Image-assisted dietary assessment: a systematic review of the evidence

The association between diet quality and chrononutritional patterns in young adults

PURPOSE

Young adults eat erratically and later in the day which may impact weight and cardiometabolic health. This cross-sectional study examined relationships between chrononutritional patterns and diet quality in two young adult populations: a university and community sample.

METHODS

Three days of dietary data were collected including food images captured using wearable cameras. Chrononutritional variables were extracted: time of first and last eating occasions, caloric midpoint (time at which 50% of daily energy was consumed), number of eating occasions per day, eating window, day-to-day variability of the above metrics, and evening eating (≥20:00h). The Healthy Eating Index for Australian Adults scored diet quality. Statistical analyses controlled for gender, body mass index, and socio-economic status.

RESULTS

No significant associations between chrononutritional patterns and diet quality were found for all participants (n = 95). However, differences in diet quality were found between university (n = 54) and community (n = 41) samples with average diet quality scores of 59.1 (SD 9.7) and 47.3 (SD 14.4), respectively. Of those who extended eating ≥20:00 h, university participants had better diet quality (62.9±SE 2.5 vs. 44.3±SE 2.3, p < 0.001) and discretionary scores (7.9±SE 0.9 vs. 1.6±SE 0.6, p < 0.001) than community participants. University participants consumed predominately healthful dinners and fruit ≥20:00h whereas community participants consumed predominately discretionary foods.

CONCLUSION

For the general young adult population, meal timing needs to be considered. Food choices made by this cohort may be poorer during evenings when the desire for energy-dense nutrient-poor foods is stronger. However, meal timing may be less relevant for young adults who already engage in healthy dietary patterns.

We got nuts! use deep neural networks to classify images of common edible nuts

BACKGROUND

Nuts are nutrient-dense foods that contribute to healthier eating. Food image datasets enable artificial intelligence (AI) powered diet-tracking apps to help people monitor daily eating patterns.

AIM

This study aimed to create an image dataset of commonly consumed nut types and use it to build an AI computer vision model to automate nut type classification tasks.

METHODS

iPhone 11 was used to take photos of 11 nut types-almond, brazil nut, cashew, chestnut, hazelnut, macadamia, peanut, pecan, pine nut, pistachio, and walnut. The dataset contains 2200 images, 200 per nut type. The dataset was randomly split into the training (60% or 1320 images), validation (20% or 440 images), and test sets (20% or 440 images). A neural network model was constructed and trained using transfer learning and other computer vision techniques-data augmentation, mixup, normalization, label smoothing, and learning rate optimization.

RESULTS

The trained neural network model correctly predicted 338 out of 440 images (40 per nut type) in the validation set, achieving 99.55% accuracy. Moreover, the model classified the 440 images in the test set with 100% accuracy.

CONCLUSION

This study built a nut image dataset and used it to train a neural network model to classify images by nut type. The model achieved near-perfect accuracy on the validation and test sets, demonstrating the feasibility of automating nut type classification using smartphone photos. Being made open-source, the dataset and model can assist the development of diet-tracking apps that facilitate users' adoption and adherence to a healthy diet.

Measures of nutrition status and health for weight-inclusive patient care: A narrative review

In healthcare, weight is often equated to and used as a marker for health. In examining nutrition and health status, there are many more effective markers independent of weight. In this article, we review practical and emerging clinical applications of technologies and tools used to collect non-weight-related data in nutrition assessment, monitoring, and evaluation in the outpatient setting. The aim is to provide clinicians with new ideas about various types of data to evaluate and track in nutrition care.

Patterns of energy availability and carbohydrate intake differentiate between adaptable and problematic low energy availability in female athletes

Background

Problematic low energy availability (EA) is the underlying culprit of relative energy deficiency in sport (REDs), and its consequences have been suggested to be exacerbated when accompanied by low carbohydrate (CHO) intakes.

Objectives

This study compared dietary intake, nutrition status and occurrence of REDs symptoms in groups of female athletes, displaying different patterns of EA and CHO intake.

Methods

Female athletes (n = 41, median age 20.4 years) from various sports weighed and recorded their food intake and training for 7 consecutive days via a photo-assisted mobile application. Participants were divided into four groups based on patterns of EA and CHO intakes: sufficient to optimal EA and sufficient to optimal CHO intake (SEA + SCHO), SEA and low CHO intake (SEA + LCHO), low energy availability and SCHO (LEA + SCHO), and LEA and LCHO (LEA + LCHO). SEA patterns were characterised by EA ≥30 and LEA by EA <30 kcal/kg fat free mass, and SCHO patterns characterised by CHO intake ≥3.0 and LCHO <3.0 g/kg body weight for most of the registered days. Body composition was measured with dual energy x-ray absorptiometry, resting metabolic rate with indirect calorimetry and serum blood samples were collected for evaluation of nutrition status. Behavioural risk factors and self-reported symptoms of REDs were assessed with the Low Energy Availability in Females Questionnaire, Eating Disorder Examination Questionnaire Short (EDE-QS), Exercise Addiction Inventory, and Muscle Dysmorphic Disorder Inventory.

Results

In total, 36.6% were categorised as SEA + SCHO, of which 5/16 were ball sport, 7/10 endurance, 1/7 aesthetic, 2/5 weight-class, and 0/3 weight-class athletes. Of LEA + LCHO athletes (19.5% of all), 50% came from ball sports. Aesthetic and endurance athletes reported the greatest training demands, with weekly training hours higher for aesthetic compared to ball sports (13.1 ± 5.7 vs. 6.7 ± 3.4 h, p = 0.012). Two LEA + LCHO and one SEA + LCHO athlete exceeded the EDE-QS cutoff. LEA + LCHO evaluated their sleep and energy levels as worse, and both LEA groups rated their recovery as worse compared to SEA + SCHO.

Conclusion

Repeated exposures to LEA and LCHO are associated with a cluster of negative implications in female athletes. In terms of nutrition strategies, sufficient EA and CHO intakes appear to be pivotal in preventing REDs.

Accuracy of energy and nutrient intake estimation versus observed intake using 4 technology-assisted dietary assessment methods: a randomized crossover feeding study

BACKGROUND

Technology-assisted 24-h dietary recalls (24HRs) have been widely adopted in population nutrition surveillance. Evaluations of 24HRs inform improvements, but direct comparisons of 24HR methods for accuracy in reference to a measure of true intake are rarely undertaken in a single study population.

OBJECTIVES

To compare the accuracy of energy and nutrient intake estimation of 4 technology-assisted dietary assessment methods relative to true intake across breakfast, lunch, and dinner.

METHODS

In a controlled feeding study with a crossover design, 152 participants [55% women; mean age 32 y, standard deviation (SD) 11; mean body mass index 26 kg/m2, SD 5] were randomized to 1 of 3 separate feeding days to consume breakfast, lunch, and dinner, with unobtrusive weighing of foods and beverages consumed. Participants undertook a 24HR the following day [Automated Self-Administered Dietary Assessment Tool-Australia (ASA24); Intake24-Australia; mobile Food Record-Trained Analyst (mFR-TA); or Image-Assisted Interviewer-Administered 24-hour recall (IA-24HR)]. When assigned to IA-24HR, participants referred to images captured of their meals using the mobile Food Record (mFR) app. True and estimated energy and nutrient intakes were compared, and differences among methods were assessed using linear mixed models.

RESULTS

The mean difference between true and estimated energy intake as a percentage of true intake was 5.4% (95% CI: 0.6, 10.2%) using ASA24, 1.7% (95% CI: -2.9, 6.3%) using Intake24, 1.3% (95% CI: -1.1, 3.8%) using mFR-TA, and 15.0% (95% CI: 11.6, 18.3%) using IA-24HR. The variances of estimated and true energy intakes were statistically significantly different for all methods (P < 0.01) except Intake24 (P = 0.1). Differential accuracy in nutrient estimation was present among the methods.

CONCLUSIONS

Under controlled conditions, Intake24, ASA24, and mFR-TA estimated average energy and nutrient intakes with reasonable validity, but intake distributions were estimated accurately by Intake24 only (energy and protein). This study may inform considerations regarding instruments of choice in future population surveillance. This trial was registered at Australian New Zealand Clinical Trials Registry as ACTRN12621000209897.

