Video observations have been widely used for providing ground truth for wearable systems for monitoring food intake in controlled laboratory conditions; however, video observation requires participants be confined to a defined space. The purpose of this analysis was to test an alternative approach for establishing activity types and food intake bouts in a relatively unconstrained environment. The accuracy of a wearable system for assessing food intake was compared with that from video observation, and inter-rater reliability of annotation was also evaluated. Forty participants were enrolled. Multiple participants were simultaneously monitored in a 4-bedroom apartment using six cameras for three days each. Participants could leave the apartment overnight and for short periods of time during the day, during which time monitoring did not take place. A wearable system (Automatic Ingestion Monitor, AIM) was used to detect and monitor participants’ food intake at a resolution of 30 s using a neural network classifier. Two different food intake detection models were tested, one trained on the data from an earlier study and the other on current study data using leave-one-out cross validation. Three trained human raters annotated the videos for major activities of daily living including eating, drinking, resting, walking, and talking. They further annotated individual bites and chewing bouts for each food intake bout. Results for inter-rater reliability showed that, for activity annotation, the raters achieved an average (±standard deviation (STD)) kappa value of 0.74 (±0.02) and for food intake annotation the average kappa (Light’s kappa) of 0.82 (±0.04). Validity results showed that AIM food intake detection matched human video-annotated food intake with a kappa of 0.77 (±0.10) and 0.78 (±0.12) for activity annotation and for food intake bout annotation, respectively. Results of one-way ANOVA suggest that there are no statistically significant differences among the average eating duration estimated from raters’ annotations and AIM predictions (p-value = 0.19). These results suggest that the AIM provides accuracy comparable to video observation and may be used to reliably detect food intake in multi-day observational studies.

Malnutrition is a major concern in low- and middle-income countries (LMIC), but the full extent of nutritional deficiencies remains unknown largely due to lack of accurate assessment methods. This study seeks to develop and validate an objective, passive method of estimating food and nutrient intake in households in Ghana and Uganda. Household members (including under-5s and adolescents) are assigned a wearable camera device to capture images of their food intake during waking hours. Using custom software, images captured are then used to estimate an individual's food and nutrient (i.e., protein, fat, carbohydrate, energy, and micronutrients) intake. Passive food image capture and assessment provides an objective measure of food and nutrient intake in real time, minimizing some of the limitations associated with self-reported dietary intake methods. Its use in LMIC could potentially increase the understanding of a population's nutritional status, and the contribution of household food intake to the malnutrition burden. This project is registered at clinicaltrials.gov (NCT03723460).

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.

We have developed a population-level method for dietary assessment using low-cost wearable cameras. Our approach, EgoDiet, employs an egocentric vision-based pipeline to learn portion sizes, addressing the shortcomings of traditional self-reported dietary methods. To evaluate the functionality of this method, field studies were conducted in London (Study A) and Ghana (Study B) among populations of Ghanaian and Kenyan origin. In Study A, EgoDiet’s estimations were contrasted with dietitians’ assessments, revealing a performance with a Mean Absolute Percentage Error (MAPE) of 31.9% for portion size estimation, compared to 40.1% for estimates made by dietitians. We further evaluated our approach in Study B, comparing its performance to the traditional 24-Hour Dietary Recall (24HR). Our approach demonstrated a MAPE of 28.0%, showing a reduction in error when contrasted with the 24HR, which exhibited a MAPE of 32.5%. This improvement highlights the potential of using passive camera technology to serve as an alternative to the traditional dietary assessment methods.

Background. The association of psychological eating behavior constructs with overweight and obesity during early adult life and middle age has been documented in several studies. However, the association of eating behavior with unexplained weight change in old age is relatively unexplored. Methods. Body weight, eating behavior (dietary restraint, disinhibition, and hunger as assessed by the Eating Inventory), reported dietary intake, and physical activity level were assessed at baseline in 36 nonobese postmenopausal women aged 61.3 ± 3.1 years (mean ± standard deviation). Measurements were repeated 4.4 ± 0.9 years later, and changes in body weight were examined in relation to baseline and follow-up eating behavior scores, reported dietary intake, and physical activity level. Results. Participants had no major changes in health or lifestyle characteristics over the study interval. Weight change ranged from −7.5 to +5.8 kg (mean −0.3 ± 3.5 kg), and there were no significant changes in reported dietary intake. Mean hunger score (calculated as the mean of baseline and follow-up hunger score) predicted weight change per year over the study period (bivariate r = 0.386, p =.020), even in statistical models adjusted for mean dietary intake variables (partial r = 0.658, p =.003). Restraint, disinhibition, and physical activity level did not predict weight change. Conclusions. Reported hunger assessed by the Eating Inventory was associated with unintentional weight change in healthy postmenopausal women. The Eating Inventory questionnaire may provide a clinically useful tool for identifying older individuals at risk of undesirable weight change, and particularly unintentional weight loss, a factor strongly associated with increased morbidity and premature death in this population.

Repeated exposure to sugary, fatty, and salty foods often enhances their appeal. However, it is unknown if exposure influences learned palatability of foods typically promoted as part of a healthy diet. We tested whether the palatability of pulse containing foods provided during a weight loss intervention which were particularly high in fiber and low in energy density would increase with repeated exposure. At weeks 0, 3, and 6, participants (n = 42; body mass index (BMI) 31.2 ± 4.3 kg/m²) were given a test battery of 28 foods, approximately half which had been provided as part of the intervention, while the remaining half were not foods provided as part of the intervention. In addition, about half of each of the foods (provided as part or not provided as part of the intervention) contained pulses. Participants rated the taste, appearance, odor, and texture pleasantness of each food, and an overall flavor pleasantness score was calculated as the mean of these four scores. Linear mixed model analyses showed an exposure type by week interaction effect for taste, texture and overall flavor pleasantness indicating statistically significant increases in ratings of provided foods in taste and texture from weeks 0 to 3 and 0 to 6, and overall flavor from weeks 0 to 6. Repeated exposure to these foods, whether they contained pulses or not, resulted in a ~4% increase in pleasantness ratings. The long-term clinical relevance of this small increase requires further study.