Dietary Assessment with a Wearable Camera among Children: Feasibility and Intercoder Reliability

Estimating Amount of Food in a Circular Dining Bowl from a Single Image

Unhealthy diet is a top risk factor causing obesity and numerous chronic diseases. To help the public adopt healthy diet, nutrition scientists need user-friendly tools to conduct Dietary Assessment (DA). In recent years, new DA tools have been developed using a smartphone or a wearable device which acquires images during a meal. These images are then processed to estimate calories and nutrients of the consumed food. Although considerable progress has been made, 2D food images lack scale reference and 3D volumetric information. In addition, food must be sufficiently observable from the image. This basic condition can be met when the food is stand-alone (no food container is used) or it is contained in a shallow plate. However, the condition cannot be met easily when a bowl is used. The food is often occluded by the bowl edge, and the shape of the bowl may not be fully determined from the image. However, bowls are the most utilized food containers by billions of people in many parts of the world, especially in Asia and Africa. In this work, we propose to premeasure plates and bowls using a marked adhesive strip before a dietary study starts. This simple procedure eliminates the use of a scale reference throughout the DA study. In addition, we use mathematical models and image processing to reconstruct the bowl in 3D. Our key idea is to estimate how full the bowl is rather than how much food is (in either volume or weight) in the bowl. This idea reduces the effect of occlusion. The experimental data have shown satisfactory results of our methods which enable accurate DA studies using both plates and bowls with reduced burden on research participants.

Diet Quality among Pre-Adolescent African American Girls in a Randomized Controlled Obesity Prevention Intervention Trial

Consuming an unhealthy diet increases health risks. This study assessed the impact of a culturally adapted behaviorally innovative obesity prevention intervention (The Butterfly Girls and the Quest for Founder's Rock) on diet quality in pre-adolescent non-Hispanic Black/African American girls. The RCT consisted of three groups (experimental, comparison, and waitlist control); block randomization allocated participants to each group. The two treatment groups varied in terms of whether or not they set goals. Data were collected at baseline (prior to receiving the intervention), post 1 (3 months post-baseline), and post 2 (6 months post-baseline). Two dietitian-assisted 24 h dietary recalls were collected at each timepoint. Healthy Eating Index 2015 (HEI-2015) was used to determine diet quality. A total of 361 families were recruited; 342 completed baseline data collection. No significant differences in overall HEI score or component scores were observed. To attain more equitable health outcomes, future efforts to promote dietary intake change among at-risk children should explore other behavior change procedures and employ more child-friendly dietary assessment methods.

Dietary Behavior Assessments in Children-A Mixed-Method Research Exploring the Perspective of Pediatric Dieticians on Innovative Technologies

Background

Assessing dietary intake and eating behavior in children is challenging, owing to children's undeveloped food knowledge and perception of portion sizes. Additionally, caregivers cannot always provide complete surrogate information. Consequently, validated dietary behavior assessment methods for children are limited, but technological innovations offer opportunities for the development of new tools. One of the first steps in the developmental process of a newly developed pediatric dietary assessment tool includes an alignment of the needs and preferences of pediatric dieticians (PDs) as potential users.

Objectives

To explore opinions of Dutch PDs about traditional dietary behavior assessment methods for children and potential technological innovations to replace or support traditional methods.

Methods

Ten PDs participated in semistructured interviews (total of 7.5 h) based on 2 theoretical frameworks, and data saturation was reached after the seventh interview. Interview transcripts were inductively coded in an iterative process, and overarching themes and domains were identified. Interview data were then used as input for an extensive online survey completed by 31 PDs who were not involved in the initial interview rounds.

Results

PDs discussed their perspective on dietary behavior assessments in 4 domains: traditional methods, technological methods, future methods, and external influences on these methods. Generally, PDs felt that traditional methods supported them in reaching their desired goals. However, the time needed to obtain a comprehensive overview of dietary intake behavior and the reliability of conventional methods were mentioned as limitations. For future technologies, PDs mention the ease of use and engaging in children as opportunities.

Conclusions

PDs have a positive attitude toward the use of technology for dietary behavior assessments. Further development of assessment technologies should be tailored to the needs of children in different care situations and age categories to increase its usability among children, their caregivers, and dietician. Curr Dev Nutr 2023;xx:xx.