Build Deep Neural Network Models to Detect Common Edible Nuts from Photos and Estimate Nutrient Portfolio

Nuts are nutrient-dense foods and can be incorporated into a healthy diet. Artificial intelligence-powered diet-tracking apps may promote nut consumption by providing real-time, accurate nutrition information but depend on data and model availability. Our team developed a dataset comprising 1380 photographs, each in RGB color format and with a resolution of 4032 × 3024 pixels. These images feature 11 types of nuts that are commonly consumed. Each photo includes three nut types; each type consists of 2-4 nuts, so 6-9 nuts are in each image. Rectangular bounding boxes were drawn using a visual geometry group (VGG) image annotator to facilitate the identification of each nut, delineating their locations within the images. This approach renders the dataset an excellent resource for training models capable of multi-label classification and object detection, as it was meticulously divided into training, validation, and test subsets. Utilizing transfer learning in Python with the IceVision framework, deep neural network models were adeptly trained to recognize and pinpoint the nuts depicted in the photographs. The ultimate model exhibited a mean average precision of 0.7596 in identifying various nut types within the validation subset and demonstrated a 97.9% accuracy rate in determining the number and kinds of nuts present in the test subset. By integrating specific nutritional data for each type of nut, the model can precisely (with error margins ranging from 0.8 to 2.6%) calculate the combined nutritional content-encompassing total energy, proteins, carbohydrates, fats (total and saturated), fiber, vitamin E, and essential minerals like magnesium, phosphorus, copper, manganese, and selenium-of the nuts shown in a photograph. Both the dataset and the model have been made publicly available to foster data exchange and the spread of knowledge. Our research underscores the potential of leveraging photographs for automated nut calorie and nutritional content estimation, paving the way for the creation of dietary tracking applications that offer real-time, precise nutritional insights to encourage nut consumption.

Personalized Machine Learning-Based Prediction of Wellbeing and Empathy in Healthcare Professionals

Healthcare professionals are known to suffer from workplace stress and burnout, which can negatively affect their empathy for patients and quality of care. While existing research has identified factors associated with wellbeing and empathy in healthcare professionals, these efforts are typically focused on the group level, ignoring potentially important individual differences and implications for individualized intervention approaches. In the current study, we implemented N-of-1 personalized machine learning (PML) to predict wellbeing and empathy in healthcare professionals at the individual level, leveraging ecological momentary assessments (EMAs) and smartwatch wearable data. A total of 47 mood and lifestyle feature variables (relating to sleep, diet, exercise, and social connections) were collected daily for up to three months followed by applying eight supervised machine learning (ML) models in a PML pipeline to predict wellbeing and empathy separately. Predictive insight into the model architecture was obtained using Shapley statistics for each of the best-fit personalized models, ranking the importance of each feature for each participant. The best-fit model and top features varied across participants, with anxious mood (13/19) and depressed mood (10/19) being the top predictors in most models. Social connection was a top predictor for wellbeing in 9/12 participants but not for empathy models (1/7). Additionally, empathy and wellbeing were the top predictors of each other in 64% of cases. These findings highlight shared and individual features of wellbeing and empathy in healthcare professionals and suggest that a one-size-fits-all approach to addressing modifiable factors to improve wellbeing and empathy will likely be suboptimal. In the future, such personalized models may serve as actionable insights for healthcare professionals that lead to increased wellness and quality of patient care.

Tailored Prompting to Improve Adherence to Image-Based Dietary Assessment: Mixed Methods Study

Background

Accurately assessing an individual's diet is vital in the management of personal nutrition and in the study of the effect of diet on health. Despite its importance, the tools available for dietary assessment remain either too imprecise, expensive, or burdensome for clinical or research use. Image-based methods offer a potential new tool to improve the reliability and accessibility of dietary assessment. Though promising, image-based methods are sensitive to adherence, as images cannot be captured from meals that have already been consumed. Adherence to image-based methods may be improved with appropriately timed prompting via text message.

Objective

This study aimed to quantitatively examine the effect of prompt timing on adherence to an image-based dietary record and qualitatively explore the participant experience of dietary assessment in order to inform the design of a novel image-based dietary assessment tool.

Methods

This study used a randomized crossover design to examine the intraindividual effect of 3 prompt settings on the number of images captured in an image-based dietary record. The prompt settings were control, where no prompts were sent; standard, where prompts were sent at 7:15 AM, 11:15 AM, and 5:15 PM for every participant; and tailored, where prompt timing was tailored to habitual meal times for each participant. Participants completed a text-based dietary record at baseline to determine the timing of tailored prompts. Participants were randomized to 1 of 6 study sequences, each with a unique order of the 3 prompt settings, with each 3-day image-based dietary record separated by a washout period of at least 7 days. The qualitative component comprised semistructured interviews and questionnaires exploring the experience of dietary assessment.

Results

A total of 37 people were recruited, and 30 participants (11 male, 19 female; mean age 30, SD 10.8 years), completed all image-based dietary records. The image rate increased by 0.83 images per day in the standard setting compared to control (P=.23) and increased by 1.78 images per day in the tailored setting compared to control (P≤.001). We found that 13/21 (62%) of participants preferred to use the image-based dietary record versus the text-based dietary record but reported method-specific challenges with each method, particularly the inability to record via an image after a meal had been consumed.

Conclusions

Tailored prompting improves adherence to image-based dietary assessment. Future image-based dietary assessment tools should use tailored prompting and offer both image-based and written input options to improve record completeness.

The Validity and Feasibility of Utilizing the Photo-Assisted Dietary Intake Assessment among College Students and Elderly Individuals in China

Dietary assessments hold significant importance within the field of public health. However, the current methods employed for dietary assessments face certain limitations and challenges that necessitate improvement. The aim of our study was to develop a reliable and practical dietary assessment tool known as photo-assisted dietary intake assessment (PAD). In order to evaluate its validity, we conducted an analysis on a sample of 71 college students' dinners at a buffet in a canteen. We compared estimates of food weights obtained through the 24-h recall (24 HR) or PAD method with those obtained through the weighing method; we also evaluated the feasibility of PAD for recording dinner intakes among a sample of college students (n = 76) and elderly individuals (n = 121). In addition, we successfully identified the dietary factors that have a significant impact on the bias observed in weight estimation. The findings of the study indicated that the PAD method exhibited a higher level of consistency with the weighing method compared to the 24 HR method. The discrepancy in D% values between cereals (14.28% vs. 40.59%, P < 0.05), vegetables (17.67% vs. 44.44%, P < 0.05), and meats (14.29% vs. 33.33%, P < 0.05) was clearly apparent. Moreover, a significant proportion of the food mass value acquired through the PAD method fell within the limits of agreement (LOAs), in closer proximity to the central horizontal line. Furthermore, vegetables, cereals, eggs, and meats, for which the primary importance lies in accuracy, exhibited a considerably higher bias with the 24 HR method compared to the PAD method (P < 0.05), implying that the PAD method has the potential to mitigate the quality bias associated with these food items in the 24 HR method. Additionally, the PAD method was well received and easily implemented by the college students and elderly individuals. In conclusion, the PAD method demonstrates a considerable level of accuracy and feasibility as a dietary assessment method that can be effectively employed across diverse populations.

Using Voice Assistant Systems to Improve Dietary Recall among Older Adults: Perspectives of Registered Dietitians

Dietary assessments are important clinical tools used by Registered Dietitians (RDs). Current methods pose barriers to accurately assess the nutritional intake of older adults due to age-related increases in risk for cognitive decline and more complex health histories. Our qualitative study explored whether implementing Voice assistant systems (VAS) could improve current dietary recall from the perspective of 20 RDs. RDs believed the implementing VAS in dietary assessments of older adults could potentially improve patient accuracy in reporting food intake, recalling portion sizes, and increasing patient-provider efficiency during clinic visits. RDs reported that low technology literacy in older adults could be a barrier to implementation. Our study provides a better understanding of how VAS can better meet the needs of both older adults and RDs in managing and assessing dietary intake.

AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review

OBJECTIVE

Human error estimating food intake is a major source of bias in nutrition research. Artificial intelligence (AI) methods may reduce bias, but the overall accuracy of AI estimates is unknown. This study was a systematic review of peer-reviewed journal articles comparing fully automated AI-based (e.g. deep learning) methods of dietary assessment from digital images to human assessors and ground truth (e.g. doubly labelled water).

MATERIALS AND METHODS

Literature was searched through May 2023 in four electronic databases plus reference mining. Eligible articles reported AI estimated volume, energy, or nutrients. Independent investigators screened articles and extracted data. Potential sources of bias were documented in absence of an applicable risk of bias assessment tool.

RESULTS

Database and hand searches identified 14,059 unique publications; fifty-two papers (studies) published from 2010 to 2023 were retained. For food detection and classification, 79% of papers used a convolutional neural network. Common ground truth sources were calculation using nutrient tables (51%) and weighed food (27%). Included papers varied widely in food image databases and results reported, so meta-analytic synthesis could not be conducted. Relative errors were extracted or calculated from 69% of papers. Average overall relative errors (AI vs. ground truth) ranged from 0.10% to 38.3% for calories and 0.09% to 33% for volume, suggesting similar performance. Ranges of relative error were lower when images had single/simple foods.

CONCLUSIONS

Relative errors for volume and calorie estimations suggest that AI methods align with - and have the potential to exceed - accuracy of human estimations. However, variability in food image databases and results reported prevented meta-analytic synthesis. The field can advance by testing AI architectures on a limited number of large-scale food image and nutrition databases that the field determines to be adequate for training and testing and by reporting accuracy of at least absolute and relative error for volume or calorie estimations.

