bland-Altman analysis displayed little to no bias between the AdMosTM-derived and Peach™ measures, indicating that there were no systematic discrepancies between signals. This single-sensor solution could form the basis for a simple, cost-effective and accessible alternative to multi-sensor instrumented systems for the determination of sub-stroke kinematic phases.

The German version of the Pregnancy Physical Activity Questionnaire: a translation, cross-cultural adaptation, reliability and validity assessment.

BACKGROUND: Validated and internationally standardised measurement instruments are a prerequisite for ensuring that physical activity during pregnancy is comparable and for deriving physical activity recommendations. In Germany, there has been no adapted version of the internationally used Pregnancy Physical Activity Questionnaire (PPAQ) until now. This study's aim centred around translating the original English version into German (PPAQ-G) and determining its reliability as well as validity in a German population. METHODS: The PPAQ was translated into German using the forward-backwards technique. Its reliability and validity were tested. Thirty-four correctly completed questionnaires were analysed. The test-retest reliability was presented using the intraclass correlation coefficient (ICC) and Spearman correlation coefficient. Validity was tested by using accelerometer (n = 23) and determined by Spearman correlation coefficient. RESULTS: In the transcultural adjustment, two questions were amended to describe intensity more precisely, and two other questions were adapted to reflect the units of measurement used in Germany. The ICC indicated a reliability of r = 0.79 for total activity (without sitting), and the intensity subcategories ranged from r = 0.70 (moderate-intensity activities) to r = 0.90 (sitting). Although, validity assessment showed no significant correlation for sedentary, moderate or vigorous intensity, there were significant correlations for total activity (light and above; r = 0.49; p < 0.05) and for light activity (r = 0.65; p < 0.01). CONCLUSIONS: The PPAQ-G showed good reliability for use on pregnant German women and a moderately accurate measurement of physical activity. It can be used nationally for epidemiological studies, and it also enables international comparisons of physical activity during pregnancy. TRIAL REGISTRATION: DRKS00023426; Registration date 20 May 2021.

Diurnal timing of physical activity and risk of colorectal cancer in the UK Biobank.

BACKGROUND: Physical activity reduces colorectal cancer risk, yet the diurnal timing of physical activity in colorectal cancer etiology remains unclear. METHODS: This study used 24-h accelerometry time series from UK Biobank participants aged 42 to 79 years to derive circadian physical activity patterns using functional principal component analysis. Multivariable Cox proportional hazard models were used to examine associations with colorectal cancer risk. RESULTS: Among 86,252 participants (56% women), 529 colorectal cancer cases occurred during a median 5.3-year follow-up. We identified four physical activity patterns that explained almost 100% of the data variability during the day. A pattern of continuous day-long activity was inversely associated with colorectal cancer risk (hazard ratio (HR) = 0.94, 95% confidence interval (CI) = 0.89-0.99). A second pattern of late-day activity was suggestively inversely related to risk (HR = 0.93, 95% CI = 0.85-1.02). A third pattern of early- plus late-day activity was associated with decreased risk (HR = 0.89, 95% CI = 0.80-0.99). A fourth pattern of mid-day plus night-time activity showed no relation (HR = 1.02, 95% CI = 0.88-1.19). Our results were consistent across various sensitivity analyses, including the restriction to never smokers, the exclusion of the first 2 years of follow-up, and the adjustment for shift work. CONCLUSIONS: A pattern of early- plus late-day activity is related to reduced colorectal cancer risk, beyond the benefits of overall activity. Further research is needed to confirm the role of activity timing in colorectal cancer prevention.