Quality of Electrocardiography Recorded with Consumer Smart Shirts.

Smart wearables support continuous monitoring of vital signs for early detection of deteriorating health. However, the devices and sensors require sufficient quality to produce meaningful signals, in particular, if data is acquired in motion. In this study, we equipped 48 subjects with smart shirts recording one-lead electrocardiography (ECG), thoracic and abdominal respiratory inductance plethysmography, and three-axis acceleration. For 10 min each, the subjects sit, stand, walk, and run, with a resting period of 5 min in between each activity. We preprocessed the electrocardiogram and applied a signal quality index. We analyzed the signal quality index grouped by the activity and participants. For sitting, standing, walking, and running, the ECG signals provide acceptable quality over 73.20 %, 91.85 %, 12.26 %, and 13.14 % of the recording time. In conclusion, smart wearables may be useful for continuous health monitoring of people with a sedentary lifestyle, but rather not for sportive activities.

Prediction of Mild Cognitive Impairment Status: Pilot Study of Machine Learning Models Based on Longitudinal Data From Fitness Trackers.

BACKGROUND: Early signs of Alzheimer disease (AD) are difficult to detect, causing diagnoses to be significantly delayed to time points when brain damage has already occurred and current experimental treatments have little effect on slowing disease progression. Tracking cognitive decline at early stages is critical for patients to make lifestyle changes and consider new and experimental therapies. Frequently studied biomarkers are invasive and costly and are limited for predicting conversion from normal to mild cognitive impairment (MCI). OBJECTIVE: This study aimed to use data collected from fitness trackers to predict MCI status. METHODS: In this pilot study, fitness trackers were worn by 20 participants: 12 patients with MCI and 8 age-matched controls. We collected physical activity, heart rate, and sleep data from each participant for up to 1 month and further developed a machine learning model to predict MCI status. RESULTS: Our machine learning model was able to perfectly separate between MCI and controls (area under the curve=1.0). The top predictive features from the model included peak, cardio, and fat burn heart rate zones; resting heart rate; average deep sleep time; and total light activity time. CONCLUSIONS: Our results suggest that a longitudinal digital biomarker differentiates between controls and patients with MCI in a very cost-effective and noninvasive way and hence may be very useful for identifying patients with very early AD who can benefit from clinical trials and new, disease-modifying therapies.

Assessment of Heat Exposure and Health Outcomes in Rural Populations of Western Kenya by Using Wearable Devices: Observational Case Study.

BACKGROUND: Climate change increasingly impacts health, particularly of rural populations in sub-Saharan Africa due to their limited resources for adaptation. Understanding these impacts remains a challenge, as continuous monitoring of vital signs in such populations is limited. Wearable devices (wearables) present a viable approach to studying these impacts on human health in real time. OBJECTIVE: The aim of this study was to assess the feasibility and effectiveness of consumer-grade wearables in measuring the health impacts of weather exposure on physiological responses (including activity, heart rate, body shell temperature, and sleep) of rural populations in western Kenya and to identify the health impacts associated with the weather exposures. METHODS: We conducted an observational case study in western Kenya by utilizing wearables over a 3-week period to continuously monitor various health metrics such as step count, sleep patterns, heart rate, and body shell temperature. Additionally, a local weather station provided detailed data on environmental conditions such as rainfall and heat, with measurements taken every 15 minutes. RESULTS: Our cohort comprised 83 participants (42 women and 41 men), with an average age of 33 years. We observed a positive correlation between step count and maximum wet bulb globe temperature (estimate 0.06, SE 0.02; P=.008). Although there was a negative correlation between minimum nighttime temperatures and heat index with sleep duration, these were not statistically significant. No significant correlations were found in other applied models. A cautionary heat index level was recorded on 194 (95.1%) of 204 days. Heavy rainfall (>20 mm/day) occurred on 16 (7.8%) out of 204 days. Despite 10 (21%) out of 47 devices failing, data completeness was high for sleep and step count (mean 82.6%, SD 21.3% and mean 86.1%, SD 18.9%, respectively), but low for heart rate (mean 7%, SD 14%), with adult women showing significantly higher data completeness for heart rate than men (2-sided t test: P=.003; Mann-Whitney U test: P=.001). Body shell temperature data achieved 36.2% (SD 24.5%) completeness. CONCLUSIONS: Our study provides a nuanced understanding of the health impacts of weather exposures in rural Kenya. Our study's application of wearables reveals a significant correlation between physical activity levels and high temperature stress, contrasting with other studies suggesting decreased activity in hotter conditions. This discrepancy invites further investigation into the unique socioenvironmental dynamics at play, particularly in sub-Saharan African contexts. Moreover, the nonsignificant trends observed in sleep disruption due to heat expose the need for localized climate change mitigation strategies, considering the vital role of sleep in health. These findings emphasize the need for context-specific research to inform policy and practice in regions susceptible to the adverse health effects of climate change.