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

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

Assessing daily energy intake in adult women: validity of a food-recognition mobile application compared to doubly labelled water

Accurate dietary assessment is crucial for nutrition and health research. Traditional methods, such as food records, food frequency questionnaires, and 24-hour dietary recalls (24HR), have limitations, such as the need for trained interviewers, time-consuming procedures, and inaccuracies in estimations. Novel technologies, such as image-based dietary assessment apps, have been developed to overcome these limitations. SNAQ is a novel image-based food-recognition app which, based on computer vision, assesses food type and volume, and provides nutritional information about dietary intake. This cross-sectional observational study aimed to investigate the validity of SNAQ as a dietary assessment tool for measuring energy and macronutrient intake in adult women with normal body weight (n = 30), compared to doubly labeled water (DLW), a reference method for total daily energy expenditure (TDEE). Energy intake was also estimated using a one-day 24HR for direct comparison. Bland-Altman plots, paired difference tests, and Pearson's correlation coefficient were used to assess agreement and relationships between the methods. SNAQ showed a slightly higher agreement (bias = -329.6 kcal/day) with DLW for total daily energy intake (TDEI) compared to 24HR (bias = -543.0 kcal/day). While both SNAQ and 24HR tended to underestimate TDEI, only 24HR significantly differed from DLW in this regard (p < 0.001). There was no significant relationship between estimated TDEI and TDEE using SNAQ (R2 = 27%, p = 0.50) or 24HR (R2 = 34%, p = 0.20) and there were no significant differences in energy and macronutrient intake estimates between SNAQ and 24HR (Δ = 213.4 kcal/day). In conclusion, these results indicate that SNAQ provides a closer representation of energy intake in adult women with normal body weight than 24HR when compared to DLW, but no relationship was found between the energy estimates of DLW and of the two dietary assessment tools. Further research is needed to determine the clinical relevance and support the implementation of SNAQ in research and clinical settings. Clinical trial registration: This study is registered on ClinicalTrials.gov with the unique identifier NCT04600596 (https://clinicaltrials.gov/ct2/show/NCT04600596).

Integration of USDA Food Classification System and Food Composition Database for Image-Based Dietary Assessment among Individuals Using Insulin

New imaging technologies to identify food can reduce the reporting burden of participants but heavily rely on the quality of the food image databases to which they are linked to accurately identify food images. The objective of this study was to develop methods to create a food image database based on the most commonly consumed U.S. foods and those contributing the most to energy. The objective included using a systematic classification structure for foods based on the standardized United States Department of Agriculture (USDA) What We Eat in America (WWEIA) food classification system that can ultimately be used to link food images to a nutrition composition database, the USDA Food and Nutrient Database for Dietary Studies (FNDDS). The food image database was built using images mined from the web that were fitted with bounding boxes, identified, annotated, and then organized according to classifications aligning with USDA WWEIA. The images were classified by food category and subcategory and then assigned a corresponding USDA food code within the USDA's FNDDS in order to systematically organize the food images and facilitate a linkage to nutrient composition. The resulting food image database can be used in food identification and dietary assessment.

Relative Validity and Reliability of the Remind App as an Image-Based Method to Assess Dietary Intake and Meal Timing in Young Adults

Image-based dietary records have been validated as tools to evaluate dietary intake. However, to determine meal timing, previous studies have relied primarily on image-based smartphone applications without validation. Noteworthy, the validation process is necessary to determine how accurately a test method measures meal timing compared with a reference method over the same time period. Thus, we aimed to assess the relative validity and reliability of the Remind^® app as an image-based method to assess dietary intake and meal timing. For this purpose, 71 young adults (aged 20-33 years, 81.7% women) were recruited for a 3-day cross-sectional study, where they completed a 3-day image-based record using the Remind app (test method) and a 3-day handwritten food record (reference method). The relative validity of the test method versus the reference method was assessed using multiple tests including Bland-Altman, % difference, paired t-test/Wilcoxon signed-rank test, Pearson/Spearman correlation coefficients, and cross-classification. We also evaluated the reliability of the test method using an intra-class correlation (ICC) coefficient. The results showed that, compared to the reference method, the relative validity of the test method was good for assessing energy and macronutrient intake, as well as meal timing. Meanwhile, the relative validity of the test method to assess micronutrient intake was poor (p < 0.05) for some micronutrients (iron, phosphorus, potassium, zinc, vitamins B1, B2, B3, B6, C, and E, and folates) and some food groups (cereals and grains, legumes, tubers, oils, and fats). Regarding the reliability of an image-based method to assess dietary intake and meal timing, results ranged from moderate to excellent (ICC 95% confidence interval [95% CI]: 0.50-1.00) for all nutrients, food groups (except oils and fats, which had low to moderate reliability), and meal timings. Thus, the results obtained in this study provide evidence of the relative validity and reliability of image-based methods to assess dietary intake (energy, macronutrients, and most food groups) and meal timing. These results open up a new framework for chrononutrition, as these methods improve the quality of the data collected and also reduce the burden on users to accurately estimate portion size and the timing of meals.

Reliability and Validity of Digital Images to Assess Child Dietary Intake in a Quick-Service Restaurant Setting

BACKGROUND

Development of methods to accurately measure dietary intake in free-living situations-restaurants or otherwise-is critically needed to understand overall dietary patterns.

OBJECTIVE

This study aimed to develop and test reliability and validity of digital images (DI) for measuring children's dietary intake in quick-service restaurants (QSRs), validating against weighed plate waste (PW) and bomb calorimetry (BC).

DESIGN

In 2016, cross-sectional data were collected at two time points within a randomized controlled trial assessing children's leftovers in QSRs from parents of 4- to 12-year-old children.

PARTICIPANTS/SETTING

Parents (n = 640; mean age = 35.9 y; 70.8% female) consented and agreed to provide their child's PW for digital imaging, across 11 QSRs in Massachusetts in areas with low socioeconomic status and ethnically diverse populations.

OUTCOME MEASURES

Outcome measures were interrater reliability for DIs, correspondence between methods for energy consumed and left over, and correspondence between methods across varying quantities of PW.

ANALYSES PERFORMED

Intraclass correlations, percent agreement, Spearman correlations, Wilcoxon signed rank tests, and Bland-Altman plots were used.

RESULTS

Interrater reliability ratings for DIs had substantial intraclass correlations (ICC = 0.94) but not acceptable exact percent agreement (80.2%); DI and PW energy consumed were significantly correlated (r = 0.96, P < 0.001); DI slightly underestimated energy consumed compared with PW (Mdiff = -1.61 kcals, P < 0.001). Bland-Altman plots showed high DI-PW correspondence across various energy amounts and revealed few outliers. Energy left over by BC was highly correlated with DI (r = 0.87, P < 0.001) and PW (r = 0.90, P < 0.001); and mean differences were not significantly different from DI (Mdiff = 9.77 kcal, P = 0.06) or PW (Mdiff = -2.84 kcal, P = 0.20).

CONCLUSIONS

Correspondence was high between PW and DI assessments of energy consumed, and high with BC energy left over. Results demonstrate reliability and practical validity of digital images for assessing child meal consumption in QSR settings.

Mobile Computer Vision-Based Applications for Food Recognition and Volume and Calorific Estimation: A Systematic Review

The growing awareness of the influence of "what we eat" on lifestyle and health has led to an increase in the use of embedded food analysis and recognition systems. These solutions aim to effectively monitor daily food consumption, and therefore provide dietary recommendations to enable and support lifestyle changes. Mobile applications, due to their high accessibility, are ideal for real-life food recognition, volume estimation and calorific estimation. In this study, we conducted a systematic review based on articles that proposed mobile computer vision-based solutions for food recognition, volume estimation and calorific estimation. In addition, we assessed the extent to which these applications provide explanations to aid the users to understand the related classification and/or predictions. Our results show that 90.9% of applications do not distinguish between food and non-food. Similarly, only one study that proposed a mobile computer vision-based application for dietary intake attempted to provide explanations of features that contribute towards classification. Mobile computer vision-based applications are attracting a lot of interest in healthcare. They have the potential to assist in the management of chronic illnesses such as diabetes, ensuring that patients eat healthily and reducing complications associated with unhealthy food. However, to improve trust, mobile computer vision-based applications in healthcare should provide explanations of how they derive their classifications or volume and calorific estimations.

Relative Validation of an Artificial Intelligence–Enhanced, Image-Assisted Mobile App for Dietary Assessment in Adults: Randomized Crossover Study

Background

Thorough dietary assessment is essential to obtain accurate food and nutrient intake data yet challenging because of the limitations of current methods. Image-based methods may decrease energy underreporting and increase the validity of self-reported dietary intake. Keenoa is an image-assisted food diary that integrates artificial intelligence food recognition. We hypothesized that Keenoa is as valid for dietary assessment as the automated self-administered 24-hour recall (ASA24)–Canada and better appreciated by users.

Objective

We aimed to evaluate the relative validity of Keenoa against a 24-hour validated web-based food recall platform (ASA24) in both healthy individuals and those living with diabetes. Secondary objectives were to compare the proportion of under- and overreporters between tools and to assess the user’s appreciation of the tools.

Methods

We used a randomized crossover design, and participants completed 4 days of Keenoa food tracking and 4 days of ASA24 food recalls. The System Usability Scale was used to assess perceived ease of use. Differences in reported intakes were analyzed using 2-tailed paired t tests or Wilcoxon signed-rank test and deattenuated correlations by Spearman coefficient. Agreement and bias were determined using the Bland-Altman test. Weighted Cohen κ was used for cross-classification analysis. Energy underreporting was defined as a ratio of reported energy intake to estimated resting energy expenditure <0.9.

