Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring.

Camera-based passive dietary intake monitoring is able to continuously capture the eating episodes of a subject, recording rich visual information, such as the type and volume of food being consumed, as well as the eating behaviors of the subject. However, there currently is no method that is able to incorporate these visual clues and provide a comprehensive context of dietary intake from passive recording (e.g., is the subject sharing food with others, what food the subject is eating, and how much food is left in the bowl). On the other hand, privacy is a major concern while egocentric wearable cameras are used for capturing. In this article, we propose a privacy-preserved secure solution (i.e., egocentric image captioning) for dietary assessment with passive monitoring, which unifies food recognition, volume estimation, and scene understanding. By converting images into rich text descriptions, nutritionists can assess individual dietary intake based on the captions instead of the original images, reducing the risk of privacy leakage from images. To this end, an egocentric dietary image captioning dataset has been built, which consists of in-the-wild images captured by head-worn and chest-worn cameras in field studies in Ghana. A novel transformer-based architecture is designed to caption egocentric dietary images. Comprehensive experiments have been conducted to evaluate the effectiveness and to justify the design of the proposed architecture for egocentric dietary image captioning. To the best of our knowledge, this is the first work that applies image captioning for dietary intake assessment in real-life settings.

Evaluation of Acceptability, Functionality, and Validity of a Passive Image-Based Dietary Intake Assessment Method in Adults and Children of Ghanaian and Kenyan Origin Living in London, UK.

BACKGROUND: Accurate estimation of dietary intake is challenging. However, whilst some progress has been made in high-income countries, low- and middle-income countries (LMICs) remain behind, contributing to critical nutritional data gaps. This study aimed to validate an objective, passive image-based dietary intake assessment method against weighed food records in London, UK, for onward deployment to LMICs. METHODS: Wearable camera devices were used to capture food intake on eating occasions in 18 adults and 17 children of Ghanaian and Kenyan origin living in London. Participants were provided pre-weighed meals of Ghanaian and Kenyan cuisine and camera devices to automatically capture images of the eating occasions. Food images were assessed for portion size, energy, nutrient intake, and the relative validity of the method compared to the weighed food records. RESULTS: The Pearson and Intraclass correlation coefficients of estimates of intakes of food, energy, and 19 nutrients ranged from 0.60 to 0.95 and 0.67 to 0.90, respectively. Bland-Altman analysis showed good agreement between the image-based method and the weighed food record. Under-estimation of dietary intake by the image-based method ranged from 4 to 23%. CONCLUSIONS: Passive food image capture and analysis provides an objective assessment of dietary intake comparable to weighed food records.

I2N: image to nutrients, a sensor guided semi-automated tool for annotation of images for nutrition analysis of eating episodes.

Introduction: Dietary assessment is important for understanding nutritional status. Traditional methods of monitoring food intake through self-report such as diet diaries, 24-hour dietary recall, and food frequency questionnaires may be subject to errors and can be time-consuming for the user. Methods: This paper presents a semi-automatic dietary assessment tool we developed - a desktop application called Image to Nutrients (I2N) - to process sensor-detected eating events and images captured during these eating events by a wearable sensor. I2N has the capacity to offer multiple food and nutrient databases (e.g., USDA-SR, FNDDS, USDA Global Branded Food Products Database) for annotating eating episodes and food items. I2N estimates energy intake, nutritional content, and the amount consumed. The components of I2N are three-fold: 1) sensor-guided image review, 2) annotation of food images for nutritional analysis, and 3) access to multiple food databases. Two studies were used to evaluate the feasibility and usefulness of I2N: 1) a US-based study with 30 participants and a total of 60 days of data and 2) a Ghana-based study with 41 participants and a total of 41 days of data). Results: In both studies, a total of 314 eating episodes were annotated using at least three food databases. Using I2N's sensor-guided image review, the number of images that needed to be reviewed was reduced by 93% and 85% for the two studies, respectively, compared to reviewing all the images. Discussion: I2N is a unique tool that allows for simultaneous viewing of food images, sensor-guided image review, and access to multiple databases in one tool, making nutritional analysis of food images efficient. The tool is flexible, allowing for nutritional analysis of images if sensor signals aren't available.

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.

