Rule-based systems to automatically count bites from meal videos.

Eating behavior is a key factor for nutritional intake and plays a significant role in the development of eating disorders and obesity. The standard methods to detect eating behavior events (i.e., bites and chews) from video recordings rely on manual annotation, which lacks objective assessment and standardization. Yet, video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we present a rule-based system to count bites automatically from video recordings with 468 3D facial key points. We tested the performance against manual annotation in 164 videos from 15 participants. The system can count bites with 79% accuracy when annotation is available, and 71.4% when annotation is unavailable. The system showed consistent performance across varying food textures. Eating behavior researchers can use this automated and objective system to replace manual bite count annotation, provided the system's error is acceptable for the purpose of their study. Utilizing our approach enables real-time bite counting, thereby promoting interventions for healthy eating behaviors. Future studies in this area should explore rule-based systems and machine learning methods with 3D facial key points to extend the automated analysis to other eating events while providing accuracy, interpretability, generalizability, and low computational requirements.

Correction: Gastric coagulation and postprandial amino acid absorption of milk is affected by mineral composition: a randomized crossover trial.

Correction for 'Gastric coagulation and postprandial amino acid absorption of milk is affected by mineral composition: a randomized crossover trial' by Elise J. M. van Eijnatten et al., Food Funct., 2024, 15, 3098-3107, https://doi.org/10.1039/D3FO04063A.

User Requirements in Developing a Novel Dietary Assessment Tool for Children: Mixed Methods Study.

BACKGROUND: The prevalence of childhood obesity and comorbidities is rising alarmingly, and diet is an important modifiable determinant. Numerous dietary interventions in children have been developed to reduce childhood obesity and overweight rates, but their long-term effects are unsatisfactory. Stakeholders call for more personalized approaches, which require detailed dietary intake data. In the case of primary school children, caregivers are key to providing such dietary information. However, as school-aged children are not under the full supervision of one specific caregiver anymore, data are likely to be biased. Recent technological advancements provide opportunities for the role of children themselves, which would serve the overall quality of the obtained dietary data. OBJECTIVE: This study aims to conduct a child-centered exploratory sequential mixed methods study to identify user requirements for a dietary assessment tool for children aged 5 to 6 years. METHODS: Formative, nonsystematic narrative literature research was undertaken to delineate initial user requirements and inform prototype ideation in an expert panel workshop (n=11). This yielded 3 prototype dietary assessment tools: FoodBear (tangible piggy bank), myBear (smartphone or tablet app), and FoodCam (physical camera). All 3 prototypes were tested for usability by means of a usability task (video analyses) and user experience (This or That method) among 14 Dutch children aged 5 to 6 years (n=8, 57% boys and n=6, 43% girls). RESULTS: Most children were able to complete FoodBear's (11/14, 79%), myBear's (10/14, 71%), and FoodCam's (9/14, 64%) usability tasks, but all children required assistance (14/14, 100%) and most of the children encountered usability problems (13/14, 93%). Usability issues were related to food group categorization and recognition, frustrations owing to unsatisfactory functioning of (parts) of the prototypes, recall of food products, and the distinction between eating moments. No short-term differences in product preference between the 3 prototypes were observed, but autonomy, challenge, gaming elements, being tablet based, appearance, social elements, and time frame were identified as determinants of liking the product. CONCLUSIONS: Our results suggest that children can play a complementary role in dietary data collection to enhance the data collected by their parents. Incorporation of a training program, auditory or visual prompts, reminders and feedback, a user-friendly and intuitive interaction design, child-friendly food groups or icons, and room for children's autonomy were identified as requirements for the future development of a novel and usable dietary assessment tool for children aged 5 to 6 years. Our findings can serve as valuable guidance for ongoing innovations in the field of children's dietary assessment and the provision of personalized dietary support.

Gastric coagulation and postprandial amino acid absorption of milk is affected by mineral composition: a randomized crossover trial.