Results

A total of 136 participants were included (mean 46.1, SD 14.6 years; 49/136, 36% men; 31/136, 22.8% with diabetes). The average reported energy intakes (kcal/d) were 2171 (SD 553) in men with Keenoa and 2118 (SD 566) in men with ASA24 (P=.38) and, in women, 1804 (SD 404) with Keenoa and 1784 (SD 389) with ASA24 (P=.61). The overall mean difference (kcal/d) was −32 (95% CI −97 to 33), with limits of agreement of −789 to 725, indicating acceptable agreement between tools without bias. Mean reported macronutrient, calcium, potassium, and folate intakes did not significantly differ between tools. Reported fiber and iron intakes were higher, and sodium intake lower, with Keenoa than ASA24. Intakes in all macronutrients (r=0.48-0.73) and micronutrients analyzed (r=0.40-0.74) were correlated (all P<.05) between tools. Weighted Cohen κ scores ranged from 0.30 to 0.52 (all P<.001). The underreporting rate was 8.8% (12/136) with both tools. Mean System Usability Scale scores were higher for Keenoa than ASA24 (77/100, 77% vs 53/100, 53%; P<.001); 74.8% (101/135) of participants preferred Keenoa.

Conclusions

The Keenoa app showed moderate to strong relative validity against ASA24 for energy, macronutrient, and most micronutrient intakes analyzed in healthy adults and those with diabetes. Keenoa is a new, alternative tool that may facilitate the work of dietitians and nutrition researchers. The perceived ease of use may improve food-tracking adherence over longer periods.

Improved Wearable Devices for Dietary Assessment Using a New Camera System

An unhealthy diet is strongly linked to obesity and numerous chronic diseases. Currently, over two-thirds of American adults are overweight or obese. Although dietary assessment helps people improve nutrition and lifestyle, traditional methods for dietary assessment depend on self-report, which is inaccurate and often biased. In recent years, as electronics, information, and artificial intelligence (AI) technologies advanced rapidly, image-based objective dietary assessment using wearable electronic devices has become a powerful approach. However, research in this field has been focused on the developments of advanced algorithms to process image data. Few reports exist on the study of device hardware for the particular purpose of dietary assessment. In this work, we demonstrate that, with the current hardware design, there is a considerable risk of missing important dietary data owing to the common use of rectangular image screen and fixed camera orientation. We then present two designs of a new camera system to reduce data loss by generating circular images using rectangular image sensor chips. We also present a mechanical design that allows the camera orientation to be adjusted, adapting to differences among device wearers, such as gender, body height, and so on. Finally, we discuss the pros and cons of rectangular versus circular images with respect to information preservation and data processing using AI algorithms.

Development and validation of a smartphone image-based app for dietary intake assessment among Palestinian undergraduates

Accurate dietary assessment is required in a variety of research fields and clinical settings. Image-based dietary assessment using smartphones applications offer the opportunity to reduce both researcher and participant burden compared to traditional dietary assessment methods. The current study, conducted in Palestine, aimed to design an image-based dietary assessment application, to assess the relative validity of the application as a dietary assessment tool for energy and macronutrient intake using the 3-Day Food Record (3-DFR) as a reference method, and to test its usability among a sample of Palestinian university students. The development of a smartphone application (Ghithaona) designed to assess energy and macronutrient intake is reported. The application validity was tested among a sample of Palestinian undergraduates from An-Najah National University. Participants recorded their dietary intake using the Ghithaona application over 2 consecutive days and 1 weekend day. Intake from the Ghithaona application were compared to intake collected from 3-DFR, taken on 2 consecutive weekdays and 1 weekend day, in the second week following the Ghithaona application. At the end of the study, participants completed an exit survey to test assess application usability and to identify barriers to its use. Mean differences in energy, and macronutrients intake were evaluated between the methods using paired t-tests or Wilcoxon signed-rank tests. Agreement between methods was ascertained using Pearson correlations and Bland–Altman plots. The Ghithaona application took 6 months to develop. The validation test was completed by 70 participants with a mean age of 21.0 ± 2.1 years. No significant differences were found between the two methods for mean intakes of energy or macronutrients (p > 0.05). Significant correlations between the two methods were observed for energy, and all macronutrients (r = 0.261–0.58, p ≤ 0.05). Bland–Altman plots confirmed wide limits of agreement between the methods with no systematic bias. According to the exit survey, it was found that majority of participants strongly agreed and agreed that the application saves time (94.2%), helps the participant to pay attention to their dietary habits (87.2%), and is easy to use (78.6%). The Ghithaona application showed relative validity for assessment of nutrient intake of Palestinian undergraduates.

Indigenous Foods to Address Malnutrition: An Inquiry into the Diets and Nutritional Status of Women in the Indigenous Community of Munda Tribes of Jharkhand, India

Background

Indigenous people globally experience poor nutrition outcomes, with women facing the greater burden. Munda, a predominant tribe in Jharkhand, India, live in a biodiverse food environment but yet have high levels of malnutrition.

Objectives

To assess diets and the nutritional status of Munda tribal women and explore associations with their Indigenous food consumption, dietary diversity, and socioeconomic and demographic profiles.

Methods

A cross-sectional study with a longitudinal component to capture seasonal dietary intake was conducted in 11 villages of the Khunti district, Jharkhand. Household surveys and FFQs, supplemented with 2-d 24-h dietary recall and anthropometric assessments on 1 randomly selected woman per household were conducted.

Results

Limited access to diverse foods from a natural food environment (Food Accessed Diversity Index score of 0.3 ± 0.3) was observed. More than 90% women in both seasons had usual nutrient intakes below the estimated average requirements for all nutrients except protein and vitamin C; 35.5% of women were underweight. The mean Minimum Dietary Diversity Score among women (MDDS) was low [2.6 ± 0.6 in wet monsoon; 3 ± 0.7 in winters (acceptable ≥5)]. Higher MDDS contributed to higher usual nutrient intakes (P <0.001). Indigenous food intakes in both seasons (wet monsoon and winter) were low, e.g. Indigenous green leafy vegetables [10.5 and 27.8% of the recommended dietary intake (RDI), respectively], other vegetables (5.2% and 7.8% of RDI, respectively), and fruits (5.8 and 22.8% of RDI, respectively). Despite low intakes, the Indigenous food consumption score was positively associated with usual intake of vitamin A, riboflavin, vitamin C, pyridoxine, and calcium (P < 0.05) in the wet monsoon and thiamine, riboflavin, and zinc (P < 0.001) in winters. After adjusting for covariates, Indigenous food consumption was associated with a higher usual intake of vitamin A (P  < 0.001) in the wet monsoon season.

Conclusion

Contextual food-based interventions promoting Indigenous foods and increasing dietary diversity have the potential to address malnutrition in Munda women.

Assessment of Exercise-Associated Gastrointestinal Perturbations in Research and Practical Settings: Methodological Concerns and Recommendations for Best Practice

Strenuous exercise is synonymous with disturbing gastrointestinal integrity and function, subsequently prompting systemic immune responses and exercise-associated gastrointestinal symptoms, a condition established as "exercise-induced gastrointestinal syndrome." When exercise stress and aligned exacerbation factors (i.e., extrinsic and intrinsic) are of substantial magnitude, these exercise-associated gastrointestinal perturbations can cause performance decrements and health implications of clinical significance. This potentially explains the exponential growth in exploratory, mechanistic, and interventional research in exercise gastroenterology to understand, accurately measure and interpret, and prevent or attenuate the performance debilitating and health consequences of exercise-induced gastrointestinal syndrome. Considering the recent advancement in exercise gastroenterology research, it has been highlighted that published literature in the area is consistently affected by substantial experimental limitations that may affect the accuracy of translating study outcomes into practical application/s and/or design of future research. This perspective methodological review attempts to highlight these concerns and provides guidance to improve the validity, reliability, and robustness of the next generation of exercise gastroenterology research. These methodological concerns include participant screening and description, exertional and exertional heat stress load, dietary control, hydration status, food and fluid provisions, circadian variation, biological sex differences, comprehensive assessment of established markers of exercise-induced gastrointestinal syndrome, validity of gastrointestinal symptoms assessment tool, and data reporting and presentation. Standardized experimental procedures are needed for the accurate interpretation of research findings, avoiding misinterpreted (e.g., pathological relevance of response magnitude) and overstated conclusions (e.g., clinical and practical relevance of intervention research outcomes), which will support more accurate translation into safe practice guidelines.

National Food Intake Assessment: Technologies to Advance Traditional Methods

National dietary surveillance produces dietary intake data used for various purposes including development and evaluation of national policies in food and nutrition. Since 2000, What We Eat in America, the dietary component of the National Health and Nutrition Examination Survey, has collected dietary data and reported on the dietary intake of the US population. Continual innovations are required to improve methods of data collection, quality, and relevance. This review article evaluates the strengths and limitations of current and newer methods in national dietary data collection, underscoring the use of technology and emerging technology applications. We offer four objectives for national dietary surveillance that serve as guiding principles in the evaluation. Moving forward, national dietary surveillance must take advantage of new technologies for their potential in enhanced efficiency and objectivity in data operations while continuing to collect accurate dietary information that is standardized, validated, and publicly transparent.