Sensor-Controlled Digital Game for Heart Failure Self-management: Protocol for a Randomized Controlled Trial.

BACKGROUND: Heart failure (HF) is the leading cause of hospitalization among older adults in the United States. There are substantial racial and geographic disparities in HF outcomes, with patients living in southern US states having a mortality rate 69% higher than the national average. Self-management behaviors, particularly daily weight monitoring and physical activity, are extremely important in improving HF outcomes; however, patients typically have particularly low adherence to these behaviors. With the rise of digital technologies to improve health outcomes and motivate health behaviors, sensor-controlled digital games (SCDGs) have become a promising approach. SCDGs, which leverage sensor-connected technologies, offer the benefits of being portable and scalable and allowing for continuous observation and motivation of health behaviors in their real-world contexts. They are also becoming increasingly popular among older adults and offer an immersive and accessible way to measure self-management behaviors and improve adherence. No SCDGs have been designed for older adults or evaluated to test their outcomes. OBJECTIVE: This randomized clinical trial aims to assess the efficacy of a SCDG in integrating the behavioral data of participants with HF from weight scale and activity tracker sensors to activate game progress, rewards, and feedback and, ultimately, to improve adherence to important self-management behaviors. METHODS: A total of 200 participants with HF, aged ≥45 years, will be recruited and randomized into 2 groups: the SCDG playing group (intervention group) and sensor-only group (control group). Both groups will receive a weight scale, physical activity tracker, and accompanying app, whereas only the intervention group will play the SCDG. This design, thereby, assesses the contributions of the game. All participants will complete a baseline survey as well as posttests at 6 and 12 weeks to assess the immediate effect of the intervention. They will also complete a third posttest at 24 weeks to assess the maintenance of behavioral changes. Efficacy and benefits will be assessed by measuring improvements in HF-related proximal outcomes (self-management behaviors of daily weight monitoring and physical activity) and distal outcomes (HF hospitalization, quality of life, and functional status) between baseline and weeks 6, 12, and 24. The primary outcome measured will be days with weight monitoring, for which this design provides at least 80% power to detect differences between the 2 groups. RESULTS: Recruitment began in the fall of 2022, and the first patient was enrolled in the study on November 7, 2022. Recruitment of the last participant is expected in quarter 1 of 2025. Publication of complete results and data from this study is expected in 2026. CONCLUSIONS: This project will generate insight and guidance for scalable and easy-to-use digital gaming solutions to motivate persistent adherence to HF self-management behaviors and improve health outcomes among individuals with HF. TRIAL REGISTRATION: ClinicalTrials.gov NCT05056129; https://clinicaltrials.gov/ct2/show/NCT05056129. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/45801.

Rationale and design of a pilot randomized controlled trial to increase moderate-to-vigorous physical activity in preadolescent Latina girls and their mothers.

Background: Hispanic/Latina girls have a low prevalence of moderate-intensity physical activity (PA) compared to their male counterparts and non-Hispanic White girls. Mothers influence their children's activity levels by creating and supporting PA opportunities, modeling PA, and reinforcing children's efforts to be physically active. The Conmigo trial will evaluate a mother-daughter intervention to promote PA and examine potential mechanisms of change including mothers' PA, parenting regarding PA, and mother-daughter communication. Method: This randomized controlled trial examines the feasibility, acceptability, and impact of a 12-week intervention promoting PA in preadolescent Latina girls in San Diego County, CA. Participants (n = 90 dyads) are randomized to the Conmigo PA intervention or to a control group that receive an abbreviated version of the intervention. The intervention was informed by Social Cognitive Theory and Family Systems Theory and emphasize family-level factors to promote PA using an actor-partner model. Mothers and daughters attend weekly 90-min sessions in English or in Spanish via Zoom video conferencing, supported by facilitator follow-ups and WhatsApp supportive chat group for mothers. Objective (accelerometer) and self-report measures at baseline, 3 months, and 6 months capture the frequency and intensity of PA and correlates and predictors of PA. We also examine the impact of the intervention on the bidirectional influence of mother-daughter PA. Implications: The findings from the Conmigo trial will form the basis of a randomized controlled community trial and will move the field forward in identifying targets of change in preventing chronic disease risk in Hispanic/Latino communities.