Background: In vitro studies suggest that casein coagulation of milk is influenced by its mineral composition, and may therefore affect the dynamics of protein digestion, gastric emptying and appearance of amino acids (AA) in the blood, but this remains to be confirmed in vivo. Objective: This study aimed to compare gastrointestinal digestion between two milks with the same total calcium content but different casein mineralization (CM). Design: Fifteen males (age 30.9 ± 13.8 years, BMI 22.5 ± 2.2 kg m-2) participated in this randomized cross-over study with two treatments. Participants underwent gastric magnetic resonance imaging (MRI) scans at the baseline and every 10 min up to 90 min after consumption of 600 ml milk with low or high CM. Blood samples were taken at the baseline and up to 5 hours postprandially. Primary outcomes were postprandial plasma AA concentrations and gastric emptying rate. Secondary outcomes were postprandial glucose and insulin levels, gastric coagulation as estimated by image texture metrics, and appetite ratings. Results: Gastric content volume over time was similar for both treatments. However, gastric content image analysis suggested that the liquid fraction emptied quicker in the high CM milk, while the coagulum emptied slower. Relative to high CM, low CM showed earlier appearance of AAs that are more dominant in casein, such as proline (MD 4.18 µmol L-1, 95% CI [2.38-5.98], p < 0.001), while there was no difference in appearance of AAs that are more dominant in whey protein, such as leucine. The image texture metrics homogeneity and busyness differed significantly between treatments (MD 0.007, 95% CI [0.001, 0.012], p = 0.022; MD 0.005, 95% CI [0.001, 0.010], p = 0.012) likely because of a reduced coagulation in the low CM milk. Conclusions: Mineral composition of milk can influence postprandial serum AA kinetics, likely due to differences in coagulation dynamics. The clinical trial registry number is NL8959 (https://clinicaltrials.gov).

Eat-Radar: Continuous Fine-Grained Intake Gesture Detection Using FMCW Radar and 3D Temporal Convolutional Network With Attention.

Unhealthy dietary habits are considered as the primary cause of various chronic diseases, including obesity and diabetes. The automatic food intake monitoring system has the potential to improve the quality of life (QoL) of people with diet-related diseases through dietary assessment. In this work, we propose a novel contactless radar-based approach for food intake monitoring. Specifically, a Frequency Modulated Continuous Wave (FMCW) radar sensor is employed to recognize fine-grained eating and drinking gestures. The fine-grained eating/drinking gesture contains a series of movements from raising the hand to the mouth until putting away the hand from the mouth. A 3D temporal convolutional network with self-attention (3D-TCN-Att) is developed to detect and segment eating and drinking gestures in meal sessions by processing the Range-Doppler Cube (RD Cube). Unlike previous radar-based research, this work collects data in continuous meal sessions (more realistic scenarios). We create a public dataset comprising 70 meal sessions (4,132 eating gestures and 893 drinking gestures) from 70 participants with a total duration of 1,155 minutes. Four eating styles (fork & knife, chopsticks, spoon, hand) are included in this dataset. To validate the performance of the proposed approach, seven-fold cross-validation method is applied. The 3D-TCN-Att model achieves a segmental F1-score of 0.896 and 0.868 for eating and drinking gestures, respectively. The results of the proposed approach indicate the feasibility of using radar for fine-grained eating and drinking gesture detection and segmentation in meal sessions.

Milk coagulation and gastric emptying in women experiencing gastrointestinal symptoms after ingestion of cow's milk.

BACKGROUND: Gastrointestinal symptoms after drinking milk are often attributed to lactose intolerance or cow's milk allergy. However, some individuals without either condition still report gastrointestinal symptoms after drinking milk. This may be caused by gastric emptying (GE) rate or gastric protein coagulation. This study aimed to compare GE rate and protein coagulation after milk consumption between individuals reporting gastrointestinal symptoms and those without symptoms using a novel gastric MRI approach. METHODS: Thirty women were included in this case-control study, of whom 15 reported gastrointestinal symptoms after drinking milk and 15 were controls. Participants underwent gastric MRI before and up to 90 min after consumption of 250 mL cow's milk. Gastric content volume and image texture of the stomach contents were used to determine GE and changes in the degree of coagulation. KEY RESULTS: GE half-time did not differ between the groups (gastrointestinal symptom group 66 ± 18 min; control group 61 ± 14 min, p = 0.845). The gastrointestinal symptom group reported symptoms from 30 min onwards and rated pain highest at 90 min. The control group reported no symptoms. Image texture analyses showed a significantly higher percentage of coagulum and lower percentage of liquid in the group in the GI symptom group (MD 11%, 95% CI [3.9, 17], p = 0.003). In vitro data suggests that pH and proteolytic enzyme activity influence the coagulum structure. CONCLUSIONS AND INFERENCES: Gastric milk coagulation and emptied fraction of stomach content may differ between individuals experiencing symptoms after milk consumption, possibly due to differences in pH and proteolytic enzyme activity.

Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions.

Background: More people than ever seek nutrition information from online sources. The chatbot ChatGPT has seen staggering popularity since its inception and may become a resource for information in nutrition. However, the adequacy of ChatGPT to answer questions in the field of nutrition has not been investigated. Thus, the aim of this research was to investigate the competency of ChatGPT in answering common nutrition questions. Methods: Dieticians were asked to provide their most commonly asked nutrition questions and their own answers to them. We then asked the same questions to ChatGPT and sent both sets of answers to other dieticians (N = 18) or nutritionists and experts in the domain of each question (N = 9) to be graded based on scientific correctness, actionability, and comprehensibility. The grades were also averaged to give an overall score, and group means of the answers to each question were compared using permutation tests. Results: The overall grades for ChatGPT were higher than those from the dieticians for the overall scores in five of the eight questions we received. ChatGPT also had higher grades on five occasions for scientific correctness, four for actionability, and five for comprehensibility. In contrast, none of the answers from the dieticians had a higher average score than ChatGPT for any of the questions, both overall and for each of the grading components. Conclusions: Our results suggest that ChatGPT can be used to answer nutrition questions that are frequently asked to dieticians and provide encouraging support for the role of chatbots in offering nutrition support.

Technology to Automatically Record Eating Behavior in Real Life: A Systematic Review.

To monitor adherence to diets and to design and evaluate nutritional interventions, it is essential to obtain objective knowledge about eating behavior. In most research, measures of eating behavior are based on self-reporting, such as 24-h recalls, food records (food diaries) and food frequency questionnaires. Self-reporting is prone to inaccuracies due to inaccurate and subjective recall and other biases. Recording behavior using nonobtrusive technology in daily life would overcome this. Here, we provide an up-to-date systematic overview encompassing all (close-to) publicly or commercially available technologies to automatically record eating behavior in real-life settings. A total of 1328 studies were screened and, after applying defined inclusion and exclusion criteria, 122 studies were included for in-depth evaluation. Technologies in these studies were categorized by what type of eating behavior they measure and which type of sensor technology they use. In general, we found that relatively simple sensors are often used. Depending on the purpose, these are mainly motion sensors, microphones, weight sensors and photo cameras. While several of these technologies are commercially available, there is still a lack of publicly available algorithms that are needed to process and interpret the resulting data. We argue that future work should focus on developing robust algorithms and validating these technologies in real-life settings. Combining technologies (e.g., prompting individuals for self-reports at sensed, opportune moments) is a promising route toward ecologically valid studies of eating behavior.

Speed limits: the effects of industrial food processing and food texture on daily energy intake and eating behaviour in healthy adults.

PURPOSE: Frequent consumption of industrially processed foods has been associated with obesity. However, it is unknown what drives this association. Food textures of industrially processed foods that stimulate energy overconsumption may be an important driver of this association. Therefore, this study aimed to determine the independent and combined effects of food texture and level of industrial food processing (based on the NOVA classification) on daily energy intake and eating behaviour. METHODS: Eighteen healthy adults (F/M: 11/7, 23 ± 3 y, 22.1 ± 2.0 kg/m2) participated in a 2 × 2 randomized crossover dietary intervention with four conditions (total of 288 meals): hard unprocessed, hard (ultra-)processed, soft unprocessed and soft (ultra-)processed. Daily diets were offered ad libitum and were equal in energy density (1 kcal/g). Food Intake (g) was measured by pre- and post-consumption weighing of the plates. Eating behaviour parameters were derived from video annotations. RESULTS: Daily energy intake and food intake were, respectively, 33% (571 ± 135 kcal) and 14% (247 ± 146 g) lower in the hard compared to the soft conditions (main texture p < 0.001). Energy intake was lower in both hard conditions compared to the (ultra)processed soft condition (Tukey p < 0.04). Eating rate (g/min) was on average 85% slower (P < 0.001) in the hard compared to the soft conditions (p < 0.001). Level of processing did not affect food intake. CONCLUSION: Consumption of hard-textured foods reduces daily energy intake of (ultra-) processed foods. This preliminary investigation shows that there is great variability in food properties that affect energy and food intake beyond industrial food processing. However, findings should be interpreted with precaution considering the limited sample size of this trial. Future classification systems for public health messaging should include energy intake rate to help reduce overconsumption. CLINICAL TRIAL REGISTRY: NCT04280146, https://www. CLINICALTRIALS: gov , February 21st 2020.