Development of an Innovative Online Dietary Assessment Tool for France: Adaptation of myfood24

myfood24 is an innovative dietary assessment tool originally developed in English for use in the United Kingdom. This online 24 h recall, a tool commonly used in nutritional epidemiology, has been developed into different international versions. This paper aims to describe the creation of its French version. We used a consistent approach to development, aligned with other international versions, using similar methodologies. A nutritional database (food item codes, portion groups and accompaniments, etc.) was developed based on commonly used French food composition tables (CIQUAL 2017). Portion sizes were adapted to French dietary habits (estimation, photographs of French portion sizes, assessment of the photograph series and their angle (aerial vs. 45 degrees)). We evaluated the new tool, which contained nearly 3000 food items with 34 individuals using the System Usability Scale. We validated the French food portion picture series using EFSA criteria for bias and agreement. The results of the picture evaluation showed that the angle with which photos are taken had limited impact on the ability to judge portion size. Estimating food intake is a challenging task. Evaluation showed "good" usability of the system in its French version. myfood24 France will be a useful addition to nutritional epidemiology research in France.

Improvement of Methodology for Manual Energy Intake Estimation From Passive Capture Devices

Objective

To describe best practices for manual nutritional analyses of data from passive capture wearable devices in free-living conditions.

Method

18 participants (10 female) with a mean age of 45 ± 10 years and mean BMI of 34.2 ± 4.6 kg/m² consumed usual diet for 3 days in a free-living environment while wearing an automated passive capture device. This wearable device facilitates capture of images without manual input from the user. Data from the first nine participants were used by two trained nutritionists to identify sources contributing to inter-nutritionist variance in nutritional analyses. The nutritionists implemented best practices to mitigate these sources of variance in the next nine participants. The three best practices to reduce variance in analysis of energy intake (EI) estimation were: (1) a priori standardized food selection, (2) standardized nutrient database selection, and (3) increased number of images captured around eating episodes.

Results

Inter-rater repeatability for EI, using intraclass correlation coefficient (ICC), improved by 0.39 from pre-best practices to post-best practices (0.14 vs 0.85, 95% CI, respectively), Bland–Altman analysis indicated strongly improved agreement between nutritionists for limits of agreement (LOA) post-best practices.

Conclusion

Significant improvement of ICC and LOA for estimation of EI following implementation of best practices demonstrates that these practices improve the reproducibility of dietary analysis from passive capture device images in free-living environments.

Underreporting of Energy Intake Increases over Pregnancy: An Intensive Longitudinal Study of Women with Overweight and Obesity

(1) Background: Energy intake (EI) underreporting is a widespread problem of great relevance to public health, yet is poorly described among pregnant women. This study aimed to describe and predict error in self-reported EI across pregnancy among women with overweight or obesity. (2) Methods: Participants were from the Healthy Mom Zone study, an adaptive intervention to regulate gestational weight gain (GWG) tested in a feasibility RCT and followed women (n = 21) with body mass index (BMI) ≥25 from 8−12 weeks to ~36 weeks gestation. Mobile health technology was used to measure daily weight (Wi-Fi Smart Scale), physical activity (activity monitor), and self-reported EI (MyFitnessPal App). Estimated EI was back-calculated daily from measured weight and physical activity data. Associations between underreporting and gestational age, demographics, pre-pregnancy BMI, GWG, perceived stress, and eating behaviors were tested. (3) Results: On average, women were 30.7 years old and primiparous (62%); reporting error was −38% ± 26 (range: −134% (underreporting) to 97% (overreporting)), representing an ~1134 kcal daily underestimation of EI (1404 observations). Estimated (back-calculated), but not self-reported, EI increased across gestation (p < 0.0001). Higher pre-pregnancy BMI (p = 0.01) and weekly GWG (p = 0.0007) was associated with greater underreporting. Underreporting was lower when participants reported higher stress (p = 0.02) and emotional eating (p < 0.0001) compared with their own average. (4) Conclusions: These findings suggest systemic underreporting in pregnant women with elevated BMI using a popular mobile app to monitor diet. Advances in technology that allow estimation of EI from weight and physical activity data may provide more accurate dietary self-monitoring during pregnancy.

Patient-Generated Health Photos and Videos Across Health and Well-being Contexts: Scoping Review

Background

Patient-generated health data are increasingly used to record health and well-being concerns and engage patients in clinical care. Patient-generated photographs and videos are accessible and meaningful to patients, making them especially relevant during the current COVID-19 pandemic. However, a systematic review of photos and videos used by patients across different areas of health and well-being is lacking.

Objective

This review aims to synthesize the existing literature on the health and well-being contexts in which patient-generated photos and videos are used, the value gained by patients and health professionals, and the challenges experienced.

Methods

Guided by a framework for scoping reviews, we searched eight health databases (CINAHL, Cochrane Library, Embase, PsycINFO, PubMed, MEDLINE, Scopus, and Web of Science) and one computing database (ACM), returning a total of 28,567 studies. After removing duplicates and screening based on the predefined inclusion criteria, we identified 110 relevant articles. Data were charted and articles were analyzed following an iterative thematic approach with the assistance of NVivo software (version 12; QSR International).

Results

Patient-generated photos and videos are used across a wide range of health care services (39/110, 35.5% articles), for example, to diagnose skin lesions, assess dietary intake, and reflect on personal experiences during therapy. In addition, patients use them to self-manage health and well-being concerns (33/110, 30%) and to share personal health experiences via social media (36/110, 32.7%). Photos and videos create significant value for health care (59/110, 53.6%), where images support diagnosis, explanation, and treatment (functional value). They also provide value directly to patients through enhanced self-determination (39/110, 35.4%), social (33/110, 30%), and emotional support (21/110, 19.1%). However, several challenges emerge when patients create, share, and examine photos and videos, such as limited accessibility (16/110, 14.5%), incomplete image sets (23/110, 20.9%), and misinformation through photos and videos shared on social media (17/110, 15.5%).

Conclusions

This review shows that photos and videos engage patients in meaningful ways across different health care activities (eg, diagnosis, treatment, and self-care) for various health conditions. Although photos and videos require effort to capture and involve challenges when patients want to use them in health care, they also engage and empower patients, generating unique value. This review highlights areas for future research and strategies for addressing these challenges.

Validity and Feasibility of the Monitoring and Modeling Family Eating Dynamics System to Automatically Detect In-field Family Eating Behavior: Observational Study

Background

The field of dietary assessment has a long history, marked by both controversies and advances. Emerging technologies may be a potential solution to address the limitations of self-report dietary assessment methods. The Monitoring and Modeling Family Eating Dynamics (M2FED) study uses wrist-worn smartwatches to automatically detect real-time eating activity in the field. The ecological momentary assessment (EMA) methodology was also used to confirm whether eating occurred (ie, ground truth) and to measure other contextual information, including positive and negative affect, hunger, satiety, mindful eating, and social context.

Objective

This study aims to report on participant compliance (feasibility) to the 2 distinct EMA protocols of the M2FED study (hourly time-triggered and eating event–triggered assessments) and on the performance (validity) of the smartwatch algorithm in automatically detecting eating events in a family-based study.

Methods

In all, 20 families (58 participants) participated in the 2-week, observational, M2FED study. All participants wore a smartwatch on their dominant hand and responded to time-triggered and eating event–triggered mobile questionnaires via EMA while at home. Compliance to EMA was calculated overall, for hourly time-triggered mobile questionnaires, and for eating event–triggered mobile questionnaires. The predictors of compliance were determined using a logistic regression model. The number of true and false positive eating events was calculated, as well as the precision of the smartwatch algorithm. The Mann-Whitney U test, Kruskal-Wallis test, and Spearman rank correlation were used to determine whether there were differences in the detection of eating events by participant age, gender, family role, and height.

Results

The overall compliance rate across the 20 deployments was 89.26% (3723/4171) for all EMAs, 89.7% (3328/3710) for time-triggered EMAs, and 85.7% (395/461) for eating event–triggered EMAs. Time of day (afternoon odds ratio [OR] 0.60, 95% CI 0.42-0.85; evening OR 0.53, 95% CI 0.38-0.74) and whether other family members had also answered an EMA (OR 2.07, 95% CI 1.66-2.58) were significant predictors of compliance to time-triggered EMAs. Weekend status (OR 2.40, 95% CI 1.25-4.91) and deployment day (OR 0.92, 95% CI 0.86-0.97) were significant predictors of compliance to eating event–triggered EMAs. Participants confirmed that 76.5% (302/395) of the detected events were true eating events (ie, true positives), and the precision was 0.77. The proportion of correctly detected eating events did not significantly differ by participant age, gender, family role, or height (P>.05).