Validated assessment tools for screen media use: A systematic review.

OBJECTIVE: Accurate measurement of adult and child screen media use are needed to robustly assess its impact on health outcomes. Our objective was to systematically review screen media use measurement tools that have been validated against an objective "gold standard" tool. METHODS: The search strategy was initially conducted in Medline Ovid and translated to Embase, Web of Science, PsychInfo and Cochrane. A modified natural language search was conducted in Google Scholar and IEEE. The initial search was conducted in March 2021, and an updated search was conducted in June 2022. Additional studies were included from the references. Studies had to describe the validation of a tool to measure screen media use on participants of any age against a 'gold standard' or comparable objective measure. The COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) was used to assess the criterion validity. Four authors reviewed the titles in two rounds and extracted data. RESULTS: Twenty-nine articles were included in the review. Studies measured TV, computer, mobile device and social media site screen media use through: self or parent report, direct or video observation, computer and mobile device use tracking programs, and through other novel devices such as wearable devices and cameras. Correlations of self or parent report of screen media with the gold standard were lower than correlations of technology-based measures, and video observation with the gold standard. The COSMIN criterion validity ratings ranged from poor to excellent; most of the studies received a global score of fair or poor. CONCLUSIONS: Technology based validated tools that more directly measure screen use are emerging that have been validated against a gold standard for measuring screen use. However, practical, objective measures of diverse types of screen media use that have been tested on diverse populations are needed to better understand the impact of screen media use on the development and physical and mental health of children and adults.

Examination of parent-reported differences in children's daily screen use, sleep, and sleep hygiene behaviors during the school year and summer and their association with BMI.

OBJECTIVE: The current study examined school-summer differences in children's sleep patterns and sleep hygiene. Cross-sectional relationships with children's sleep, sleep hygiene, and weight status were explored during the school year and summer. METHODS: Children (5-8 years) and their parents (n = 197 dyads) were recruited from 4 schools in southeastern Texas and via Facebook. Parents reported children's school year and summer sleep, sleep hygiene, and screen media use. Children's body mass index (BMI) was objectively assessed at the beginning and end of the summer. Associations between children's sleep hygiene and screen media use, sleep duration, and weight status were explored. RESULTS: Children's sleep midpoint was earlier during the school year (1:54 AM ± 0.03) than in the summer (2:06 AM ± 0.03; t = 4.07, p < .0001). During summer, children increased their screen media use by 38 minutes (t = 2.32, p = .023) and decreased their caffeine intake from 7.43 to 7.0 (with scores ranging from 3 to 15; t = 2.83, p = .006). Greater sleep-inhibiting (ß = 0.40, p = .011) and fewer sleep-promoting (ß = -0.28, p = .049) behaviors during the school year were associated with having a higher BMI. There were no associations among sleep patterns, sleep hygiene and BMI during summer. CONCLUSIONS: More positive school year sleep hygiene behaviors were supportive of having a healthier weight status. Changes in these behaviors during the summer did not portend worse weight outcomes. Supporting families in the establishment of sleep-promoting behaviors, particularly during the school year may help address the child obesity epidemic.

How much did it cost to develop and implement an eHealth intervention for a minority children population that overlapped with the COVID-19 pandemic?

BACKGROUND: eHealth interventions using active video games (AVGs) offer an alternative method to help children exercise, especially during a pandemic where options are limited. There is limited data on costs associated with developing and implementing such interventions. OBJECTIVES: We quantified the costs of delivering an eHealth RCT intervention among minority children during COVID-19. METHODS: We categorized the total trial cost into five subcategories: intervention material development, advertising and recruitment, intervention delivery, personnel salaries, and COVID-19-related equipment costs. RESULTS: The total RCT cost was $1,927,807 (Direct: $1,227,903; Indirect: $699,904) with three visits required for each participant. The average cost per participant completing the RCT (79 participants/237 visits) was $24,403 (Direct: $15,543; Indirect: $8860). Due to no-shows and cancellations (198 visits) and dropouts before study completion (61 visits; 56 participants), 496 visits had to be scheduled to ensure complete data collection on 79 participants. If all 496 visits were from participants completing the three-visit protocol, that would correspond to 165 participants, bringing the average cost per participant down to $11,684 (Direct: $7442; Indirect: $4242). Of the subcategories, intervention material development accounted for the largest portion, followed by personnel salaries. While the direct COVID-19-specific cost constituted <1% of the entire budget, the indirect effects were much larger and significantly impacted the trial. CONCLUSION: RCTs typically involve significant resources, even more so during a pandemic. Future eHealth intervention investigators should budget and plan accordingly to prepare for unexpected costs such as recruitment challenges to increase flexibility while maximizing the intervention efficacy.