Automated wearable cameras for improving recall of diet and time use in Uganda: a cross-sectional feasibility study

BACKGROUND

Traditional recall approaches of data collection for assessing dietary intake and time use are prone to recall bias. Studies in high- and middle-income countries show that automated wearable cameras are a promising method for collecting objective health behavior data and may improve study participants' recall of foods consumed and daily activities performed. This study aimed to evaluate the feasibility of using automated wearable cameras in rural Eastern Ugandan to collect dietary and time use data.

METHODS

Mothers of young children (n = 211) wore an automated wearable camera on 2 non-consecutive days while continuing their usual activities. The day after wearing the camera, participants' dietary diversity and time use was assessed using an image-assisted recall. Their experiences of the method were assessed via a questionnaire.

RESULTS

Most study participants reported their experiences with the automated wearable camera and image-assisted recall to be good (36%) or very good (56%) and would participate in a similar study in the future (97%). None of the eight study withdrawals could be definitively attributed to the camera. Fifteen percent of data was lost due to device malfunction, and twelve percent of the images were "uncodable" due to insufficient lighting. Processing and analyzing the images were labor-intensive, time-consuming, and prone to human error. Half (53%) of participants had difficulty interpreting the images captured by the camera.

CONCLUSIONS

Using an automated wearable camera in rural Eastern Uganda was feasible, although improvements are needed to overcome the challenges common to rural, low-income country contexts and reduce the burdens posed on both participants and researchers. To improve the quality of data obtained, future automated wearable camera-based image assisted recall studies should use a structured data format to reduce image coding time; electronically code the data in the field, as an output of the image review process, to eliminate ex post facto data entry; and, ideally, use computer-assisted personal interviews software to ensure completion and reduce errors. In-depth formative work in partnership with key local stakeholders (e.g., researchers from low-income countries, representatives from government and/or other institutional review boards, and community representatives and local leaders) is also needed to identify practical approaches to ensuring that the ethical rights of automated wearable camera study participants in low-income countries are adequately protected.

Technological tools for assessing children's food intake: a scoping review

Technological innovations can standardise and minimise reporting errors in dietary assessment. This scoping review aimed to summarise the characteristics of technological tools used to assess children's food intake. The review followed the Joanna Briggs Institute's manual. The main inclusion criterion was studied that assessed the dietary intake of children 0-9 years of age using technology. We also considered articles on validation and calibration of technologies. We retrieved 15 119 studies and 279 articles were read in full, after which we selected 93 works that met the eligibility criteria. Forty-six technologies were identified, 37 % of which had been developed in Europe and 32⋅6 % in North America; 65⋅2 % were self-administered; 27 % were used exclusively at home; 37 % involved web-based software and more than 80 % were in children over 6 years of age. 24HR was the most widely used traditional method in the technologies (56⋅5 %), and 47⋅8 % of the tools were validated. The review summarised helpful information for studies on using existing tools or that intend to develop or validate tools with various innovations. It focused on places with a shortage of such technologies.

Feasibility of the automatic ingestion monitor (AIM-2) for infant feeding assessment: a pilot study among breast-feeding mothers from Ghana

OBJECTIVE

Passive, wearable sensors can be used to obtain objective information in infant feeding, but their use has not been tested. Our objective was to compare assessment of infant feeding (frequency, duration and cues) by self-report and that of the Automatic Ingestion Monitor-2 (AIM-2).

DESIGN

A cross-sectional pilot study was conducted in Ghana. Mothers wore the AIM-2 on eyeglasses for 1 d during waking hours to assess infant feeding using images automatically captured by the device every 15 s. Feasibility was assessed using compliance with wearing the device. Infant feeding practices collected by the AIM-2 images were annotated by a trained evaluator and compared with maternal self-report via interviewer-administered questionnaire.

SETTING

Rural and urban communities in Ghana.

PARTICIPANTS

Participants were thirty eight (eighteen rural and twenty urban) breast-feeding mothers of infants (child age ≤7 months).

RESULTS

Twenty-five mothers reported exclusive breast-feeding, which was common among those < 30 years of age (n 15, 60 %) and those residing in urban communities (n 14, 70 %). Compliance with wearing the AIM-2 was high (83 % of wake-time), suggesting low user burden. Maternal report differed from the AIM-2 data, such that mothers reported higher mean breast-feeding frequency (eleven v. eight times, P = 0·041) and duration (18·5 v. 10 min, P = 0·007) during waking hours.