Conclusions

This study demonstrates that EMA is a feasible tool to collect ground-truth eating activity and thus evaluate the performance of wearable sensors in the field. The combination of a wrist-worn smartwatch to automatically detect eating and a mobile device to capture ground-truth eating activity offers key advantages for the user and makes mobile health technologies more accessible to nonengineering behavioral researchers.

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 Mixed-Method Study Exploring Experiences and Perceptions of Nutritionists Regarding Use of an Image-Based Dietary Assessment System in Tanzania

Due to global advances in technology, image-based food record methods have emerged as an alternative to traditional assessment methods. The use of image-based food records in low and lower-middle income countries such as Tanzania is limited, with countries still using traditional methods. The current study aimed to determine the feasibility of using a new voice and image-based dietary assessment system (VISIDA) in Dar es Salaam, Tanzania. This mixed-method study recruited 18 nutritionists as participants who collected image-based records of food and drinks they consumed using the VISIDA smartphone app. Participants viewed an online demonstration of the VISIDA web platform and the analysis process for intake data collected using the VISIDA app. Then, participants completed an online survey and were interviewed about the VISIDA app and web platform for food and nutrient intake analysis. The method was reported as being acceptable and was found to be easy to use, although technical challenges were experienced by some participants. Most participants indicated a willingness to use the VISIDA app again for one week or longer and were interested in using the VISIDA system in their current role. Participants acknowledged that the VISIDA web platform would simplify some aspects of their current job. Image-based food records could potentially be used in Tanzania to improve the assessment of dietary intake by nutritionists in urban areas. Participants recommended adding sound-on notifications, using the VISIDA app in both Apple and Android phones, enabling installation from the app store, and improving the quality of the fiducial markers.

Should you "picture" this? Effects of picture-taking features of food diary apps on memory, liking, and wanting

Picture-taking functions are commonly available features in food diaries and other mobile applications that may influence how we think about the very food we consume. Because memories of food (Higgs & Donohoe, 2011) and the act of recording food consumption (Turk et al., 2013) have been shown to influence desire for and consumption of food, this paper investigated the effects of using the picture-taking feature of a food diary app on liking, wanting, and memory of food. Using a simple food diary app with a picture-taking feature loaded onto iPads, participants took part in a lab experiment where they either did or did not use the picture-taking feature of the app as they ate a snack. To capture the changes in liking and wanting that naturally occur as more food is consumed, participants were also randomly assigned to receive either larger or smaller portions of the snack. The results indicate that picture-taking while eating is associated with greater wanting of the food following consumption. Furthermore, for smaller portions of food, taking pictures during consumption is associated with greater liking of the food. However, taking pictures in the smaller portion size condition was also associated with less detailed recall of food's sensory properties.

OUP accepted manuscript

While families have a central role in shaping individual choices and behaviors, healthcare largely focuses on treating individuals or supporting self-care. However, a family is also a health unit. We argue that family informatics is a necessary evolution in scope of health informatics. To deal with the needs of individuals, we must ensure technologies account for the role of their families and may require new classes of digital service. Social networks can help conceptualize the structure, composition, and behavior of families. A family network can be seen as a multiagent system with distributed cognition. Digital tools can address family needs in (1) sensing and monitoring; (2) communicating and sharing; (3) deciding and acting; and (4) treating and preventing illness. Family informatics is inherently multidisciplinary and has the potential to address unresolved chronic health challenges such as obesity, mental health, and substance abuse, support acute health challenges, and to improve the capacity of individuals to manage their own health needs.

Accuracy and Cost-effectiveness of Technology-Assisted Dietary Assessment Comparing the Automated Self-administered Dietary Assessment Tool, Intake24, and an Image-Assisted Mobile Food Record 24-Hour Recall Relative to Observed Intake: Protocol for a Randomized Crossover Feeding Study

BACKGROUND

The assessment of dietary intake underpins population nutrition surveillance and nutritional epidemiology and is essential to inform effective public health policies and programs. Technological advances in dietary assessment that use images and automated methods have the potential to improve accuracy, respondent burden, and cost; however, they need to be evaluated to inform large-scale use.

OBJECTIVE

The aim of this study is to compare the accuracy, acceptability, and cost-effectiveness of 3 technology-assisted 24-hour dietary recall (24HR) methods relative to observed intake across 3 meals.

METHODS

Using a controlled feeding study design, 24HR data collected using 3 methods will be obtained for comparison with observed intake. A total of 150 healthy adults, aged 18 to 70 years, will be recruited and will complete web-based demographic and psychosocial questionnaires and cognitive tests. Participants will attend a university study center on 3 separate days to consume breakfast, lunch, and dinner, with unobtrusive documentation of the foods and beverages consumed and their amounts. Following each feeding day, participants will complete a 24HR process using 1 of 3 methods: the Automated Self-Administered Dietary Assessment Tool, Intake24, or the Image-Assisted mobile Food Record 24-Hour Recall. The sequence of the 3 methods will be randomized, with each participant exposed to each method approximately 1 week apart. Acceptability and the preferred 24HR method will be assessed using a questionnaire. Estimates of energy, nutrient, and food group intake and portion sizes from each 24HR method will be compared with the observed intake for each day. Linear mixed models will be used, with 24HR method and method order as fixed effects, to assess differences in the 24HR methods. Reporting bias will be assessed by examining the ratios of reported 24HR intake to observed intake. Food and beverage omission and intrusion rates will be calculated, and differences by 24HR method will be assessed using chi-square tests. Psychosocial, demographic, and cognitive factors associated with energy misestimation will be evaluated using chi-square tests and multivariable logistic regression. The financial costs, time costs, and cost-effectiveness of each 24HR method will be assessed and compared using repeated measures analysis of variance tests.

RESULTS

Participant recruitment commenced in March 2021 and is planned to be completed by the end of 2021.

CONCLUSIONS

This protocol outlines the methodology of a study that will evaluate the accuracy, acceptability, and cost-effectiveness of 3 technology-enabled dietary assessment methods. This will inform the selection of dietary assessment methods in future studies on nutrition surveillance and epidemiology.

TRIAL REGISTRATION

Australian New Zealand Clinical Trials Registry ACTRN12621000209897; https://tinyurl.com/2p9fpf2s.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/32891.

Personalized nutrition for dementia prevention

The role of nutrition has been investigated for decades under the assumption of one-size-fits-all. Yet there is heterogeneity in metabolic and neurobiological responses to diet. Thus a more personalized approach may better fit biological reality and have increased efficacy to prevent dementia. Personalized nutrition builds on the food exposome, defined as the history of diet-related exposures over the lifetime, and on its interactions with the genome and other biological characteristics (eg, metabolism, the microbiome) to shape health. We review current advances of personalized nutrition in dementia research. We discuss key questions, success milestones, and future roadmap from observational epidemiology to clinical studies through basic science. A personalized nutrition approach based on the best prescription for the most appropriate target population in the most relevant time-window has the potential to strengthen dementia-prevention efforts.

Eating in the absence of hunger in 18-month-old children in a home setting

BACKGROUND

Eating in the absence of hunger (EAH), the susceptibility to eat despite satiety, may increase overweight. While EAH has been established in school-aged children, less is known about it during toddlerhood.

OBJECTIVES

This study assessed to what extent 18-month-old children eat in the absence of hunger, the stability of this behaviour at 24 months and the association of child eating behaviours with EAH.

METHODS

Children were presented with four palatable finger foods (total 275 kcal) after dinner. Univariate GLM's assessed the association between EAH, child satiety and eating behaviours and energy intake of dinner at 18 and 24 months (n = 206 and 103, respectively). Another GLM was run to assess the association between EAH at both time points.

RESULTS

Mean (±SD) energy intakes from dinner and finger foods were 240 kcal (±117) and 40 kcal (±37), respectively. No association was found between energy intake of dinner and finger foods. Enjoyment of food was significantly related to intake of finger foods (P = .005). EAH at 18 months predicted EAH at 24 months.

CONCLUSION

Eighteen-month-old children ate in the absence of hunger, irrespective of satiety. Thus, preceding energy intake was not compensated for. Other factors, for example, enjoyment of food seem to determine finger food intake.

Sports Nutrition: Diets, Selection Factors, Recommendations

An athlete’s diet is influenced by external and internal factors that can reduce or exacerbate exercise-induced food intolerance/allergy symptoms. This review highlights many factors that influence food choices. However, it is important to remember that these food choices are dynamic, and their effectiveness varies with the time, location, and environmental factors in which the athlete chooses the food. Therefore, before training and competition, athletes should follow the recommendations of physicians and nutritionists. It is important to study and understand the nutritional strategies and trends that athletes use before and during training or competitions. This will identify future clinical trials that can be conducted to identify specific foods that athletes can consume to minimize negative symptoms associated with their consumption and optimize training outcomes.

Feasibility, acceptability, and effects of behavior change interventions for improving multiple dietary behaviors among cancer survivors: a systematic review

OBJECTIVE

This study aimed to systematically identify and synthesize evidence on the feasibility, acceptability, and effects of behavior change interventions for improving multiple dietary behaviors among cancer survivors.