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.

Dutch veterinary graduates leaving practice: A mixed-methods analysis of frequency and underlying reasons.

BACKGROUND: This study aimed to evaluate the frequency of veterinarians graduated between 2009 and 2019 in the Netherlands leaving practice, their reasons for leaving and the relative importance of these reasons. METHODS: Study 1 (focus group sessions, n = 14) of this project was aimed at defining the reasons Dutch veterinarians have for leaving veterinary practice within 10 years of graduation. In study 2, the frequency of veterinarians leaving veterinary practice and the relative importance of the reasons for leaving identified in study 1 were investigated through a cross-sectional digital survey. A career in veterinary practice was defined as working in first- or second-line veterinary practice. Leaving practice was defined as ending employment in veterinary practice. RESULTS: The results of study 1 yielded 20 reasons given by veterinarians to leave veterinary practice within 10 years of graduation. One of the reasons obtained by this study was not mentioned in literature before: leaving veterinary practice as a pre-planned career path. Study 2 demonstrated that the mean percentage of respondents from graduation years 2009 to 2014 who left practice within 5 years of graduation was 16.8%. The most important reasons respondents gave for this career move were poor work-life balance, excessive workload, insufficient remuneration and perceived lack of employer support. CONCLUSION: A substantial number of veterinarians leave veterinary practice within 5 years of graduation. The most important reasons for this decision are excessive job demands or insufficient job resources. Furthermore, these reasons are a result of negative experiences regarding organisation of work, management and remuneration.

Low- and Medium-Socioeconomic-Status Group Members' Perceived Challenges and Solutions for Healthy Nutrition: Qualitative Focus Group Study.

BACKGROUND: Although digital tools for healthy nutrition have shown great potential, their actual impact remains variable as digital solutions often do not fit users' needs and barriers. This is especially poignant for priority communities in society. Involving these groups in citizen science may have great benefits even beyond the increase in knowledge of the lives and experiences of these groups. However, this requires specialized skills. Participants from priority groups could benefit from an approach that offers sensitization and discussion to help them voice their needs regarding healthy nutrition and technology to support healthy eating. OBJECTIVE: This study aimed to gather insights into people's thoughts on everyday eating practices, self-regulation in healthy eating, and skill acquisition and on applying technological innovations to these domains. METHODS: Participants answered 3 daily questionnaires to garner their current practices regarding habits, self-regulation, skills, and technology use surrounding healthy eating and make it easier for them to collect their thoughts and experiences (sensitization). Within a week of filling out the 3 questionnaires, participants took part in a web-based focus group discussion session. All sessions were transcribed and analyzed using a thematic qualitative approach. RESULTS: A total of 42 people took part in 7 focus group interviews of 6 people each. The analysis showed that participants would like to receive support from technology for a broad range of aspects of nutrition, such as measuring the effect their personal nutrition has on their individual health, providing them with reliable product information, giving them practical guidance for healthy eating and snacking, and reducing the burden of registering food intake. Technology should be easy to use, reduce burdens, and be tailored to personal situations. Privacy and cost were major concerns for the participants. CONCLUSIONS: This study shows that people from low- and medium-socioeconomic-status groups have a need for specific support in tailoring their knowledge of healthy nutrition to their own situation and see technology as a means to achieve this.

Capturing Eating Behavior from Video Analysis: A Systematic Review.

Current methods to detect eating behavior events (i.e., bites, chews, and swallows) lack objective measurements, standard procedures, and automation. The video recordings of eating episodes provide a non-invasive and scalable source for automation. Here, we reviewed the current methods to automatically detect eating behavior events from video recordings. According to PRISMA guidelines, publications from 2010-2021 in PubMed, Scopus, ScienceDirect, and Google Scholar were screened through title and abstract, leading to the identification of 277 publications. We screened the full text of 52 publications and included 13 for analysis. We classified the methods in five distinct categories based on their similarities and analyzed their accuracy. Facial landmarks can count bites, chews, and food liking automatically (accuracy: 90%, 60%, 25%). Deep neural networks can detect bites and gesture intake (accuracy: 91%, 86%). The active appearance model can detect chewing (accuracy: 93%), and optical flow can count chews (accuracy: 88%). Video fluoroscopy can track swallows but is currently not suitable beyond clinical settings. The optimal method for automated counts of bites and chews is facial landmarks, although further improvements are required. Future methods should accurately predict bites, chews, and swallows using inexpensive hardware and limited computational capacity. Automatic eating behavior analysis will allow the study of eating behavior and real-time interventions to promote healthy eating behaviors.