The Family Level Assessment of Screen Use-Mobile Approach: Development of an Approach to Measure Children's Mobile Device Use.

BACKGROUND: There is a strong association between increased mobile device use and worse dietary habits, worse sleep outcomes, and poor academic performance in children. Self-report or parent-proxy report of children's screen time has been the most common method of measuring screen time, which may be imprecise or biased. OBJECTIVE: The objective of this study was to assess the feasibility of measuring the screen time of children on mobile devices using the Family Level Assessment of Screen Use (FLASH)-mobile approach, an innovative method that leverages the existing features of the Android platform. METHODS: This pilot study consisted of 2 laboratory-based observational feasibility studies and 2 home-based feasibility studies in the United States. A total of 48 parent-child dyads consisting of a parent and child aged 6 to 11 years participated in the pilot study. The children had to have their own or shared Android device. The laboratory-based studies included a standardized series of tasks while using the mobile device or watching television, which were video recorded. Video recordings were coded by staff for a gold standard comparison. The home-based studies instructed the parent-child dyads to use their mobile device as they typically use it over 3 days. Parents received a copy of the use logs at the end of the study and completed an exit interview in which they were asked to review their logs and share their perceptions and suggestions for the improvement of the FLASH-mobile approach. RESULTS: The final version of the FLASH-mobile approach resulted in user identification compliance rates of >90% for smartphones and >80% for tablets. For laboratory-based studies, a mean agreement of 73.6% (SD 16.15%) was achieved compared with the gold standard (human coding of video recordings) in capturing the target child's mobile use. Qualitative feedback from parents and children revealed that parents found the FLASH-mobile approach useful for tracking how much time their child spends using the mobile device as well as tracking the apps they used. Some parents revealed concerns over privacy and provided suggestions for improving the FLASH-mobile approach. CONCLUSIONS: The FLASH-mobile approach offers an important new research approach to measure children's use of mobile devices more accurately across several days, even when the child shares the device with other family members. With additional enhancement and validation studies, this approach can significantly advance the measurement of mobile device use among young children.

Seasonality of Children's Height and Weight and Their Contribution to Accelerated Summer Weight Gain.

Background: While children have been shown to have increased BMI during the summer compared to the school year, it is not known if this may be due to seasonal variations in height or weight separately. Methods: Trained nurses measured heights (cm) and weights (kg) in a cohort of Kindergarteners (n = 7648) twice per year from the beginning of kindergarten through 5th grade. Variation in height and weight by season (school year vs. summer) was examined using separate mixed-effects models. Season, sex, and BMI trajectory group were tested as fixed effects. Random effects included repeated measurements of time, students nested within a school, intercept, and slope for growth over time. Similar models using BMIz as the outcome examined the interaction of height or weight with season. Results: The rate of height gain was greater during the school year (∼Sept to April) compared to summer (∼April to Sept) (ß = -0.05, SE = 0.013, p < 0.0001). The rate of weight gain did not differ seasonally. Height gain was more strongly associated with increased BMIz during summer compared to the school year (ß =.02, SE = 0.005, p <0 .0001), mainly among children who remained healthy weight throughout elementary school (ß = 0.014, SE = 0.003, p < 0.0001) and those who transitioned to a healthier weight status (ß = 0.026, SE = 0.008, p = 0.004). We found a similar seasonal effect for the association between weight with BMIz among children who maintained a healthy weight status (ß = 0.014, SE = 0.014, p < 0.0001). Conclusion: This study indicates seasonality in children's height gain, gaining height at a faster rate during the school year compared to the summer, while weight gain remained relatively more consistent throughout the year. Seasonality in height and weight gain had the greatest impact on BMIz among children with a healthy weight status. Future research with more frequent measurements is needed to better understand the seasonal regulation of children's growth and weight gain.