METHODS

A total of 14 electronic databases and three trial registries were searched. Experimental studies that examined the feasibility, acceptability, and effects of behavior change interventions for improving multiple dietary behaviors among cancer survivors and published in English or Chinese peer-reviewed journals or protocols were considered eligible. The methodological quality of the included studies was evaluated using the revised Cochrane risk-of-bias assessment tool. Data were extracted and synthesized narratively.

RESULTS

Six studies, with a sample size ranging from 50 to 3088, were included. The studies had a high overall risk of bias. Six studies reported feasibility data, and the average eligibility, recruitment, and retention rates at post-intervention were 60.7%, 66.7%, and 90.7%, respectively. Only one study measured the acceptability and reported that 66.6% of participants were satisfied with the intervention. Five out of the six studies that measured fruit and vegetable consumption reported statistically significant positive intervention effects. Two studies reported inconsistent intervention effects on wholegrain consumption. Only one study measured the consumption of processed meat, sugar, and alcohol, which had statistically nonsignificant intervention effect.

CONCLUSIONS

Behavior change interventions for improving multiple dietary behaviors might be feasible and effective to increase fruit and/or vegetable consumption among cancer survivors. Further research is needed to examine the acceptability and effects of the intervention for modifying other dietary behavior.

Effect of a late afternoon/early evening bout of aerobic exercise on postprandial lipid and lipoprotein particle responses to a high-sugar meal breakfast the following day in postmenopausal women: a randomized cross-over study

High-sugar consumption is related to dyslipidemia. How acute exercise affects postprandial lipid and lipoprotein particle responses to a high-sugar meal (HSM) in postmenopausal women is unclear. We examined the effects of a late afternoon/early evening bout of aerobic exercise on postprandial lipid and lipoprotein particle responses to a HSM breakfast the following day in 22 postmenopausal women. Subjects underwent exercise (EX) and no exercise (NE) conditions in the evening 13-16 h before the HSM breakfast consumption, in a random order. During the EX condition, subjects performed supervised aerobic exercise for 60 min at 75% of age-predicted maximum heart rate. The HSM (75.6% carbohydrate and 33% energy needs) was consumed after a 12-h fast. Serum lipids and lipoproteins were assessed at baseline and postprandially (60, 120, 180 min). Repeated measures analysis showed significantly lower area under the curve (geometric means [95% CI]) for triglycerides (TG) (2.96[2.43, 3.61] vs. 3.24[2.70, 3.88] mmol/L*hr; p = 0.049) and very low density lipoprotein particles (VLDLP) (114.6[88.2, 148.9] vs. 134.3[108.1, 166.9] nmol/L*hr; p = 0.02) during the EX versus NE condition. There were no condition effects for other variables. In conclusion, the EX versus NE condition lowered postprandial AUC for TG and VLDLP following HSM consumption in postmenopausal women.Trial Registration: ClinicalTrials.gov Identifier: NCT02919488.

Perspective: Opportunities and Challenges of Technology Tools in Dietary and Activity Assessment: Bridging Stakeholder Viewpoints

The science and tools of measuring energy intake and output in humans have rapidly advanced in the last decade. Engineered devices such as wearables and sensors, software applications, and Web-based tools are now ubiquitous in both research and consumer environments. The assessment of energy expenditure in particular has progressed from reliance on self-report instruments to advanced technologies requiring collaboration across multiple disciplines, from optics to accelerometry. In contrast, assessing energy intake still heavily relies on self-report mechanisms. Although these tools have improved, moving from paper-based to online reporting, considerable room for refinement remains in existing tools, and great opportunities exist for novel, transformational tools, including those using spectroscopy and chemo-sensing. This report reviews the state of the science, and the opportunities and challenges in existing and emerging technologies, from the perspectives of 3 key stakeholders: researchers, users, and developers. Each stakeholder approaches these tools with unique requirements: researchers are concerned with validity, accuracy, data detail and abundance, and ethical use; users with ease of use and privacy; and developers with high adherence and utilization, intellectual property, licensing rights, and monetization. Cross-cutting concerns include frequent updating and integration of the food and nutrient databases on which assessments rely, improving accessibility and reducing disparities in use, and maintaining reliable technical assistance. These contextual challenges are discussed in terms of opportunities and further steps in the direction of personalized health.

Perceptions of appetite do not match hormonal measures of appetite in trained competitive cyclists and triathletes following a ketogenic diet compared to a high-carbohydrate or habitual diet: A randomized crossover trial

Endurance athletes may implement rigid dietary strategies, such as the ketogenic diet (KD), to improve performance. The effect of the KD on appetite remains unclear in endurance athletes. This study analyzed the effects of a KD, a high-carbohydrate diet (HCD), and habitual diet (HD) on objective and subjective measures of appetite in trained cyclists and triathletes, and hypothesized that the KD would result in greater objective and subjective appetite suppression. Six participants consumed the KD and HCD for 2-weeks each, in a random order, following their HD. Fasting appetite measures were collected after 2-weeks on each diet. Postprandial appetite measures were collected following consumption of a ketogenic meal after the KD, high-carbohydrate meal after the HCD, and standard American/Western meal after the HD. Fasting total ghrelin (GHR) was lower and glucagon-like peptide-1 (GLP-1) and hunger were higher following the KD versus HD and HCD. Fasting insulin was not different. Mixed-effects model repeated measures analysis and effect sizes and 95% confidence intervals showed that postprandial GHR and insulin were lower and GLP-1 was higher following the ketogenic versus the standard and high-carbohydrate meals. Postprandial appetite ratings were not different across test meals. In conclusion, both fasting and postprandial concentrations of GHR were lower and GLP-1 were higher following the KD than the HC and HD, and postprandial insulin was lower on the KD. Subjective ratings of appetite did not correspond with the objective measures of appetite in trained competitive endurance athlete. More research is needed to confirm our findings.

Development of an Athlete Diet Index for Rapid Dietary Assessment of Athletes

Food-based diet indices provide a practical, rapid, and inexpensive way of evaluating dietary intake. Rather than nutrients, diet indices assess the intake of whole foods and dietary patterns, and compare these with nutrition guidelines. An athlete-specific diet index would offer an efficient and practical way to assess the quality of athletes' diets, guide nutrition interventions, and focus sport nutrition support. This study describes the development and validation of an Athlete Diet Index (ADI). Item development was informed by a review of existing diet indices, relevant literature, and in-depth focus groups with 20 sports nutritionists (median of 11 years' professional experience) from four elite athlete sporting institutes. Focus group data were analyzed (NVivo 11 Pro; QSR International Pty. Ltd., 2017, Melbourne, Australia), and key themes were identified to guide the development of athlete-relevant items. A modified Delphi survey in a subgroup of sports nutritionists (n = 9) supported item content validation. Pilot testing with athletes (n = 15) subsequently informed face validity. The final ADI (n = 68 items) was categorized into three sections. Section A (n = 45 items) evaluated usual intake, special diets or intolerances, dietary habits, and culinary skills. Section B (n = 15 items) assessed training load, nutrition supporting training, and sports supplement use. Section C (n = 8 items) captured the demographic details, sporting type, and caliber. All of the athletes reported the ADI as easy (40%) or very easy (60% of participants) to use and rated the tool as relevant (37%) or very relevant (63% of participants) to athletes. Further evaluation of the ADI, including the development of a scoring matrix and validation compared with established dietary methodology, is warranted.

Personalized machine learning of depressed mood using wearables

Depression is a multifaceted illness with large interindividual variability in clinical response to treatment. In the era of digital medicine and precision therapeutics, new personalized treatment approaches are warranted for depression. Here, we use a combination of longitudinal ecological momentary assessments of depression, neurocognitive sampling synchronized with electroencephalography, and lifestyle data from wearables to generate individualized predictions of depressed mood over a 1-month time period. This study, thus, develops a systematic pipeline for N-of-1 personalized modeling of depression using multiple modalities of data. In the models, we integrate seven types of supervised machine learning (ML) approaches for each individual, including ensemble learning and regression-based methods. All models were verified using fourfold nested cross-validation. The best-fit as benchmarked by the lowest mean absolute percentage error, was obtained by a different type of ML model for each individual, demonstrating that there is no one-size-fits-all strategy. The voting regressor, which is a composite strategy across ML models, was best performing on-average across subjects. However, the individually selected best-fit models still showed significantly less error than the voting regressor performance across subjects. For each individual's best-fit personalized model, we further extracted top-feature predictors using Shapley statistics. Shapley values revealed distinct feature determinants of depression over time for each person ranging from co-morbid anxiety, to physical exercise, diet, momentary stress and breathing performance, sleep times, and neurocognition. In future, these personalized features can serve as targets for a personalized ML-guided, multimodal treatment strategy for depression.

Investigating sex differences in the accuracy of dietary assessment methods to measure energy intake in adults: a systematic review and meta-analysis

BACKGROUND

To inform the interpretation of dietary data in the context of sex differences in diet-disease relations, it is important to understand whether there are any sex differences in accuracy of dietary reporting.

OBJECTIVE

To quantify sex differences in self-reported total energy intake (TEI) compared with a reference measure of total energy expenditure (TEE).

