Simon J. Marshall

An Ethical Framework for Automated, Wearable Cameras in Health Behavior Research

Technologic advances mean automated, wearable cameras are now feasible for investigating health behaviors in a public health context. This paper attempts to identify and discuss the ethical implications of such research, in relation to existing guidelines for ethical research in traditional visual methodologies. Research using automated, wearable cameras can be very intrusive, generating unprecedented levels of image data, some of it potentially unflattering or unwanted. Participants and third parties they encounter may feel uncomfortable or that their privacy has been affected negatively. This paper attempts to formalize the protection of all according to best ethical principles through the development of an ethical framework. Respect for autonomy, through appropriate approaches to informed consent and adequate privacy and confidentiality controls, allows for ethical research, which has the potential to confer substantial benefits on the field of health behavior research.

Using the SenseCam to Improve Classifications of Sedentary Behavior in Free-Living Settings

BACKGROUND Studies have shown relationships between important health outcomes and sedentary behavior, independent of physical activity. There are known errors in tools employed to assess sedentary behavior. Studies of accelerometers have been limited to laboratory environments. PURPOSE To assess a broad range of sedentary behaviors in free-living adults using accelerometers and a Microsoft SenseCam that can provide an objective observation of sedentary behaviors through first person-view images. METHODS Participants were 40 university employees who wore a SenseCam and Actigraph accelerometer for 3-5 days. Images were coded for sitting and standing posture and 12 activity types. Data were merged and aggregated to a 60-second epoch. Accelerometer counts per minute (cpm) of <100 were compared with coded behaviors. Sensitivity and specificity analyses were performed. Data were collected in June and July 2011 and analyzed in April 2012. RESULTS TV viewing, other screen use, and administrative activities were correctly classified by the 100-cpm cutpoint. However, standing behaviors also fell under this threshold, and driving behaviors exceeded it. Multiple behaviors occurred simultaneously. A nearly 30-minute per day difference was found in sedentary behavior estimates based on the accelerometer versus the SenseCam. CONCLUSIONS Researchers should be aware of the strengths and weaknesses of the 100-cpm accelerometer cutpoint for identifying sedentary behavior. The SenseCam may be a useful tool in free-living conditions to better understand health behaviors such as sitting.

A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers

Wrist accelerometers are being used in population level surveillance of physical activity (PA) but more research is needed to evaluate their validity for correctly classifying types of PA behavior and predicting energy expenditure (EE). In this study we compare accelerometers worn on the wrist and hip, and the added value of heart rate (HR) data, for predicting PA type and EE using machine learning. Forty adults performed locomotion and household activities in a lab setting while wearing three ActiGraph GT3X+ accelerometers (left hip, right hip, non-dominant wrist) and a HR monitor (Polar RS400). Participants also wore a portable indirect calorimeter (COSMED K4b2), from which EE and metabolic equivalents (METs) were computed for each minute. We developed two predictive models: a random forest classifier to predict activity type and a random forest of regression trees to estimate METs. Predictions were evaluated using leave-one-user-out cross-validation. The hip accelerometer obtained an average accuracy of 92.3% in predicting four activity types (household, stairs, walking, running), while the wrist accelerometer obtained an average accuracy of 87.5%. Across all 8 activities combined (laundry, window washing, dusting, dishes, sweeping, stairs, walking, running), the hip and wrist accelerometers obtained average accuracies of 70.2% and 80.2% respectively. Predicting METs using the hip or wrist devices alone obtained root mean square errors (rMSE) of 1.09 and 1.00 METs per 6 min bout, respectively. Including HR data improved MET estimation, but did not significantly improve activity type classification. These results demonstrate the validity of random forest classification and regression forests for PA type and MET prediction using accelerometers. The wrist accelerometer proved more useful in predicting activities with significant arm movement, while the hip accelerometer was superior for predicting locomotion and estimating EE.