Parent-perceived neighbourhood environment, parenting practices and preschool-aged children physical activity and screen time: a cross-sectional study of two culturally and geographically diverse cities.

BACKGROUND: Preschool-aged children's physical activity (PA) and screen time (ST) are important health-related behaviours likely influenced by PA opportunities, parental perceptions of neighbourhood safety and parenting practices pertaining to PA and ST. How these factors interact to impact on young children's PA and ST, and whether their effects are generalisable across cultures and geographical location is not known. This study addressed these knowledge gaps by conducting pooled analyses of comparable data from two culturally and geographically diverse samples - Chinese parent-child dyads from an ultra-dense city (Hong Kong, China) and Latino parent-child dyads from a low-density city (Houston, USA). METHODS: The analytical sample consisted of 164 Hong Kong Chinese and 84 US Latino parent-child dyads with data on socio-demographic characteristics, parent-perceived neighbourhood destinations and facilities for children's PA, physical and social safety-related neighbourhood attributes, PA-related parenting practices and child's ST and accelerometer-assessed PA. Generalised linear models with robust standard errors accounting for neighbourhood-level clustering were used to estimate associations and interaction effects. RESULTS: Hong Kong Chinese children accumulated less PA than US Latino children, although the latter had more ST. Hong Kong Chinese parents reported more parenting practices promoting inactivity. Neighbourhood PA opportunities were positively related to children's PA only if parental perceptions of neighbourhood safety were favourable, and the associations of physical neighbourhood environment characteristics with children's PA and ST depended on PA-related parenting practices. Community cohesion was positively related to children's PA and negatively related to ST, while parental promotion of ST was positively associated with children's ST. Correlates of children's PA and ST did not differ by city. CONCLUSIONS: The substantial differences in activity patterns between Hong Kong Chinese and US Latino preschool-aged children observed in this study are likely due to a combination of cultural and built environmental factors. However, the fact that no between-city differences in correlates of PA and ST were detected indicates that both populations of children are equally affected by parent-perceived neighbourhood environmental characteristics and parenting practices. Overall, this study highlights the importance of considering how various individual-, home- and neighbourhood physical and social factors interact to influence young children's health-promoting activity levels.

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.

Evaluation of a Circadian Rhythm and Sleep-Focused Mobile Health Intervention for the Prevention of Accelerated Summer Weight Gain Among Elementary School-Age Children: Protocol for a Randomized Controlled Feasibility Study.

BACKGROUND: The i♥rhythm project is a mobile health adaptation of interpersonal and social rhythm therapy designed to promote healthy sleep and behavioral rhythms among 5-8-year olds during summer for the prevention of accelerated summer weight gain. OBJECTIVE: This pilot study will examine the feasibility, acceptability, and preliminary efficacy of the i♥rhythm intervention. This will ensure that the research protocol and procedures work as desired and are acceptable to families in preparation for the fully powered randomized controlled trial. The proposed study will examine the willingness of participants to participate in the intervention and determine whether modifications to the intervention, procedures, and measures are needed before conducting a fully powered study. We will assess our ability to (1) recruit, consent, and retain participants; (2) deliver the intervention; (3) implement the study and assessment procedures; (4) assess the reliability of the proposed measures; and (5) assess the acceptability of the intervention and assessment protocol. METHODS: This study will employ a single-blinded 2-group randomized control design (treatment and no-treatment control) with randomization occurring after baseline (Time 0) and 3 additional evaluation periods (postintervention [Time 1], and 9 months [Time 2] and 12 months after intervention [Time 3]). A sample of 40 parent-child dyads will be recruited. RESULTS: This study was approved by the institutional review board of Baylor College of Medicine (H-47369). Recruitment began in March 2021. As of March 2022, data collection and recruitment are ongoing. CONCLUSIONS: This study will address the role of sleep and circadian rhythms in the prevention of accelerated summer weight gain and assess the intervention's effects on the long-term prevention of child obesity. TRIAL REGISTRATION: ClinicalTrials.gov NCT04445740; https://clinicaltrials.gov/ct2/show/NCT04445740. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/37002.