Drinking Gesture Detection Using Wrist-Worn IMU Sensors with Multi-Stage Temporal Convolutional Network in Free-Living Environments.

Maintaining adequate hydration is important for health. Inadequate liquid intake can cause dehydration problems. Despite the increasing development of liquid intake monitoring, there are still open challenges in drinking detection under free-living conditions. This paper proposes an automatic liquid intake monitoring system comprised of wrist-worn Inertial Measurement Units (IMU s) to recognize drinking gesture in free-living environments. We build an end-to-end approach for drinking gesture detection by employing a novel multi-stage temporal convolutional network (MS-TCN). Two datasets are collected in this research, one contains 8.9 hours data from 13 participants in semi-controlled environments, the other one contains 45.2 hours data from 7 participants in free-living environments. The Leave-One-Subject-Out (LOSO) evaluation shows that this method achieves a segmental F1-score of 0.943 and 0.900 in the semi-controlled and free-living datasets, respectively. The results also indicate that our approach outperforms the convolutional neural network and long-short-term-memory network combined model (CNN-LSTM) on our datasets. The dataset used in this paper is available at https://github.com/Pituohai/drinking-gesture-dataset/. Clinical Relevance- This automatic liquid intake monitoring system can detect drinking gesture in daily life. It has the potential to be used to record the frequency of drinking water for at-risk elderly or patients in the hospital.

Machine Learning in Nutrition Research.

Data currently generated in the field of nutrition are becoming increasingly complex and high-dimensional, bringing with them new methods of data analysis. The characteristics of machine learning (ML) make it suitable for such analysis and thus lend itself as an alternative tool to deal with data of this nature. ML has already been applied in important problem areas in nutrition, such as obesity, metabolic health, and malnutrition. Despite this, experts in nutrition are often without an understanding of ML, which limits its application and therefore potential to solve currently open questions. The current article aims to bridge this knowledge gap by supplying nutrition researchers with a resource to facilitate the use of ML in their research. ML is first explained and distinguished from existing solutions, with key examples of applications in the nutrition literature provided. Two case studies of domains in which ML is particularly applicable, precision nutrition and metabolomics, are then presented. Finally, a framework is outlined to guide interested researchers in integrating ML into their work. By acting as a resource to which researchers can refer, we hope to support the integration of ML in the field of nutrition to facilitate modern research.

Eating for 2: A Systematic Review of Dutch App Stores for Apps Promoting a Healthy Diet during Pregnancy.

A healthy diet during pregnancy has been associated with beneficial child and maternal health outcomes but is challenging to achieve. Recent technological advances offer new opportunities to support pregnant women in their food choices-for instance, via apps. This is already reflected by a wide availability of pregnancy-related apps, but health care professionals feel unsure about their potential. Therefore, the Dutch Google Play Store and Apple App Store were reviewed to identify existing apps on diet and pregnancy. App quality was assessed using the 1) Mobile App Rating Scale (MARS; i.e., assessing functionality, aesthetics, engagement, information quality), 2) Dutch dietary guidelines for pregnant women, and 3) App Behavior Change Scale (ABACUS). Fifty-seven unique apps were identified with an average star rating of 4.2 ±  0.6 and MARS quality score of 3.2 ±  0.3, indicating a moderate quality. Most apps scored best in terms of functionality and aesthetics (4.0 ±  0.4 and 3.3 ±  0.6), but lowest in terms of engagement (2.5 ±  0.6). Regarding nutrition information provision, most apps were incomplete or deviated from the Dutch guidelines. Folic acid supplementation (91%), hygiene (81%), caffeine (79%), and alcohol (77%) were the most commonly addressed nutrition aspects, whereas licorice (11%), iodine (19%), and soy (18%) were only addressed in a few apps. Moreover, a median of 2 out of 21 ABACUS behavior change items were identified per app, which were predominantly related to the category "knowledge and information." Thus, despite the abundance of apps supporting a healthy diet during pregnancy in the Dutch app stores, there is an urgent need for apps with complete and scientifically sound dietary information that is supported by effective behavior change techniques.