CONCLUSION

The AIM-2 was a feasible tool for the assessment of infant feeding among mothers in Ghana as a passive, objective method and identified overestimation of self-reported breast-feeding frequency and duration. Future studies using the AIM-2 are warranted to determine validity on a larger scale.

Validation of an Automated Wearable Camera-Based Image-Assisted Recall Method and the 24-h Recall Method for Assessing Women's Time Allocation in a Nutritionally Vulnerable Population: The Case of Rural Uganda

Accurate data are essential for investigating relationships between maternal time-use patterns and nutritional outcomes. The 24 h recall (24HR) has traditionally been used to collect time-use data, however, automated wearable cameras (AWCs) with an image-assisted recall (IAR) may reduce recall bias. This study aimed to evaluate their concurrent criterion validity for assessing women’s time use in rural Eastern Ugandan. Women’s (n = 211) time allocations estimated via the AWC-IAR and 24HR methods were compared with direct observation (criterion method) using the Bland–Altman limits of agreement (LOA) method of analysis and Cronbach’s coefficient alpha (time allocation) or Cohen’s κ (concurrent activities). Systematic bias varied from 1 min (domestic chores) to 226 min (caregiving) for 24HR and 1 min (own production) to 109 min (socializing) for AWC-IAR. The LOAs were within 2 h for employment, own production, and self-care for 24HR and AWC-IAR but exceeded 11 h (24HR) and 9 h (AWC-IAR) for caregiving and socializing. The LOAs were within four concurrent activities for 24HR (−1.1 to 3.7) and AWC-IAR (−3.2 to 3.2). Cronbach’s alpha for time allocation ranged from 0.1728 (socializing) to 0.8056 (own production) for 24HR and 0.2270 (socializing) to 0.7938 (own production) for AWC-IAR. For assessing women’s time allocations at the population level, the 24HR and AWC-IAR methods are accurate and reliable for employment, own production, and domestic chores but poor for caregiving and socializing. The results of this study suggest the need to revisit previously published research investigating the associations between women’s time allocations and nutrition outcomes.

Using Wearable Cameras to Categorize the Type and Context of Screen-Based Behaviors Among Adolescents: Observational Study

BACKGROUND

Automated wearable cameras present a new opportunity to accurately assess human behavior. However, this technology is seldom used in the study of adolescent's screen exposure, and the field is reliant on poor-quality self-report data.

OBJECTIVE

This study aimed to examine adolescents' screen exposure by categorizing the type and context of behaviors using automated wearable cameras.

METHODS

Adolescents (mean age 15.4 years, SD 1.6 years; n=10) wore a camera for 3 school evenings and 1 weekend day. The camera captured an image every 10 seconds. Fieldwork was completed between February and March 2020, and data were analyzed in August 2020. Images were date and time stamped, and coded for screen type, content, and context.

RESULTS

Data representing 71,396 images were analyzed. Overall, 74.0% (52,842/71,396) of images contained screens and 16.8% (11,976/71,396) of images contained multiple screens. Most screen exposures involved television sets (25,950/71,396, 36.3%), smartphones (20,851/71,396, 29.2%), and laptop computers (15,309/71,396, 21.4%). The context of screen use differed by device type, although most screen exposures occurred at home (62,455/64,856, 96.3%) and with solitary engagement (54,430/64,856, 83.9%). The immediate after-school period saw high laptop computer use (4785/15,950, 30.0%), while smartphone use (2059/5320, 38.7%) peaked during prebedtime hours. Weekend screen exposure was high, with smartphone use (1070/1927, 55.5%) peaking in the early morning period and fluctuating throughout the day.

CONCLUSIONS

There was evidence for high screen use during the after-school and weekend period, mostly through solitary engagement, and within the home environment. The findings may inform the basis of larger studies aimed at examining screen exposure in free-living conditions.

Sedentary Behavior in Children by Wearable Cameras: Development of an Annotation Protocol

INTRODUCTION

There is increasing evidence that not all types of sedentary behavior have the same harmful effects on children's health. Hence, there has been a growing interest in the use of wearable cameras. The aim of this study is to develop a protocol to categorize children's wearable camera data into sedentary behavior components.