An Objective System for Quantitative Assessment of Television Viewing Among Children (Family Level Assessment of Screen Use in the Home-Television): System Development Study.

BACKGROUND: Television viewing among children is associated with developmental and health outcomes, yet measurement techniques for television viewing are prone to errors, biases, or both. OBJECTIVE: This study aims to develop a system to objectively and passively measure children's television viewing time. METHODS: The Family Level Assessment of Screen Use in the Home-Television (FLASH-TV) system includes three sequential algorithms applied to video data collected in front of a television screen: face detection, face verification, and gaze estimation. A total of 21 families of diverse race and ethnicity were enrolled in 1 of 4 design studies to train the algorithms and provide proof of concept testing for the integrated FLASH-TV system. Video data were collected from each family in a laboratory mimicking a living room or in the child's home. Staff coded the video data for the target child as the gold standard. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value were calculated for each algorithm, as compared with the gold standard. Prevalence and biased adjusted κ scores and an intraclass correlation using a generalized linear mixed model compared FLASH-TV's estimation of television viewing duration to the gold standard. RESULTS: FLASH-TV demonstrated high sensitivity for detecting faces (95.5%-97.9%) and performed well on face verification when the child's gaze was on the television. Each of the metrics for estimating the child's gaze on the screen was moderate to good (range: 55.1% negative predictive value to 91.2% specificity). When combining the 3 sequential steps, FLASH-TV estimation of the child's screen viewing was overall good, with an intraclass correlation for an overall time watching television of 0.725 across conditions. CONCLUSIONS: FLASH-TV offers a critical step forward in improving the assessment of children's television viewing.

A Novel Approach to Dining Bowl Reconstruction for Image-Based Food Volume Estimation.

Knowing the amounts of energy and nutrients in an individual's diet is important for maintaining health and preventing chronic diseases. As electronic and AI technologies advance rapidly, dietary assessment can now be performed using food images obtained from a smartphone or a wearable device. One of the challenges in this approach is to computationally measure the volume of food in a bowl from an image. This problem has not been studied systematically despite the bowl being the most utilized food container in many parts of the world, especially in Asia and Africa. In this paper, we present a new method to measure the size and shape of a bowl by adhering a paper ruler centrally across the bottom and sides of the bowl and then taking an image. When observed from the image, the distortions in the width of the paper ruler and the spacings between ruler markers completely encode the size and shape of the bowl. A computational algorithm is developed to reconstruct the three-dimensional bowl interior using the observed distortions. Our experiments using nine bowls, colored liquids, and amorphous foods demonstrate high accuracy of our method for food volume estimation involving round bowls as containers. A total of 228 images of amorphous foods were also used in a comparative experiment between our algorithm and an independent human estimator. The results showed that our algorithm overperformed the human estimator who utilized different types of reference information and two estimation methods, including direct volume estimation and indirect estimation through the fullness of the bowl.

A Sensor-Controlled Digital Game for Heart Failure Self-Care Based on Behavioral Change Frameworks.

Self-care behaviors are critical to manage the adverse impact of heart failure disease. However, engaging in self-care behaviors such as physical activity or daily weight-monitoring can be difficult due to lack of knowledge or motivation. Digital games can serve as an alternative to traditional patient education to provide information and motivate engagement in critical self-care behaviors. In this paper, we describe a sensor-controlled digital game (SCDG) in which game play is driven by the player's real life self-care behaviors. We also present the design and development of the next iteration of the SCDG based on playtesting results and behavioral theoretical frameworks.

Vegetable parenting practices vary by feeding styles among middle class mothers of young children.