METHODS

Six electronic databases were systematically searched for published original research articles between 1980 and April 2020. Studies were included if they were conducted in adult populations with measures for both females and males of self-reported TEI and TEE from doubly labeled water (DLW). Studies were screened and quality assessed independently by 2 authors. Random-effects meta-analyses were conducted to pool the mean differences between TEI and TEE for, and between, females and males, by method of dietary assessment.

RESULTS

From 1313 identified studies, 31 met the inclusion criteria. The studies collectively included information on 4518 individuals (54% females). Dietary assessment methods included 24-h recalls (n = 12, 2 with supplemental photos of food items consumed), estimated food records (EFRs; n = 11), FFQs (n = 10), weighed food records (WFRs, n = 5), and diet histories (n = 2). Meta-analyses identified underestimation of TEI by females and males, ranging from -1318 kJ/d (95% CI: -1967, -669) for FFQ to -2650 kJ/d (95% CI: -3492, -1807) for 24-h recalls for females, and from -1764 kJ/d (95% CI: -2285, -1242) for FFQ to -3438 kJ/d (95% CI: -5382, -1494) for WFR for males. There was no difference in the level of underestimation by sex, except when using EFR, for which males underestimated energy intake more than females (by 590 kJ/d, 95% CI: 35, 1,146).

CONCLUSION

Substantial underestimation of TEI across a range of dietary assessment methods was identified, similar by sex. These underestimations should be considered when assessing TEI and interpreting diet-disease relations.

Personalized nutrition and healthy aging

The human lifespan and quality of life depend on complex interactions among genetic, environmental, and lifestyle factors. Aging research has been remarkably advanced by the development of high-throughput "omics" technologies. Differences between chronological and biological ages, and identification of factors (eg, nutrition) that modulate the rate of aging can now be assessed at the individual level on the basis of telomere length, the epigenome, and the metabolome. Nevertheless, the understanding of the different responses of people to dietary factors, which is the focus of precision nutrition research, remains incomplete. The lack of reliable dietary assessment methods constitutes a significant challenge in nutrition research, especially in elderly populations. For practical and successful personalized diet advice, big data techniques are needed to analyze and integrate the relevant omics (ie, genomic, epigenomic, metabolomics) with an objective and longitudinal capture of individual nutritional and environmental information. Application of such techniques will provide the scientific evidence and knowledge needed to offer actionable, personalized health recommendations to transform the promise of personalized nutrition into reality.

Measuring the Exercise Component of Energy Availability during Arduous Training in Women

INTRODUCTION

Low energy availability (EA) may impede adaptation to exercise, suppressing reproductive function and bone turnover. Exercise energy expenditure (EEE) measurements lack definition and consistency. This study aimed to compare EA measured from moderate and vigorous physical activity from accelerometry (EEEmpva) with EA from total physical activity (EEEtpa) from doubly labeled water in women. The secondary aim was to determine the relationship of EA with physical fitness, body composition by dual-energy x-ray absorptiometry, heart rate variability (HRV), and eating behavior (Brief Eating Disorder in Athletes Questionnaire [BEDA-Q]).

METHODS

This was a prospective, repeated-measures study, assessing EA measures and training adaptation during 11-month basic military training. Forty-seven women (23.9 ± 2.6 yr) completed three consecutive 10-d assessments of EEEmvpa, EEEtpa, and energy intake (EI). EA measures were compared using linear regression and Bland-Altman analyses; relationships of EA with fat mass, HRV, 1.5-mile run times, and BEDA-Q were evaluated using partial correlations.

RESULTS

EA from EEEmvpa demonstrated strong agreement with EA from EEEtpa across the measurement range (R2 = 0.76, r = 0.87, P < 0.001) and was higher by 10 kcal·kg-1 FFM·d-1. However, EA was low in absolute terms because of underreported EI. Higher EA was associated with improved 1.5-mile run time (r = 0.28, P < 0.001), fat mass loss (r = 0.38, P < 0.001), and lower BEDA-Q score (r = -0.37, P < 0.001) but not HRV (all P > 0.10).

CONCLUSION

Accelerometry-based EEE demonstrated validity against doubly labeled water during multistressor training, the difference representing 10 kcal·kg-1 FFM·d-1 EEE from nonexercise activity. Beneficial physical but not autonomic adaptations were associated with higher EA. EAmvpa and BEDA-Q warrant consideration for low EA assessment and screening.

An Assessment of the Validity of the Remote Food Photography Method (Termed Snap-N-Send) in Experienced and Inexperienced Sport Nutritionists

The remote food photography method, often referred to as "Snap-N-Send" by sport nutritionists, has been reported as a valid method to assess energy intake in athletic populations. However, preliminary studies were not conducted in true free-living conditions, and dietary assessment was performed by one researcher only. The authors, therefore, assessed the validity of Snap-N-Send to assess the energy and macronutrient composition in experienced (EXP, n = 23) and inexperienced (INEXP, n = 25) sport nutritionists. The participants analyzed 2 days of dietary photographs, comprising eight meals. Day 1 consisted of "simple" meals based around easily distinguishable foods (i.e., chicken breast and rice), and Day 2 consisted of "complex" meals, containing "hidden" ingredients (i.e., chicken curry). The estimates of dietary intake were analyzed for validity using one-sample t tests and typical error of estimates (TEE). The INEXP and EXP nutritionists underestimated energy intake for the simple day (mean difference [MD] = -1.5 MJ, TEE = 10.1%; -1.2 MJ, TEE = 9.3%, respectively) and the complex day (MD = -1.2 MJ, TEE = 17.8%; MD = -0.6 MJ, 14.3%, respectively). Carbohydrate intake was underestimated by INEXP (MD = -65.5 g/day, TEE = 10.8% and MD = -28.7 g/day, TEE = 24.4%) and EXP (MD = -53.4 g/day, TEE = 10.1% and -19.9 g/day, TEE = 17.5%) for both the simple and complex days, respectively. Interpractitioner reliability was generally "poor" for energy and macronutrients. The data demonstrate that the remote food photography method/Snap-N-Send underestimates energy intake in simple and complex meals, and these errors are evident in the EXP and INEXP sport nutritionists.

Estimating Dining Plate Size From an Egocentric Image Sequence Without a Fiducial Marker

Despite the extreme importance of food intake in human health, it is currently difficult to conduct an objective dietary assessment without individuals' self-report. In recent years, a passive method utilizing a wearable electronic device has emerged. This device acquires food images automatically during the eating process. These images are then analyzed to estimate intakes of calories and nutrients, assisted by advanced computational algorithms. Although this passive method is highly desirable, it has been thwarted by the requirement of a fiducial marker which must be present in the image for a scale reference. The importance of this scale reference is analogous to the importance of the scale bar in a map which determines distances or areas in any geological region covered by the map. Likewise, the sizes or volumes of arbitrary foods on a dining table covered by an image cannot be determined without the scale reference. Currently, the fiducial marker (often a checkerboard card) serves as the scale reference which must be present on the table before taking pictures, requiring human efforts to carry, place and retrieve the fiducial marker manually. In this work, we demonstrate that the fiducial marker can be eliminated if an individual's dining location is fixed and a one-time calibration using a circular plate of known size is performed. When the individual uses another circular plate of an unknown size, our algorithm estimates its radius using the range of pre-calibrated distances between the camera and the plate from which the desired scale reference is determined automatically. Our comparative experiment indicates that the mean absolute percentage error of the proposed estimation method is ~10.73%. Although this error is larger than that of the manual method of 6.68% using a fiducial marker on the table, the new method has a distinctive advantage of eliminating the manual procedure and automatically generating the scale reference.

Integration of an Image-Based Dietary Assessment Paradigm into Dietetic Training Improves Food Portion Estimates by Future Dietitians

The use of image-based dietary assessments (IBDAs) has rapidly increased; however, there is no formalized training program to enhance the digital viewing skills of dieticians. An IBDA was integrated into a nutritional practicum course in the School of Nutrition and Health Sciences, Taipei Medical University Taiwan. An online IBDA platform was created as an off-campus remedial teaching tool to reinforce the conceptualization of food portion sizes. Dietetic students’ receptiveness and response to the IBDA, and their performance in food identification and quantification, were compared between the IBDA and real food visual estimations (RFVEs). No differences were found between the IBDA and RFVE in terms of food identification (67% vs. 71%) or quantification (±10% of estimated calories: 23% vs. 24%). A Spearman correlation analysis showed a moderate to high correlation for calorie estimates between the IBDA and RFVE (r ≥ 0.33~0.75, all p < 0.0001). Repeated IBDA training significantly improved students’ image-viewing skills [food identification: first semester: 67%; pretest: 77%; second semester: 84%) and quantification [±10%: first semester: 23%; pretest: 28%; second semester: 32%; and ±20%: first semester: 38%; pretest: 48%; second semester: 59%] and reduced absolute estimated errors from 27% (first semester) to 16% (second semester). Training also greatly improved the identification of omitted foods (e.g., condiments, sugar, cooking oil, and batter coatings) and the accuracy of food portion size estimates. The integration of an IBDA into dietetic courses has the potential to help students develop knowledge and skills related to “e-dietetics”.