A Mobile Food Record For Integrated Dietary Assessment

Abstract

This paper presents an integrated dietary assessment system based on food image analysis that uses mobile devices or smartphones. We describe two components of our integrated system: a mobile application and an image-based food nutrient database that is connected to the mobile application. An easy-to-use mobile application user interface is described that was designed based on user preferences as well as the requirements of the image analysis methods. The user interface is validated by user feedback collected from several studies. Food nutrient and image databases are also described which facilitates image-based dietary assessment and enable dietitians and other healthcare professionals to monitor patients dietary intake in real-time. The system has been tested and validated in several user studies involving more than 500 users who took more than 60,000 food images under controlled and community-dwelling conditions.

Reported Energy Intake Accuracy Compared to Doubly Labeled Water and Usability of the Mobile Food Record among Community Dwelling Adults

“…After baseline urine samples were collected, participants drank a mixture containing 1.8 g/kg total body water of 10% H 2 18 O and 0.12 g/kg total body water of 99% 2 H 2 O. Postdose urine samples were collected 4.5 and 6 h later, after urine voids were discarded at 1.5 and 3 h. During this time, the participants completed two physical activity questionnaires [18,19] and the Three Factor Eating Questionnaire [20]. After completing the questionnaires, each participant was provided with an iPhone 3GS with the mFR application preinstalled and a fiducial marker [21] (e.g., a checkerboard pattern of known shape, size, and color). The staff asked each participant about his/her usual eating times and accordingly installed three recording reminders.…”

“…The application is based on one of the technology assisted dietary assessment (TADA) protocols [4,21,23]. Crucial for the image analysis is the inclusion of the fiducial marker (FM) in the image [4,24,25].…”

“…The images from the study participants informed the automated classifier under community dwelling conditions. The results and progress of this aspect of the study are published elsewhere [21,23,24]. …”

Feasibility of Assessing Diet with a Mobile Food Record for Adolescents and Young Adults with Down Syndrome

“…Using the camera function on a mobile device such as an iPod may have been more familiar to PANDs study participants if they had previously used these devices. Compared to using the iPod camera, the mFR app required additional steps in taking the image (e.g., turning the iPod horizontally to capture the image) and buttons on the screen had written instructions (e.g., ‘snap it’) [27]. The need to read instructions was compensated for, however, by the buttons always being in the same place on the screen, and participants with Down syndrome and their family members/carers receiving training on how to use the app and device, and written and visual instructions being left with participants and families.…”

“…Images taken in real time can provide accurate information on the type and amount of food and beverages consumed whilst potentially reducing the recording burden associated with written food records for participants [22,23]. An image-based dietary assessment system known as Technology-Assisted Dietary Assessment or TADA [24,25,26,27] uses the camera on a mobile device to capture before and after images of food and beverages consumed. Referred to as the mobile food record (mFR) app, the participant is instructed take a before and after image of all food and beverages and to include a reference device known as a fiducial marker (a checkerboard pattern of known shape, size and colour) to assist with food identification and portion size estimation [26,28].…”