The optimal approach to feeding preschool children balances expectation setting (demandingness) with responsivity to the child (responsiveness), and ideal feeding practices use environmental structuring and covert, non-directive control strategies while maintaining responsiveness. However, research has not examined the extent to which demandingness and responsiveness in feeding style is concordant with structure, responsiveness and control (directive and non-directive) in feeding practices. We classified the feeding style of 122 parents of preschoolers as authoritative (high demandingness/high responsiveness), authoritarian (high demandingness/low responsiveness), indulgent (low demandingness/high responsiveness), or uninvolved (low demandingness/low responsiveness). Parents reported on their frequency of use of 31 vegetable parenting practices (VPPs), that were classified into the domains of structure, control and responsiveness, and subcategorized as effective (likely to obtain the desired change without increasing child obesity risk) or ineffective (unlikely or increases risk) by expert consensus. We hypothesized that parents with an authoritative feeding style would have the highest effective structure, responsiveness and control VPPs, and the authoritarian style would differ with less responsiveness VPPs. We also hypothesized that the indulgent feeding style would have low levels of structure and control VPPs and high ineffective responsiveness VPPs. As expected, we found that parents with an authoritative feeding style reported using more effective structure and responsiveness VPPs. Surprisingly, parents with an authoritarian feeding style did not have VPPs which differed from those with an authoritative feeding style, and parents with an indulgent feeding style had surprisingly high effective control VPPs. Further research into the similarities and differences between parents' overall approach to feeding and their use of feeding practices related to specific foods is warranted, which may help inform the design of more effective interventions aimed at improving child dietary quality.

Selection and use of vegetable parenting practices did not vary by parent feeding styles: Mixed methods investigation.

Parents influence their child's vegetable intake through their feeding style, i.e. the emotional tone established around feeding, and vegetable parenting practices (VPPs), i.e. the specific behaviors employed to influence their child's vegetable intake. A model of precision food parenting proposes that child healthy dietary intake could be optimized by the selection and implementation of effective food parenting practices. Parents use and learn from these complex interactions with their child, which are reflective of feeding style. Intervention research has targeted VPPs in general without a delineation of which practices were selected, which were used, or why they were selected. It is not clear how these users were influenced by feeding style, nor what the parent learned from the interaction. The current study used mixed methods wherein middle socioeconomic status parents of 3-5 year old children were categorized within feeding style groups (n = 122), asked to select two VPPs, implemented them for a week (n = 63), and qualitatively interviewed about their experience. Responsiveness VPPs were most commonly selected, primarily due to their perceived ease of implementation. Parents believed there would be long term positive outcomes, e.g. more vegetable intake from using the practices selected. Frequency of use depended in part on opportunity, e.g. food purchase parenting practices could only be employed during intermittent shopping events. Few differences were detected by parent feeding styles in the types of VPPs selected, frequency of use, or effectiveness. Food parenting interventions can encourage selection of specific VPPs to employ and do not appear to have to tailor the types of VPPs offered to parent feeding style. Research is needed with larger, socioeconomically diverse samples to assess optimal categorization into feeding styles and confirm the present results.

SmartFeeding4Kids, an online self-guided parenting intervention to promote positive feeding practices and healthy diet in young children: study protocol for a randomized controlled trial.

BACKGROUND: Caregivers' influence on young children's eating behaviors is widely recognized. Nutritional interventions that focus on the promotion of children's healthy diet should actively involve parents, focusing on their feeding behaviors and practices. METHODS: This work aims to describe the development and study protocol of the SmartFeeding4Kids (SF4K) program, an online self-guided 7-session intervention for parents of young (2-6 years old) children. The program is informed by social cognitive, self-regulation, and habit formation theoretical models and uses self-regulatory techniques as self-monitoring, goal setting, and feedback to promote behavior change. We propose to examine the intervention efficacy on children's intake of fruit, vegetables, and added sugars, and parental feeding practices with a two-arm randomized controlled with four times repeated measures design (baseline, immediately, 3 and 6 months after intervention). Parental perceived barriers about food and feeding, food parenting self-efficacy, and motivation to change will be analyzed as secondary outcomes. The study of the predictors of parents' dropout rates and the trajectories of parents' and children's outcomes are also objectives of this work. DISCUSSION: The SmartFeeding4Kids program relies on technological resources to deliver parents' self-regulation techniques that proved effective in promoting health behaviors. The study design can enhance the knowledge about the most effective methodologies to change parental feeding practices and children's food intake. As a self-guided online program, SmartFeeding4Kids might overcome parents' attrition more effectively, besides being easy to disseminate and cost-effective. TRIAL REGISTRATION: The study was registered in ClinicalTrials.gov ( NCT04591496 ) on October 19, 2020.