Gastric Emptying and Intragastric Behavior of Breast Milk and Infant Formula in Lactating Mothers.

BACKGROUND: When sufficient breast milk is not available, infant formula is often used as an alternative. As for digestion, gastric behavior of infant formula and breast milk have not been studied in detail. OBJECTIVE: This study aimed to compare gastric emptying and intragastric behavior between breast milk and infant formula in vivo using MRI. METHODS: In this randomized crossover study, 16 lactating mothers (age: 31.7 ± 2.9 y; time since giving birth: 9.3 ± 2 mo), underwent gastric MRI scans before and after consumption of 200 mL of infant formula or their own breast milk. MRI scans were performed after an overnight fast (baseline) and every 10 min up until 60 min following ingestion. Primary outcomes were gastric emptying measures and the secondary outcome was gastric layer volume over time. Differences between infant formula and breast milk in total gastric volume and layering volume were tested using linear mixed models. RESULTS: Gastric emptying half-time was 5.1 min faster for breast milk than for infant formula (95% CI: -19.0 to 29.2) (n = 14). Within a subgroup (n = 12) with similar initial gastric volume (<20 mL difference), gastric emptying half-time was 20 min faster for breast milk (95% CI: 1.23-43.1). Top layer volume (n = 16) was 6.4 mL greater for infant formula than for breast milk (95% CI: 1.9-10.8). This effect is driven by t = 10 and t = 20 min postingestion. CONCLUSIONS: When taking initial gastric volume into account, breast milk emptied faster than infant formula in women, which is in line with previous findings in infants. Infant formula showed a significantly larger top layer volume in the first 20 min after ingestion. MRI in adults may find application in studies assessing gastric behavior of infant formula.

Short and Long-Term Innovations on Dietary Behavior Assessment and Coaching: Present Efforts and Vision of the Pride and Prejudice Consortium.

Overweight, obesity and cardiometabolic diseases are major global health concerns. Lifestyle factors, including diet, have been acknowledged to play a key role in the solution of these health risks. However, as shown by numerous studies, and in clinical practice, it is extremely challenging to quantify dietary behaviors as well as influencing them via dietary interventions. As shown by the limited success of 'one-size-fits-all' nutritional campaigns catered to an entire population or subpopulation, the need for more personalized coaching approaches is evident. New technology-based innovations provide opportunities to further improve the accuracy of dietary assessment and develop approaches to coach individuals towards healthier dietary behaviors. Pride & Prejudice (P&P) is a unique multi-disciplinary consortium consisting of researchers in life, nutrition, ICT, design, behavioral and social sciences from all four Dutch Universities of Technology. P&P focuses on the development and integration of innovative technological techniques such as artificial intelligence (AI), machine learning, conversational agents, behavior change theory and personalized coaching to improve current practices and establish lasting dietary behavior change.

Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method.

The vast majority of dietary and eating behavior assessment methods are based on self-reports. They are burdensome and also prone to measurement errors. Recent technological innovations allow for the development of more accurate and precise dietary and eating behavior assessment tools that require less effort for both the user and the researcher. Therefore, a new sensor-based device to assess food intake and eating behavior was developed. The device is a regular dining tray equipped with a video camera and three separate built-in weighing stations. The weighing stations measure the weight of the bowl, plate, and drinking cup continuously over the course of a meal. The video camera positioned to the face records eating behavior characteristics (chews, bites), which are analyzed using artificial intelligence (AI)-based automatic facial expression software. The tray weight and the video data are transported at real-time to a personal computer (PC) using a wireless receiver. The outcomes of interest, such as the amount eaten, eating rate and bite size, can be calculated by subtracting the data of these measures at the timepoints of interest. The information obtained by the current version of the tray can be used for research purposes, an upgraded version of the device would also facilitate the provision of more personalized advice on dietary intake and eating behavior. Contrary to the conventional dietary assessment methods, this dietary assessment device measures food intake directly within a meal and is not dependent on memory or the portion size estimation. Ultimately, this device is therefore suited for daily main meal food intake and eating behavior measures. In the future, this technology based dietary assessment method can be linked to health applications or smart watches to obtain a complete overview of exercise, energy intake, and eating behavior.