The use of wearable devices on physical activity levels among individuals living with diabetes: 2017 BRFSS.

AIM: This study aims to examine the association between wearing wearable devices and physical activity levels among people living with diabetes. METHODS: 1298 wearable device users and nonusers living with diabetes from eight states of the 2017 Behavioral Risk Factors Surveillance System were included in the analysis. Unadjusted and adjusted linear regression was performed to determine the association between self-reported physical activity per week (min) and wearable device usage (users and nonusers) among people living with diabetes using survey analysis. RESULTS: 84.97 % (95 % CI [80.39, 88.89]) of participants were nonusers of wearable devices, while 15.03 % (95 % CI [11.11, 19.61]) were users. Across the sample, the average weekly physical activity was 427.39 mins (95 % Cl [356.43, 498.35]). Nonusers had a higher physical activity per week with 433.83 mins (95 % CI [353.59, 514.07]), while users only had 392.59 mins (95 % CI [253.48, 531.69]) of physical activity per week. However, the differences between the two groups were non-statistically significant (p=.61). In both adjusted and unadjusted linear regressions between physical activity per week and wearable device usage, statistically significant associations were not found (unadjusted: ß=-41.24, p=.62; adjusted: ß=-56.41, p=.59). CONCLUSION: Further research is needed to determine the effectiveness of wearable devices in promoting physical activity among people with diabetes. Additionally, there is a need to determine how people with diabetes use wearable devices that could promote physical activity levels.

Continuous Assessment of Active-Duty Army Special Operations and Reconnaissance Marines Using Digital Devices and Custom Software: The Digital Comprehensive Operator Readiness Assessment (DcORA) Study.

BACKGROUND: Continuous exposure to extreme and chronic stress from uncontrollable events has been linked to increased psychological and physiological reactivity. Prolonged, frequent deployments may test coping skills over time, ultimately rendering Servicemembers vulnerable to mental health problems and suicide. This study develops a methodology for accurately collecting holistic health measures from Servicemembers using digital tools, including custom-built phone software and body-worn sensors. METHODS: The secure research platform and mobile app continuously collect multiple health measures and, after data analysis, deliver continuously updated summary data back to the Servicemember. This system provides novel insights into the relationships between the measures while helping individuals track their progress toward self-established goals. Participants were given an iPhone (including the study app) and an Apple Watch. Participants tracked their data for more than 6 months and responded to baseline, daily, and weekly questions and assessments. Physiologic, psychologic, and cognitive assessment data across the Preservation of the Force and Family program (POTFF) domains were collected, displayed to the individual, and analyzed in aggregate. RESULTS: When coupled with custom-built software, this hardware can be elevated from a fitness tracker to a user-facing health monitoring, educational, and delivery system. CONCLUSION: This wearable system measured vital factors associated with the health and human performance of Servicemembers. In real-time, it engaged Servicemembers in health and human performance optimization practices to achieve a goal of prevention of physical or mental injury.

Accuracy of the Apple Watch Series 4 and Fitbit Versa for Assessing Energy Expenditure and Heart Rate of Wheelchair Users During Treadmill Wheelchair Propulsion: Cross-sectional Study.