METHODS

Wearable camera data were collected in 3 different samples of children in 2014. A development sample (3 children aged 4-8 years) was used to design the annotation protocol. A training sample (4 children aged 10 years) was used to train 3 different coders. The independent reliability sample (14 children aged 9-11 years) was used for independent coding of wearable camera images and to estimate inter-rater agreement. Data were analyzed in 2018. Cohen's κ was calculated for every rater pair on a per-participant basis. Means and SDs were then calculated across per-participant κ scores.

RESULTS

A total of 41,651 images from 14 participants were considered for analysis. Inter-rater agreement over all raters over all the sedentary behavior components was almost perfect (mean κ=0.85, 95% CI=0.83, 0.87). Inter-rater reliability for screen-based sedentary behavior (mean κ=0.72, 95% CI=0.62, 0.82) and nonscreen sedentary behavior (κ=0.69, 95% CI=0.65, 0.72) showed substantial agreement. Inter-rater reliability for location (κ=0.91, 95% CI=0.88, 0.93) showed almost perfect agreement.

CONCLUSIONS

A reliable annotation protocol to categorize wearable camera data of children into sedentary behavior components was developed. Once applied to larger samples in children, this protocol can ultimately help to better understand the potential harms of screen time and sedentary behavior in children.

Privacy Perceptions and Concerns in Image-Based Dietary Assessment Systems: Questionnaire-Based Study

BACKGROUND

Complying with individual privacy perceptions is essential when processing personal information for research. Our specific research area is performance development of elite athletes, wherein nutritional aspects are important. Before adopting new automated tools that capture such data, it is crucial to understand and address the privacy concerns of the research subjects that are to be studied. Privacy as contextual integrity emphasizes understanding contextual sensitivity in an information flow. In this study, we explore privacy perceptions in image-based dietary assessments. This research field lacks empirical evidence on what will be considered as privacy violations when exploring trends in long-running studies. Prior studies have only classified images as either private or public depending on their basic content. An assessment and analysis are thus needed to prevent unwanted consequences of privacy breach and other issues perceived as sensitive when designing systems for dietary assessment by using food images.

OBJECTIVE

The aim of this study was to investigate common perceptions of computer systems using food images for dietary assessment. The study delves into perceived risks and data-sharing behaviors.

METHODS

We investigated the privacy perceptions of 105 individuals by using a web-based survey. We analyzed these perceptions along with perceived risks in sharing dietary information with third parties.

RESULTS

We found that understanding the motive behind the use of data increases its chances of sharing with a social group.

CONCLUSIONS

In this study, we highlight various privacy concerns that can be addressed during the design phase. A system design that is compliant with general data protection regulations will increase participants' and stakeholders' trust in an image-based dietary assessment system. Innovative solutions are needed to reduce the intrusiveness of a continuous assessment. Individuals show varying behaviors for sharing metadata, as knowing what the data is being used for, increases the chance of it being shared.

Future Directions for Integrative Objective Assessment of Eating Using Wearable Sensing Technology

Established methods for nutritional assessment suffer from a number of important limitations. Diaries are burdensome to complete, food frequency questionnaires only capture average food intake, and both suffer from difficulties in self estimation of portion size and biases resulting from misreporting. Online and app versions of these methods have been developed, but issues with misreporting and portion size estimation remain. New methods utilizing passive data capture are required that address reporting bias, extend timescales for data collection, and transform what is possible for measuring habitual intakes. Digital and sensing technologies are enabling the development of innovative and transformative new methods in this area that will provide a better understanding of eating behavior and associations with health. In this article we describe how wrist-worn wearables, on-body cameras, and body-mounted biosensors can be used to capture data about when, what, and how much people eat and drink. We illustrate how these new techniques can be integrated to provide complete solutions for the passive, objective assessment of a wide range of traditional dietary factors, as well as novel measures of eating architecture, within person variation in intakes, and food/nutrient combinations within meals. We also discuss some of the challenges these new approaches will bring.

The development of food image detection and recognition model of Korean food for mobile dietary management

BACKGROUND/OBJECTIVES

The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake.

SUBJECTS/METHODS

We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of 150 × 150 and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition.

RESULTS

Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks.

CONCLUSION

The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

Feasibility of Automated Cameras to Measure Screen Use in Adolescents

INTRODUCTION

The influence of screens and technology on adolescent well-being is controversial and there is a need to improve methods to measure these behaviors. This study examines the feasibility and acceptability of using automated wearable cameras to measure evening screen use in adolescents.