Design and implementation of a randomized controlled social and mobile weight loss trial for young adults (project SMART)

PURPOSE To describe the theoretical rationale, intervention design, and clinical trial of a two-year weight control intervention for young adults deployed via social and mobile media. METHODS A total of 404 overweight or obese college students from three Southern California universities (M(age) = 22( ± 4) years; M(BMI) = 29( ± 2.8); 70% female) were randomized to participate in the intervention or to receive an informational web-based weight loss program. The intervention is based on behavioral theory and integrates intervention elements across multiple touch points, including Facebook, text messaging, smartphone applications, blogs, and e-mail. Participants are encouraged to seek social support among their friends, self-monitor their weight weekly, post their health behaviors on Facebook, and e-mail their weight loss questions/concerns to a health coach. The intervention is adaptive because new theory-driven and iteratively tailored intervention elements are developed and released over the course of the two-year intervention in response to patterns of use and user feedback. Measures of body mass index, waist circumference, diet, physical activity, sedentary behavior, weight management practices, smoking, alcohol, sleep, body image, self-esteem, and depression occur at 6, 12, 18, and 24 months. Currently, all participants have been recruited, and all are in the final year of the trial. CONCLUSION Theory-driven, evidence-based strategies for physical activity, sedentary behavior, and dietary intake can be embedded in an intervention using social and mobile technologies to promote healthy weight-related behaviors in young adults.

Using wearable cameras to categorise type and context of accelerometer-identified episodes of physical activity.

BackgroundAccelerometers can identify certain physical activity behaviours, but not the context in which they take place. This study investigates the feasibility of wearable cameras to objectively categorise the behaviour type and context of participants’ accelerometer-identified episodes of activity.MethodsAdults were given an Actical hip-mounted accelerometer and a SenseCam wearable camera (worn via lanyard). The onboard clocks on both devices were time-synchronised. Participants engaged in free-living activities for 3 days. Actical data were cleaned and episodes of sedentary, lifestyle-light, lifestyle-moderate, and moderate-to-vigorous physical activity (MVPA) were identified. Actical episodes were categorised according to their social and environmental context and Physical Activity (PA) compendium category as identified from time-matched SenseCam images.ResultsThere were 212 days considered from 49 participants from whom SenseCam images and associated Actical data were captured. Using SenseCam images, behaviour type and context attributes were annotated for 386 (out of 3017) randomly selected episodes (such as walking/transportation, social/not-social, domestic/leisure). Across the episodes, 12 categories that aligned with the PA Compendium were identified, and 114 subcategory types were identified. Nineteen percent of episodes could not have their behaviour type and context categorized; 59% were outdoors versus 39% indoors; 33% of episodes were recorded as leisure time activities, with 33% transport, 18% domestic, and 15% occupational. 33% of the randomly selected episodes contained direct social interaction and 22% were in social situations where the participant wasn’t involved in direct engagement.ConclusionWearable camera images offer an objective method to capture a spectrum of activity behaviour types and context across 81% of accelerometer-identified episodes of activity. Wearable cameras represent the best objective method currently available to categorise the social and environmental context of accelerometer-defined episodes of activity in free-living conditions.

The Relationship Between Outdoor Activity and Health in Older Adults Using GPS

Physical activity (PA) provides health benefits in older adults. Research suggests that exposure to nature and time spent outdoors may also have effects on health. Older adults are the least active segment of our population, and are likely to spend less time outdoors than other age groups. The relationship between time spent in PA, outdoor time, and various health outcomes was assessed for 117 older adults living in retirement communities. Participants wore an accelerometer and GPS device for 7 days. They also completed assessments of physical, cognitive, and emotional functioning. Analyses of variance were employed with a main and interaction effect tested for ±30 min PA and outdoor time. Significant differences were found for those who spent >30 min in PA or outdoors for depressive symptoms, fear of falling, and self-reported functioning. Time to complete a 400 m walk was significantly different by PA time only. QoL and cognitive functioning scores were not significantly different. The interactions were also not significant. This study is one of the first to demonstrate the feasibility of using accelerometer and GPS data concurrently to assess PA location in older adults. Future analyses will shed light on potential causal relationships and could inform guidelines for outdoor activity.

