Importance of user interaction with automated dietary assessment methods

Boushey, Carol J.; Kerr, Deborah A.; Schap, TusaRebecca E.; Daugherty, B L

doi:10.1038/ejcn.2012.14

Cited by 3 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A fiducial marker, which resembles a checker board square, is included in the images as a color and size reference to help with the reconstruction of a three-dimensional environment that allows for estimation of the volume of the foods and beverages [13-16]. In addition, as shown in Figure 1, the system includes a user confirmation component referred to as the “review process” [17]. This step is important as a predominantly automated system requires a method to identify new foods (whether new to the system or new to market), correct foods that are misclassified, or identify attributes that cannot be captured in an image (eg, no salt, artificially sweetened).…”

Section: Introductionmentioning

confidence: 99%

How Willing Are Adolescents to Record Their Dietary Intake? The Mobile Food Record

Boushey¹,

Harray²,

Kerr³

et al. 2015

JMIR mHealth uHealth

View full text Add to dashboard Cite

BackgroundAccurately assessing the diets of children and adolescents can be problematic. Use of technologies, such as mobile apps designed to capture food and beverages consumed at eating occasions with images taken using device-embedded cameras, may address many of the barriers to gathering accurate dietary intake data from adolescents.ObjectiveThe objectives of this study were to assess the willingness of adolescents to take images of food and beverages at their eating occasions using a novel mobile food record (mFR) and to evaluate the usability of the user confirmation component of the mFR app, referred to as the “review process.”MethodsMixed methods combining quantitative and qualitative protocols were used in this study. Adolescents (11-15-year olds) attending a summer camp were recruited to participate in the study. First, the participants were asked to take images of foods and beverages consumed as meals and snacks for 2 consecutive days using the mFR app running on an iPhone and the number of images taken was noted. This was followed by focus group sessions to evaluate usability, which was analyzed by content and themes. After using the mFR, a think-aloud method was used to evaluate the usability of the mFR method for reviewing system-identified foods (ie, the review process). A usability questionnaire was administered at the end of all activities.ResultsThe mFR was accepted by the majority of the 24 boys and 17 girls (n=41) but varied according to gender and eating occasion. Girls were significantly more likely than boys to capture images of their eating occasions (Fisher exact test, P=.03). Participants were more likely to take images of their breakfasts (90%, 36/40) and lunches (90%, 72/80) and least likely to capture afternoon and evening snacks, 54% (43/80) and 40% (32/80), respectively. The major themes from the focus groups with regard to using the mFR were games, rewards, and the need to know more about why they were using the app. Results of the usability questionnaire indicated that including a game component would be important to increase willingness to use the mFR, and a high majority of the participants indicated a willingness to use the mFR for 7 days or more. The image review process was found to be easy to use except for some confusion with overlapping markers on the screen.ConclusionsThe adolescents’ experiences with and feedback about the mFR highlighted the importance of increased training, reminders, entertainment (eg, games), and training with practice in using the device to capture complete dietary intake as part of their active lifestyles.

show abstract

Section: Introductionmentioning

confidence: 99%

How Willing Are Adolescents to Record Their Dietary Intake? The Mobile Food Record

Boushey¹,

Harray²,

Kerr³

et al. 2015

JMIR mHealth uHealth

View full text Add to dashboard Cite

show abstract

“…Our strategy was to develop a user interface that is easy and intuitive given these requirements. We developed the mobile application for the Apple iPhone and tested it in various user studies (presented in [18–20]) involving more than 170 users that acquired just over half of the 11,000 images in our system’s database.…”

Section: Discussionmentioning

confidence: 99%

“…To our knowledge such issues have not been addressed in any previous work. Before closing this section, we would like to emphasize that our application is the result of several user studies involving more than 170 individuals [18–20]. Our system has images from these studies and the training images for these studies which represents about 11,000 images.…”