METHODS

A convenience sample of adolescents (aged 13-17 years, n=15) wore an automated camera for 3 evenings from 5:00pm to bedtime. The camera (Brinno TLC120) captured an image every 15 seconds. Fieldwork was completed between October and December 2017, and data analyzed in 2018. Feasibility was examined by quality of the captured images, wear time, and whether images could be coded in relation to contextual factors (e.g., type of screen and where screen use occurred). Acceptability was examined by participant compliance to the protocol and from an exit interview.

RESULTS

Data from 39 evenings were analyzed (41,734 images), with a median of 268 minutes per evening. The camera was worn for 78% of the evening on Day 1, declining to 51% on Day 3. Nearly half of the images contained a screen in active use (46%), most commonly phones (13.7%), TV (12.6%), and laptops (8.2%). Multiple screen use was evident in 5% of images. Within the exit interview, participants raised no major concerns about wearing the camera, and data loss because of deletions or privacy concerns was minimal (mean, 14 minutes, 6%).

CONCLUSIONS

Automated cameras offer a feasible, acceptable method of measuring prebedtime screen behavior, including environmental context and aspects of media multitasking in adolescents.

Feasibility of wearable cameras to assess screen time and time spent restrained in children aged 3 to 5 years: a study protocol

INTRODUCTION

Wearable cameras may help overcome the limitations of existing tools to measure young children's sedentary behaviour, but their use introduces a range of ethical challenges. The primary aim of this study is to determine the feasibility of using wearable cameras to measure the two aspects of sedentary behaviour currently included in evidence-based guidelines (ie, screen time and time spent restrained). If shown to be feasible, a secondary aim will be to validate subjective measures against the directly measured screen time and time spent restrained.

METHODS AND ANALYSIS

A convenience sample (n=20) will be recruited via flyers at the University of Strathclyde and advertisements on online forums for parents of young children (aged 3 to 5 years). Children will be provided with a wearable camera, attached to the front of their clothing with a clip, to be worn for 3 days (2 non-childcare days and 1 weekend day) in non-public settings. Once switched on, the camera will record continuous video footage. Parents will complete an online survey providing their feedback on their own and their child's experience of the wearable camera. They will also report their own and their child's demographical characteristics and their child's usual daily screen time and time spent restrained in the past week. Data will be downloaded using specialised software and second-by-second coding will be undertaken. Feasibility and acceptability will be assessed using percentages and by analysing qualitative data. If feasibility is shown, intraclass coefficients will be used to determine agreement between video data and parent-reported sedentary behaviours.

ETHICS AND DISSEMINATION

Ethical approval has been granted by the School of Psychological Sciences and Health Ethics Committee at the University of Strathclyde. Results will be used to inform future studies and will be disseminated in peer-reviewed journals and at major international conferences.

Advances and Controversies in Diet and Physical Activity Measurement in Youth

Technological advancements in the past decades have improved dietary intake and physical activity measurements. This report reviews current developments in dietary intake and physical activity assessment in youth. Dietary intake assessment has relied predominantly on self-report or image-based methods to measure key aspects of dietary intake (e.g., food types, portion size, eating occasion), which are prone to notable methodologic (e.g., recall bias) and logistic (e.g., participant and researcher burden) challenges. Although there have been improvements in automatic eating detection, artificial intelligence, and sensor-based technologies, participant input is often needed to verify food categories and portions. Current physical activity assessment methods, including self-report, direct observation, and wearable devices, provide researchers with reliable estimations for energy expenditure and bodily movement. Recent developments in algorithms that incorporate signals from multiple sensors and technology-augmented self-reporting methods have shown preliminary efficacy in measuring specific types of activity patterns and relevant contextual information. However, challenges in detecting resistance (e.g., in resistance training, weight lifting), prolonged physical activity monitoring, and algorithm (non)equivalence remain to be addressed. In summary, although dietary intake assessment methods have yet to achieve the same validity and reliability as physical activity measurement, recent developments in wearable technologies in both arenas have the potential to improve current assessment methods.

THEME INFORMATION

This article is part of a theme issue entitled Innovative Tools for Assessing Diet and Physical Activity for Health Promotion, which is sponsored by the North American branch of the International Life Sciences Institute.