BACKGROUND: The Apple Watch (AW) Series 1 provides energy expenditure (EE) for wheelchair users but was found to be inaccurate with an error of approximately 30%, and the corresponding error for heart rate (HR) provided by the Fitbit Charge 2 was approximately 10% to 20%. Improved accuracy of estimated EE and HR is expected with newer editions of these smart watches (SWs). OBJECTIVE: This study aims to assess the accuracy of the AW Series 4 (wheelchair-specific setting) and the Fitbit Versa (treadmill running mode) for estimating EE and HR during wheelchair propulsion at different intensities. METHODS: Data from 20 manual wheelchair users (male: n=11, female: n=9; body mass: mean 75, SD 19 kg) and 20 people without a disability (male: n=11, female: n=9; body mass: mean 75, SD 11 kg) were included. Three 4-minute wheelchair propulsion stages at increasing speed were performed on 3 separate test days (0.5%, 2.5%, or 5% incline), while EE and HR were collected by criterion devices and the AW or Fitbit. The mean absolute percentage error (MAPE) was used to indicate the absolute agreement between the criterion device and SWs for EE and HR. Additionally, linear mixed model analyses assessed the effect of exercise intensity, sex, and group on the SW error. Interclass correlation coefficients were used to assess relative agreement between criterion devices and SWs. RESULTS: The AW underestimated EE with MAPEs of 29.2% (SD 22%) in wheelchair users and 30% (SD 12%) in people without a disability. The Fitbit overestimated EE with MAPEs of 73.9% (SD 7%) in wheelchair users and 44.7% (SD 38%) in people without a disability. Both SWs underestimated HR. The device error for EE and HR increased with intensity for both SWs (all comparisons: P<.001), and the only significant difference between groups was found for HR in the AW (-5.27 beats/min for wheelchair users; P=.02). There was a significant effect of sex on the estimation error in EE, with worse accuracy for the AW (-0.69 kcal/min; P<.001) and better accuracy for the Fitbit (-2.08 kcal/min; P<.001) in female participants. For HR, sex differences were found only for the AW, with a smaller error in female participants (5.23 beats/min; P=.02). Interclass correlation coefficients showed poor to moderate relative agreement for both SWs apart from 2 stage-incline combinations (AW: 0.12-0.57 for EE and 0.11-0.86 for HR; Fitbit: 0.06-0.85 for EE and 0.03-0.29 for HR). CONCLUSIONS: Neither the AW nor Fitbit were sufficiently accurate for estimating EE or HR during wheelchair propulsion. The AW underestimated EE and the Fitbit overestimated EE, and both SWs underestimated HR. Caution is hence required when using SWs as a tool for training intensity regulation and energy balance or imbalance in wheelchair users.

The Use of Mobile Technologies to Promote Physical Activity and Reduce Sedentary Behaviors in the Middle East and North Africa Region: Systematic Review and Meta-Analysis.

BACKGROUND: The Middle East and North Africa (MENA) region faces unique challenges in promoting physical activity and reducing sedentary behaviors, as the prevalence of insufficient physical activity is higher than the global average. Mobile technologies present a promising approach to delivering behavioral interventions; however, little is known about the effectiveness and user perspectives on these technologies in the MENA region. OBJECTIVE: This study aims to evaluate the effectiveness of mobile interventions targeting physical activity and sedentary behaviors in the MENA region and explore users' perspectives on these interventions as well as any other outcomes that might influence users' adoption and use of mobile technologies (eg, appropriateness and cultural fit). METHODS: A systematic search of 5 databases (MEDLINE, Embase, CINAHL, Scopus, and Global Index Medicus) was performed. Any primary studies (participants of all ages regardless of medical condition) conducted in the MENA region that investigated the use of mobile technologies and reported any measures of physical activity, sedentary behaviors, or user perceptions were included. We conducted a narrative synthesis of all studies and a meta-analysis of randomized controlled trials (RCTs). The Cochrane risk-of-bias tool was used to assess the quality of the included RCTs; quality assessment of the rest of the included studies was completed using the relevant Joanna Briggs Institute critical appraisal tools. RESULTS: In total, 27 articles describing 22 interventions (n=10, 37% RCTs) and 4 (15%) nonexperimental studies were included (n=6141, 46% women). Half (11/22, 50%) of the interventions included mobile apps, whereas the other half examined SMS. The main app functions were goal setting and self-monitoring of activity, whereas SMS interventions were primarily used to deliver educational content. Users in experimental studies described several benefits of the interventions (eg, gaining knowledge and receiving reminders to be active). Engagement with the interventions was poorly reported; few studies (8/27, 30%) examined users' perspectives on the appropriateness or cultural fit of the interventions. Nonexperimental studies examined users' perspectives on mobile apps and fitness trackers, reporting several barriers to their use, such as perceived lack of usefulness, loss of interest, and technical issues. The meta-analysis of RCTs showed a positive effect of mobile interventions on physical activity outcomes (standardized mean difference=0.45, 95% CI 0.17-0.73); several sensitivity analyses showed similar results. The trim-and-fill method showed possible publication bias. Only 20% (2/10) of the RCTs measured sedentary behaviors; both reported positive changes. CONCLUSIONS: The use of mobile interventions for physical activity and sedentary behaviors in the MENA region is in its early stages, with preliminary evidence of effectiveness. Policy makers and researchers should invest in high-quality studies to evaluate long-term effectiveness, intervention engagement, and implementation outcomes, which can inform the design of culturally and socially appropriate interventions for countries in the MENA region. TRIAL REGISTRATION: PROSPERO CRD42023392699; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=392699.