Section: Related Workmentioning

confidence: 99%

A mobile phone user interface for image-based dietary assessment

et al. 2014

View full text Add to dashboard Cite

Many chronic diseases, including obesity and cancer, are related to diet. Such diseases may be prevented and/or successfully treated by accurately monitoring and assessing food and beverage intakes. Existing dietary assessment methods such as the 24-hour dietary recall and the food frequency questionnaire, are burdensome and not generally accurate. In this paper, we present a user interface for a mobile telephone food record that relies on taking images, using the built-in camera, as the primary method of recording. We describe the design and implementation of this user interface while stressing the solutions we devised to meet the requirements imposed by the image analysis process, yet keeping the user interface easy to use.

show abstract

“…Acquiring photos is reasonably simple but nutritional content analysis of images is a major challenge. Automated food identification and portion size assessment is computationally and participant intensive; relying on participant feedback for accuracy (1) . Dietitian analysis of photos is accurate but time-consuming and expensive (2) .…”

mentioning

confidence: 99%

FoodFinder: developing a rapid low-cost crowdsourcing approach for obtaining data on meal size from meal photos

et al. 2016

View full text Add to dashboard Cite

Capturing meal images using mobile phone cameras is a promising alternative to traditional dietary assessment methods. Acquiring photos is reasonably simple but nutritional content analysis of images is a major challenge. Automated food identification and portion size assessment is computationally and participant intensive; relying on participant feedback for accuracy (1) . Dietitian analysis of photos is accurate but time-consuming and expensive (2) . Crowdsourcing could offer a rapid low-cost alternative by utilising the life-long experience that all humans have in food identification. Previous crowdsourcing methods include the Eatery app, which produces a simple 11-point 'healthiness' scale for each meal (3) and the PlateMate system, which creates a list of all individual foods with portion sizes, energy and macronutrient content (4) . While the Eatery produces limited and subjective data on meal content, PlateMate represents a complex integrated system of multiple tasks requiring on average 25 workers, costing £2·75 and taking 90 min per image. For feasible data-capture in a large-scale longitudinal studies, crowdsourcing data from meal photos needs to be cheaper and quicker. We aimed to develop a simpler task and tested it's feasibility for crowdsourcing dietary data.FoodFinder, a single task for identifying food groups and portion sizes, developed using Qualtrics (www.qualtrics.com/), and linked to the Prolific Academic (https://prolific.ac/) crowdsourcing platform for recruitment and reimbursement of a UK crowd. Thirty meal photos with measured total meal weight (grams) were analysed by a dietitian and crowds ranging in size from 5 to 50 people. The difference between actual meal weight (the gold-standard) and total meal weight estimated by different sized crowds and ratings by a dietician were compared to each other. To establish group consensus crowd estimates were weighted by majority agreement (5) . Bland-Altman analysis assessed agreement with actual meal weight.A crowd of 5 people underestimated true meal weight by 63 g, equating to 15 % of actual meal weight with limits of agreement (LOA) from −299 to 174 g. In comparison experts overestimated by 28 g equating to 9 % of actual meal weight with LOA −158, 214 g. With a crowd of 5 people, crowdsourcing cost £3·35 and took a mean 2 mins 55 sec (SD 2 min 6 sec) per image. A crowd of 50 had similar accuracy and limits of agreement (−65 g LOA −278, 149 g) but was more expensive. Further development of FoodFinder is required to make rapid low-cost analysis of meal photos via crowdsourcing a feasible method for assessing diet.

show abstract

Importance of user interaction with automated dietary assessment methods

Cited by 3 publications

References 4 publications

How Willing Are Adolescents to Record Their Dietary Intake? The Mobile Food Record

How Willing Are Adolescents to Record Their Dietary Intake? The Mobile Food Record

A mobile phone user interface for image-based dietary assessment

FoodFinder: developing a rapid low-cost crowdsourcing approach for obtaining data on meal size from meal photos

Contact Info

Product

Resources

About