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).

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.

Rural and urban communities in Ghana.

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

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.

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.

Survival rates for paediatric cancers have increased dramatically since the 1970s, but childhood cancer survivors (CCS) are at increased risk for several chronic diseases throughout life. Nutrition interventions promoting healthy family meals may support wellness for survivors, but little research has explored CCS family food preparation habits. The goal of the present study was to describe and compare food preparation practices of CCS and non-CCS families.

Observational.

Typical evening meal preparation events were observed and recorded in participant homes. Recordings and notes were analysed using the Healthy Cooking Index (HCI), a measure of nutrition-optimizing food preparation practices relevant to survivor wellness. Demographics, BMI and nutrient composition of prepared meals were also collected.

Forty parents with a CCS or non-CCS child aged 5–17 years were recruited.

There were no major differences between the CCS and non-CCS families with regard to summative HCI score or specific food preparation behaviours. Meals prepared by CCS and non-CCS families had similar nutrient compositions.

The study revealed areas for practical nutrition intervention in CCS and non-CCS families. Future studies should consider adopting and tailoring nutrition intervention methods that have been successful in non-CCS communities.

To identify most commonly consumed foods by adolescents contributing to percentage of total energy, added sugars, SFA, Na and total gram intake per day.

Data from the National Health and Nutrition Examination Survey (NHANES) 2011–2014.

NHANES is a cross-sectional study nationally representative of the US population.

One 24 h dietary recall was used to assess dietary intake of 3156 adolescents aged 10–19 years. What We Eat in America food category classification system was used for all foods consumed. Food sources of energy, added sugars, SFA, Na and total gram amount consumed were sample-weighted and ranked based on percentage contribution to intake of total amount.

Three-highest ranked food subgroup sources of total energy consumed were: sugar-sweetened beverages (SSB; 7·8 %); sweet bakery products (6·9 %); mixed dishes – pizza (6·6 %). Highest ranked food sources of total gram amount consumed were: plain water (33·1 %); SSB (15·8 %); milk (7·2 %). Three highest ranked food sources of total Na were: mixed dishes – pizza (8·7 %); mixed dishes – Mexican (6·7 %); cured meats/poultry (6·6 %). Three highest ranked food sources of SFA were: mixed dishes – pizza (9·1 %); sweet bakery products (8·3 %); mixed dishes – Mexican (7·9 %). Three highest ranked food sources of added sugars were: SSB (42·1 %); sweet bakery products (12·1 %); coffee and tea (7·6 %).

Identifying current food sources of percentage energy, nutrients to limit and total gram amount consumed among US adolescents is critical for designing strategies to help them meet nutrient recommendations within energy needs.

To develop an artificial intelligence (AI)-based algorithm which can automatically detect food items from images acquired by an egocentric wearable camera for dietary assessment.

To study human diet and lifestyle, large sets of egocentric images were acquired using a wearable device, called eButton, from free-living individuals. Three thousand nine hundred images containing real-world activities, which formed eButton data set 1, were manually selected from thirty subjects. eButton data set 2 contained 29 515 images acquired from a research participant in a week-long unrestricted recording. They included both food- and non-food-related real-life activities, such as dining at both home and restaurants, cooking, shopping, gardening, housekeeping chores, taking classes, gym exercise, etc. All images in these data sets were classified as food/non-food images based on their tags generated by a convolutional neural network.

A cross data-set test was conducted on eButton data set 1. The overall accuracy of food detection was 91·5 and 86·4 %, respectively, when one-half of data set 1 was used for training and the other half for testing. For eButton data set 2, 74·0 % sensitivity and 87·0 % specificity were obtained if both ‘food’ and ‘drink’ were considered as food images. Alternatively, if only ‘food’ items were considered, the sensitivity and specificity reached 85·0 and 85·8 %, respectively.

The AI technology can automatically detect foods from low-quality, wearable camera-acquired real-world egocentric images with reasonable accuracy, reducing both the burden of data processing and privacy concerns.