Lifestyle Walking Intervention for Patients With Heart Failure With Reduced Ejection Fraction: The WATCHFUL Trial.

BACKGROUND: Physical activity is pivotal in managing heart failure with reduced ejection fraction, and walking integrated into daily life is an especially suitable form of physical activity. This study aimed to determine whether a 6-month lifestyle walking intervention combining self-monitoring and regular telephone counseling improves functional capacity assessed by the 6-minute walk test (6MWT) in patients with stable heart failure with reduced ejection fraction compared with usual care. METHODS: The WATCHFUL trial (Pedometer-Based Walking Intervention in Patients With Chronic Heart Failure With Reduced Ejection Fraction) was a 6-month multicenter, parallel-group randomized controlled trial recruiting patients with heart failure with reduced ejection fraction from 6 cardiovascular centers in the Czech Republic. Eligible participants were ≥18 years of age, had left ventricular ejection fraction <40%, and had New York Heart Association class II or III symptoms on guidelines-recommended medication. Individuals exceeding 450 meters on the baseline 6MWT were excluded. Patients in the intervention group were equipped with a Garmin vívofit activity tracker and received monthly telephone counseling from research nurses who encouraged them to use behavior change techniques such as self-monitoring, goal-setting, and action planning to increase their daily step count. The patients in the control group continued usual care. The primary outcome was the between-group difference in the distance walked during the 6MWT at 6 months. Secondary outcomes included daily step count and minutes of moderate to vigorous physical activity as measured by the hip-worn Actigraph wGT3X-BT accelerometer, NT-proBNP (N-terminal pro-B-type natriuretic peptide) and high-sensitivity C-reactive protein biomarkers, ejection fraction, anthropometric measures, depression score, self-efficacy, quality of life, and survival risk score. The primary analysis was conducted by intention to treat. RESULTS: Of 218 screened patients, 202 were randomized (mean age, 65 years; 22.8% female; 90.6% New York Heart Association class II; median left ventricular ejection fraction, 32.5%; median 6MWT, 385 meters; average 5071 steps/day; average 10.9 minutes of moderate to vigorous physical activity per day). At 6 months, no between-group differences were detected in the 6MWT (mean 7.4 meters [95% CI, -8.0 to 22.7]; P=0.345, n=186). The intervention group increased their average daily step count by 1420 (95% CI, 749 to 2091) and daily minutes of moderate to vigorous physical activity by 8.2 (95% CI, 3.0 to 13.3) over the control group. No between-group differences were detected for any other secondary outcomes. CONCLUSIONS: Whereas the lifestyle intervention in patients with heart failure with reduced ejection fraction improved daily steps by about 25%, it failed to demonstrate a corresponding improvement in functional capacity. Further research is needed to understand the lack of association between increased physical activity and functional outcomes. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT03041610.

Developing Climate Change and Health Impact Monitoring with eHealth at the South East Asia Community Observatory and Health and Demographic Surveillance Site, Malaysia (CHIMES).

