Carbohydrate Estimation by a Mobile Phone-Based System Versus Self-Estimations of Individuals With Type 1 Diabetes Mellitus: A Comparative Study

Abstract

BackgroundDiabetes mellitus is spreading throughout the world and diabetic individuals have been shown to often assess their food intake inaccurately; therefore, it is a matter of urgency to develop automated diet assessment tools. The recent availability of mobile phones with enhanced capabilities, together with the advances in computer vision, have permitted the development of image analysis apps for the automated assessment of meals. GoCARB is a mobile phone-based system designed to support individuals with type 1 diabetes during daily carbohydrate estimation. In a typical scenario, the user places a reference card next to the dish and acquires two images using a mobile phone. A series of computer vision modules detect the plate and automatically segment and recognize the different food items, while their 3D shape is reconstructed. Finally, the carbohydrate content is calculated by combining the volume of each food item with the nutritional information provided by the USDA Nutrient Database for Standard Reference.ObjectiveThe main objective of this study is to assess the accuracy of the GoCARB prototype when used by individuals with type 1 diabetes and to compare it to their own performance in carbohydrate counting. In addition, the user experience and usability of the system is evaluated by questionnaires.MethodsThe study was conducted at the Bern University Hospital, “Inselspital” (Bern, Switzerland) and involved 19 adult volunteers with type 1 diabetes, each participating once. Each study day, a total of six meals of broad diversity were taken from the hospital’s restaurant and presented to the participants. The food items were weighed on a standard balance and the true amount of carbohydrate was calculated from the USDA nutrient database. Participants were asked to count the carbohydrate content of each meal independently and then by using GoCARB. At the end of each session, a questionnaire was completed to assess the user’s experience with GoCARB.ResultsThe mean absolute error was 27.89 (SD 38.20) grams of carbohydrate for the estimation of participants, whereas the corresponding value for the GoCARB system was 12.28 (SD 9.56) grams of carbohydrate, which was a significantly better performance ( P=.001). In 75.4% (86/114) of the meals, the GoCARB automatic segmentation was successful and 85.1% (291/342) of individual food items were successfully recognized. Most participants found GoCARB easy to use.ConclusionsThis study indicates that the system is able to estimate, on average, the carbohydrate content of meals with higher accuracy than individuals with type 1 diabetes can. The participants thought the app was useful and easy to use. GoCARB seems to be a well-accepted supportive mHealth tool for the assessment of served-on-a-plate meals.

eHealth technologies to support nutrition and physical activity behaviors in diabetes self-management

“…When the GoCARB application was tested in 19 adults with T1DM, the estimation error of the carbohydrate content of each meal using manual estimation was 28±38 g, whereas when using the GoCARB app, the estimation error was reduced to 12±10 g of carbohydrate. The system correctly identified 85% of the food items contained within the meals 57. The participants rated the usability highly, but delays in the transmission of data and reliance on an Internet connection were seen as negative elements of the application 57…”

Two-View 3D Reconstruction for Food Volume Estimation

“…It uses segmentation to calculate portion sizes, and, by using food recognition, the nutrient profile is built up. The system has been tested in a pre-clinical trial showing greater accuracy than the target users [39], and in a clinical trial which showed a positive impact to the selfmanagement of type 1 diabetes [40].…”

Meal estimation from Continuous Glucose Monitor data using Kalman filtering and hypothesis testing

“…One of the problems with relying on user meal announcements is that the carbohydrate estimation by the user is often inaccurate, both in time and value. An example of this is reported by [9], where the CHO estimation by diabetes patients was off by 28 g on average. In other cases, users will forget to announce the meal entirely.…”

“…Other researchers have investigated systems for automatic carbohydrate estimation based on e.g. images [9]. The drawback here is that while the estimate of the carbohydrate content may be more accurate through computer vision, meal announcement by the user is still needed, as he or she will have to remember to take a picture of every meal.…”