The eButton takes frontal images at 4s intervals throughout the day. A three-dimensional manually administered wire mesh procedure has been developed to quantify portion sizes from the two-dimensional images. The present paper reports a test of the inter-rater reliability and validity of use of the wire mesh procedure.

Seventeen foods of diverse shapes and sizes served on plates, bowls and cups were selected to rigorously test the portion assessment procedure. A dietitian not involved in inter-rater reliability assessment used standard cups to independently measure the quantities of foods to generate the ‘true’ value for a total of seventy-five ‘served’ and seventy-five smaller ‘left’ images with diverse portion sizes.

The images appeared on the computer to which the digital wire meshes were applied.

Two dietitians and three engineers independently estimated portion size of the larger (‘served’) and smaller (‘left’) images for the same foods.

The engineers had higher reliability and validity than the dietitians. The dietitians had lower reliabilities and validities for the smaller more irregular images, but the engineers did not, suggesting training could overcome this limitation. The lower reliabilities and validities for foods served in bowls, compared with plates, suggest difficulties with the curved nature of the bowls.

The wire mesh procedure is an important step forward in quantifying portion size, which has been subject to substantial self-report error. Improved training procedures are needed to overcome the identified problems.

Habit has been defined as the automatic performance of a usual behaviour. The present paper reports the relationships of variables from a Model of Goal Directed Behavior to four scales in regard to parents’ habits when feeding their children: habit of (i) actively involving child in selection of vegetables; (ii) maintaining a positive vegetable environment; (iii) positive communications about vegetables; and (iv) controlling vegetable practices. We tested the hypothesis that the primary predictor of each habit variable would be the measure of the corresponding parenting practice.

Internet survey data from a mostly female sample. Primary analyses employed regression modelling with backward deletion, controlling for demographics and parenting practices behaviour.

Houston, Texas, USA.

Parents of 307 pre-school (3–5-year-old) children.

Three of the four models accounted for about 50 % of the variance in the parenting practices habit scales. Each habit scale was primarily predicted by the corresponding parenting practices scale (suggesting validity). The habit of active child involvement in vegetable selection was also most strongly predicted by two barriers and rudimentary self-efficacy; the habit of maintaining a positive vegetable environment by one barrier; the habit of maintaining positive communications about vegetables by an emotional scale; and the habit of controlling vegetable practices by a perceived behavioural control scale.

The predictiveness of the psychosocial variables beyond parenting practices behaviour was modest. Discontinuing the habit of ineffective controlling parenting practices may require increasing the parent’s perceived control of parenting practices, perhaps through simulated parent–child interactions.

To model effective vegetable parenting practices using the Model of Goal Directed Vegetable Parenting Practices construct scales.

An Internet survey was conducted with parents of pre-school children to assess their agreement with effective vegetable parenting practices and Model of Goal Directed Vegetable Parenting Practices items. Block regression modelling was conducted using the composite score of effective vegetable parenting practices scales as the outcome variable and the Model of Goal Directed Vegetable Parenting Practices constructs as predictors in separate and sequential blocks: demographics, intention, desire (intrinsic motivation), perceived barriers, autonomy, relatedness, self-efficacy, habit, anticipated emotions, perceived behavioural control, attitudes and lastly norms. Backward deletion was employed at the end for any variable not significant at P<0·05.

Houston, TX, USA.

Three hundred and seven parents (mostly mothers) of pre-school children.

Significant predictors in the final model in order of relationship strength included habit of active child involvement in vegetable selection, habit of positive vegetable communications, respondent not liking vegetables, habit of keeping a positive vegetable environment and perceived behavioural control of having a positive influence on child’s vegetable consumption. The final model’s adjusted R2 was 0·486.

This was the first study to test scales from a behavioural model to predict effective vegetable parenting practices. Further research needs to assess these Model of Goal Directed Vegetable Parenting Practices scales for their (i) predictiveness of child consumption of vegetables in longitudinal samples and (ii) utility in guiding design of vegetable parenting practices interventions.