Background: Malaysia is projected to experience an increase in heat, rainfall, rainfall variability, dry spells, thunderstorms, and high winds due to climate change. This may lead to a rise in heat-related mortality, reduced nutritional security, and potential migration due to uninhabitable land. Currently, there is limited data regarding the health implications of climate change on the Malaysian populace, which hinders informed decision-making and interventions. Objective: This study aims to assess the feasibility and reliability of using sensor-based devices to enhance climate change and health research within the SEACO health and demographic surveillance site (HDSS) in Malaysia. We will particularly focus on the effects of climate-sensitive diseases, emphasizing lung conditions like chronic obstructive pulmonary disease (COPD) and asthma. Methods: In our mixed-methods approach, 120 participants (>18 years) from the SEACO HDSS in Segamat, Malaysia, will be engaged over three cycles, each lasting 3 weeks. Participants will use wearables to monitor heart rate, activity, and sleep. Indoor sensors will measure temperature in indoor living spaces, while 3D-printed weather stations will track indoor temperature and humidity. In each cycle, a minimum of 10 participants at high risk for COPD or asthma will be identified. Through interviews and questionnaires, we will evaluate the devices' reliability, the prevalence of climate-sensitive lung diseases, and their correlation with environmental factors, like heat and humidity. Results: We anticipate that the sensor-based measurements will offer a comprehensive understanding of the interplay between climate-sensitive diseases and weather variables. The data is expected to reveal correlations between health impacts and weather exposures like heat. Participant feedback will offer perspectives on the usability and feasibility of these digital tools. Conclusion: Our study within the SEACO HDSS in Malaysia will evaluate the potential of sensor-based digital technologies in monitoring the interplay between climate change and health, particularly for climate-sensitive diseases like COPD and asthma. The data generated will likely provide details on health profiles in relation to weather exposures. Feedback will indicate the acceptability of these tools for broader health surveillance. As climate change continues to impact global health, evaluating the potential of such digital technologies is crucial to understand its potential to inform policy and intervention strategies in vulnerable regions.

Usability and ease of use of long-term remote monitoring of physical activity for individuals with acquired brain injury in community: a qualitative analysis.

Introduction: Objective and continuous monitoring of physical activity over the long-term in the community is perhaps the most important step in the paradigm shift toward evidence-based practice and personalized therapy for successful community integration. With the advancement in technology, physical activity monitors have become the go-to tools for objective and continuous monitoring of everyday physical activity in the community. While these devices are widely used in many patient populations, their use in individuals with acquired brain injury is slowly gaining traction. The first step before using activity monitors in this population is to understand the patient perspective on usability and ease of use of physical activity monitors at different wear locations. However, there are no studies that have looked at the feasibility and patient perspectives on long-term utilization of activity monitors in individuals with acquired brain injury. Methods: This pilot study aims to fill this gap and understand patient-reported aspects of the feasibility of using physical activity monitors for long-term use in community-dwelling individuals with acquired brain injury. Results: This pilot study found that patients with acquired brain injury faced challenges specific to their functional limitations and that the activity monitors worn on the waist or wrist may be better suited in this population. Discussion: The unique wear location-specific challenges faced by individuals with ABI need to be taken into account when selecting wearable activity monitors for long term use in this population.

Validity of activity wristbands for estimating daily physical activity in primary schoolchildren under free-living conditions: School-Fit study.