Identifying Active Travel Behaviors in Challenging Environments Using GPS, Accelerometers, and Machine Learning Algorithms

Background: Active travel is an important area in physical activity research, but objective measurement of active travel is still difficult. Automated methods to measure travel behaviors will improve research in this area. In this paper, we present a supervised machine learning method for transportation mode prediction from global positioning system (GPS) and accelerometer data. Methods: We collected a dataset of about 150 h of GPS and accelerometer data from two research assistants following a protocol of prescribed trips consisting of five activities: bicycling, riding in a vehicle, walking, sitting, and standing. We extracted 49 features from 1-min windows of this data. We compared the performance of several machine learning algorithms and chose a random forest algorithm to classify the transportation mode. We used a moving average output filter to smooth the output predictions over time. Results: The random forest algorithm achieved 89.8% cross-validated accuracy on this dataset. Adding the moving average filter to smooth output predictions increased the cross-validated accuracy to 91.9%. Conclusion: Machine learning methods are a viable approach for automating measurement of active travel, particularly for measuring travel activities that traditional accelerometer data processing methods misclassify, such as bicycling and vehicle travel.

Objectively measured physical activity is related to cognitive function in older adults.

To explore the relationship between cognitive functioning and time spent at different intensities of physical activity (PA) in free‐living older adults.

Applying the ecological model of behavior change to a physical activity trial in retirement communities: Description of the study protocol

OBJECTIVES To describe the intervention protocol for the first multilevel ecological intervention for physical activity in retirement communities that addresses individual, interpersonal and community influences on behavior change. DESIGN A cluster randomized controlled trial design was employed with two study arms: a physical activity intervention and an attention control successful aging condition. SETTING Sixteen continuing care retirement communities in San Diego County. PARTICIPANTS Three hundred twenty older adults, aged 65 years and older, are being recruited to participate in the trial. In addition, peer leaders are being recruited to lead some study activities, especially to sustain the intervention after study activities ceased. INTERVENTION Participants in the physical activity trial receive individual, interpersonal and community intervention components. The individual level components include pedometers, goal setting and individual phone counseling. The interpersonal level components include group education sessions and peer-led activities. The community level components include resource audits and enumeration, tailored walking maps, and community improvement projects. The successful aging group receives individual and group attention about successful aging topics. MEASUREMENTS The main outcome is light to moderate physical activity, measured objectively by accelerometry. Other objective outcomes included physical functioning, blood pressure, physical fitness, and cognitive functioning. Self report measures include depressive symptoms and health related quality of life. RESULTS The intervention is being delivered successfully in the communities and compliance rates are high. CONCLUSION Ecological Models call for interventions that address multiple levels of the model. Previous studies have not included components at each level and retirement communities provide a model environment to demonstrate how to implement such an intervention.

Accelerometer adherence and performance in a cohort study of US Hispanic adults.

PURPOSE This study described participant adherence to wearing the accelerometer and accelerometer performance in a cohort study of adults. METHODS From 2008 to 2011, 16,415 US Hispanic/Latino adults age 18-74 yr enrolled in the Hispanic Community Health Study/Study of Latinos. Immediately after the baseline visit, participants wore an Actical accelerometer for 1 wk. This study explored correlates of accelerometer participation and adherence, defined as wearing it for at least three of a possible six days for ≥10 h·d. Accelerometer performance was assessed by exploring the number of different values of accelerometer counts per minute for each participant. RESULTS Overall, 92.3% (n = 15,153) had at least 1 d with accelerometer data and 77.7% (n = 12,750) were adherent. Both accelerometer participation and adherence were higher among participants who were married or partnered, reported a higher household income, were first-generation immigrants, or reported lower sitting time. Participation was also higher among those with no stair limitations. Adherence was higher among participants who were male, older, employed or retired, not US born, preferred Spanish over English, reported higher work activity or lower recreational activity, and with a lower body mass index. Among the sample that met the adherence definition, the maximum recorded count per minute was 12,000, and there were a total of 5846 different counts per minute. On average, participants had 112.5 different counts per minute over 6 d (median, 106; interquartile range, 91-122). The number of different counts per minute was higher among men, younger ages, normal weight, and those with higher accelerometer-assessed physical activity. CONCLUSION Several correlates differed between accelerometer participation and adherence. These characteristics could be targeted in future studies to improve accelerometer wear. The performance of the accelerometer provided insight into creating a more accurate nonwear algorithm.