Introduction: The use of activity wristbands to monitor and promote schoolchildren's physical activity (PA) is increasingly widespread. However, their validity has not been sufficiently studied, especially among primary schoolchildren. Consequently, the main purpose was to examine the validity of the daily steps and moderate-to-vigorous PA (MVPA) scores estimated by the activity wristbands Fitbit Ace 2, Garmin Vivofit Jr 2, and the Xiaomi Mi Band 5 in primary schoolchildren under free-living conditions. Materials and methods: An initial sample of 67 schoolchildren (final sample = 62; 50% females), aged 9-12 years old (mean = 10.4 ± 1.0 years), participated in the present study. Each participant wore three activity wristbands (Fitbit Ace 2, Garmin Vivofit Jr 2, and Xiaomi Mi Band 5) on his/her non-dominant wrist and a research-grade accelerometer (ActiGraph wGT3X-BT) on his/her hip as the reference standard (number of steps and time in MVPA) during the waking time of one day. Results: Results showed that the validity of the daily step scores estimated by the Garmin Vivofit Jr 2 and Xiaomi Mi Band 5 were good and acceptable (e.g., MAPE = 9.6/11.3%, and lower 95% IC of ICC = 0.87/0.73), respectively, as well as correctly classified schoolchildren as meeting or not meeting the daily 10,000/12,000-step-based recommendations, obtaining excellent/good and good/acceptable results (e.g., Garmin Vivofit Jr 2, k = 0.75/0.62; Xiaomi Mi Band 5, k = 0.73/0.53), respectively. However, the Fitbit Ace 2 did not show an acceptable validity (e.g., daily steps: MAPE = 21.1%, and lower 95% IC of ICC = 0.00; step-based recommendations: k = 0.48/0.36). None of the three activity wristbands showed an adequate validity for estimating daily MVPA (e.g., MAPE = 36.6-90.3%, and lower 95% IC of ICC = 0.00-0.41) and the validity for the MVPA-based recommendation tended to be considerably lower (e.g., k = -0.03-0.54). Conclusions: The activity wristband Garmin Vivofit Jr 2 obtained the best validity for monitoring primary schoolchildren's daily steps, offering a feasible alternative to the research-grade accelerometers. Furthermore, this activity wristband could be used during PA promotion programs to provide accurate feedback to primary schoolchildren to ensure their accomplishment with the PA recommendations.

Agreement between Fitbit and ActiGraph Estimates of Physical Activity in Young Children.

Physical activity (PA) estimates from the Fitbit Flex 2 were compared to those from the ActiGraph GT9X Link in 123 elementary school children. Steps and intensity-specific estimates of PA and 3-month PA change were calculated using two different ActiGraph cut-points (Evenson and Romanzini). Fitbit estimates were 35% higher for steps compared to the ActiGraph. Fitbit and ActiGraph intensity-specific estimates were closest for sedentary and light PA while estimates of moderate and vigorous PA varied substantially depending upon the ActiGraph cut-points used. Spearman correlations between device estimates were higher for steps (rs=.70) than for moderate (rs =.54 to .55) or vigorous (rs =.29 to .48) PA. There was low concordance between devices in assessing PA changes over time. Agreement between Fitbit Flex 2 and ActiGraph estimates may depend upon the cut-points used to classify PA intensity. However, there is fair to good agreement between devices in ranking children's steps and MVPA.

Feasibility and efficacy of an activity-monitoring approach using pedometer in patients undergoing subacute rehabilitation: A pilot study.

Wearable devices for the quantification of walking have recently been adopted for gait rehabilitation. To apply this method in subacute rehabilitation settings, this approach must be effective in these populations and implemented as a feasible method in terms of adherence and safety, especially the risk of falling. This study aimed to investigate the feasibility and efficacy of an activity monitoring approach in subacute rehabilitation using a commercially available pedometer validated with slow walking. This randomized controlled study with blinded assessors recruited 29 patients admitted to a rehabilitation ward. The participants were randomly assigned to either the feedback (intervention) or the no-feedback (control) group. Participants in both groups received at least 120 min of therapy sessions every day for 6 or 7 days per week while wearing pedometers on their unaffected ankles from the day they were permitted to walk independently till discharge. Only participants in the feedback group received weekly encouragement and the next goals. The primary outcome was the change in the 6-minute walking distance (Δ6MD). Feasibility (percentage of pedometer data acquisition days in the total observational period and the number of falls) and other efficacy outcomes (step counts, gait speed, 30-seconds chair stand test, Berg Balance Scale, and Timed Up and Go Test) were also evaluated. Regarding feasibility outcomes, the data acquisition rate was 94.1% and the number of falls during the observation period was one in the feedback group. Regarding efficacy outcomes, Δ6MD was not significantly greater in the feedback group [mean (standard deviation): 79.1 (51.7) m] than in the no-feedback group [86.1 (65.4) m] (p = 0.774) and the other five secondary outcomes showed no between-group difference. Considering the large number of steps per day in both groups [6,912 (4,751) and 5,600 (5,108) steps in the feedback and no-feedback group, respectively], the effect of the intended intervention might have been masked by the effect of simply wearing pedometers in the control group. This study revealed that the activity monitoring approach using an ankle-worn pedometer was practical in terms of adherence and safety. Further clinical trials are required to elucidate ways to effectively use wearable devices in subacute rehabilitation.

(Cost-)effectiveness of a personalized multidisciplinary eHealth intervention for knee arthroplasty patients to enhance return to activities of daily life, work and sports - rationale and protocol of the multicentre ACTIVE randomized controlled trial.

BACKGROUND: With the worldwide rising obesity epidemic and the aging population, it is essential to deliver (cost-)effective care that results in enhanced societal participation among knee arthroplasty patients. The purpose of this study is to describe the development, content, and protocol of our (cost-)effectiveness study that assesses a perioperative integrated care program, including a personalized eHealth app, for knee arthroplasty patients aimed to enhance societal participation post-surgery compared to care as usual. METHODS: The intervention will be tested in a multicentre randomized controlled trial with eleven participating Dutch medical centers (i.e., hospitals and clinics). Working patients on the waiting-list for a total- or unicompartmental knee arthroplasty with the intention to return to work after surgery will be included. After pre-stratification on medical centre with or without eHealth as usual care, operation procedure (total- or unicompartmental knee arthroplasty) and recovery expectations regarding return to work, randomization will take place at the patient-level. A minimum of 138 patients will be included in both the intervention and control group, 276 in total. The control group will receive usual care. On top of care as usual, patients in the intervention group will receive an intervention consisting of three components: 1) a personalized eHealth intervention called ikHerstel ('I Recover') including an activity tracker, 2) goal setting using goal attainment scaling to improve rehabilitation and 3) a referral to a case-manager. Our main outcome is quality of life, based on patient-reported physical functioning (using PROMIS-PF). (Cost-)effectiveness will be assessed from a healthcare and societal perspective. Data collection has been started in 2020 and is expected to finish in 2024. DISCUSSION: Improving societal participation for knee arthroplasty is relevant for patients, health care providers, employers and society. This multicentre randomized controlled trial will evaluate the (cost-)effectiveness of a personalized integrated care program for knee arthroplasty patients, consisting of effective intervention components based on previous studies, compared to care as usual. TRIAL REGISTRATION: Trialsearch.who.int; reference no. NL8525, reference date version 1: 14-04-2020.

Mining Sensor Data to Assess Changes in Physical Activity Behaviors in Health Interventions: Systematic Review.

BACKGROUND: Sensors are increasingly used in health interventions to unobtrusively and continuously capture participants' physical activity in free-living conditions. The rich granularity of sensor data offers great potential for analyzing patterns and changes in physical activity behaviors. The use of specialized machine learning and data mining techniques to detect, extract, and analyze these patterns has increased, helping to better understand how participants' physical activity evolves. OBJECTIVE: The aim of this systematic review was to identify and present the various data mining techniques employed to analyze changes in physical activity behaviors from sensors-derived data in health education and health promotion intervention studies. We addressed two main research questions: (1) What are the current techniques used for mining physical activity sensor data to detect behavior changes in health education or health promotion contexts? (2) What are the challenges and opportunities in mining physical activity sensor data for detecting physical activity behavior changes? METHODS: The systematic review was performed in May 2021 using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We queried the Association for Computing Machinery (ACM), IEEE Xplore, ProQuest, Scopus, Web of Science, Education Resources Information Center (ERIC), and Springer literature databases for peer-reviewed references related to wearable machine learning to detect physical activity changes in health education. A total of 4388 references were initially retrieved from the databases. After removing duplicates and screening titles and abstracts, 285 references were subjected to full-text review, resulting in 19 articles included for analysis. RESULTS: All studies used accelerometers, sometimes in combination with another sensor (37%). Data were collected over a period ranging from 4 days to 1 year (median 10 weeks) from a cohort size ranging between 10 and 11615 (median 74). Data preprocessing was mainly carried out using proprietary software, generally resulting in step counts and time spent in physical activity aggregated predominantly at the daily or minute level. The main features used as input for the data mining models were descriptive statistics of the preprocessed data. The most common data mining methods were classifiers, clusters, and decision-making algorithms, and these focused on personalization (58%) and analysis of physical activity behaviors (42%). CONCLUSIONS: Mining sensor data offers great opportunities to analyze physical activity behavior changes, build models to better detect and interpret behavior changes, and allow for personalized feedback and support for participants, especially where larger sample sizes and longer recording times are available. Exploring different data aggregation levels can help detect subtle and sustained behavior changes. However, the literature suggests that there is still work remaining to improve the transparency, explicitness, and standardization of the data preprocessing and mining processes to establish best practices and make the detection methods easier to understand, scrutinize, and reproduce.

Experience and Satisfaction with a Family-Based Physical Activity Intervention Using Activity Trackers and Apps: A Qualitative Study.

Wearable activity trackers and smartphone apps have been shown to increase physical activity in children and adults. However, interventions using activity trackers and apps have rarely been tested in whole families. This study examined the experience and satisfaction with an activity tracker and app intervention (Step it Up Family) to increase physical activity in whole families. Telephone interviews were conducted with Queensland-based families (n = 19) who participated in the Step it Up Family intervention (N = 40, single-arm, pre/post feasibility study) in 2017/2018. Using commercial activity trackers combined with apps, the intervention included an introductory session, individual and family-level goal setting, self-monitoring, family step challenges, and weekly motivational text messages. Qualitative content analysis was conducted to identify themes, categories and sub-categories. In summary, parents reported that children were engaged with the activity tracker and app features to reach their daily step goals. Some technical difficulties were experienced with app navigation, syncing of activity tracker data, and tracker band discomfort. Although families liked that the weekly text messages reminded them to be active, they did not find them very motivating. Using text messages for physical activity motivation in families requires further testing. Overall, the intervention was well-received by families for increasing physical activity motivation.

Wearable Health Technology for Preoperative Risk Assessment in Elderly Patients: The WELCOME Study.

Preoperative identification of high-risk groups has been extensively studied to improve patients' outcomes. Wearable devices, which can track heart rate and physical activity data, are starting to be evaluated for patients' management. We hypothesized that commercial wearable devices (WD) may provide data associated with preoperative evaluation scales and tests, to identify patients with poor functional capacity at increased risk for complications. We conducted a prospective observational study including seventy-year-old patients undergoing two-hour surgeries under general anesthesia. Patients were asked to wear a WD for 7 days before surgery. WD data were compared to preoperatory clinical evaluation scales and with a 6-min walking test (6MWT). We enrolled 31 patients, with a mean age of 76.1 (SD ± 4.9) years. There were 11 (35%) ASA 3-4 patients. 6MWT results averaged 328.9 (SD ± 99.5) m. Daily steps and 𝑉𝑂2𝑚𝑎𝑥 as recorded using WD and were associated with 6MWT performance (R = 0.56, p = 0.001 and r = 0.58, p = 0.006, respectively) and clinical evaluation scales. This is the first study to evaluate WD as preoperative evaluation tools; we found a strong association between 6MWT, preoperative scales, and WD data. Low-cost wearable devices are a promising tool for the evaluation of cardiopulmonary fitness. Further research is needed to validate WD in this setting.

Enhancing user awareness on inferences obtained from fitness trackers data.

In the IoT era, sensitive and non-sensitive data are recorded and transmitted to multiple service providers and IoT platforms, aiming to improve the quality of our lives through the provision of high-quality services. However, in some cases these data may become available to interested third parties, who can analyse them with the intention to derive further knowledge and generate new insights about the users, that they can ultimately use for their own benefit. This predicament raises a crucial issue regarding the privacy of the users and their awareness on how their personal data are shared and potentially used. The immense increase in fitness trackers use has further increased the amount of user data generated, processed and possibly shared or sold to third parties, enabling the extraction of further insights about the users. In this work, we investigate if the analysis and exploitation of the data collected by fitness trackers can lead to the extraction of inferences about the owners routines, health status or other sensitive information. Based on the results, we utilise the PrivacyEnhAction privacy tool, a web application we implemented in a previous work through which the users can analyse data collected from their IoT devices, to educate the users about the possible risks and to enable them to set their user privacy preferences on their fitness trackers accordingly, contributing to the personalisation of the provided services, in respect of their personal data.