JMIR Publications

ABSTRACT

Background:

The monitoring of caloric intake is an important challenge for the maintenance of individual and public health. The instruments used so far for dietary monitoring mainly include food frequency questionnaires, food diaries and telephone interviews. Although they are inexpensive and easy to implement, these methods show important inaccuracies. Recently, alternative methods based on wearable devices and wrist accelerometers have been proposed. Though, poor analytics usually not well suited to manage massive sets of data generated from devices results in a limited accuracy of such methods in predicting caloric intake.

Objective:

The aim of this study is to develop an algorithm characterized by precision and stability in the estimate of caloric intake, using recent advances in machine learning methodology.

Methods:

The study will capture four individual eating activities outside the home over a two-month period. Twenty healthy Italian people will be recruited from the University of Padova with e-mail, flyers, and website announcements. The eligibility requirements include age 18 to 66 years and no eating disorder history. Each participant will be randomized to one of two menus to be eaten on weekdays in a predefined cafeteria in Padova (North-Eastern Italy). Flows of raw data will be accessed and downloaded from the wearable devices given to study participants and associated with anthropometric and demographic characteristics of the user (with his/her written permission). These massive data flows will provide a detailed picture of real-life conditions and will be analysed through an up-to-date machine learning approach with the aim to accurately predict the caloric contribution of individual eating activities. Gold standard evaluation of the energy content of eaten foods will be obtained by means of calorimetric assessments made at the Laboratory of Dietetics and Nutraceutical Research of the University of Padova.

Results:

From the present study, we expect to obtain a series of relevant data that, opportunely filtered, could allow the construction of a prototype algorithm able to estimate caloric intake through the recognition of food type and the number of bites. The algorithm should work in real time, to be embedded in a wearable device able to match bite-related movements and the corresponding caloric intake with high accuracy.

Conclusions:

Building an automatic calculation method for caloric intake, independent on the black-box processing of the wearable devices marketed so far, has a great potential both for clinical nutrition, for example for assessing cardiovascular compliance or for the prevention of coronary heart disease through proper dietary control, and public health nutrition as a low-cost monitoring tool for eating habits of population's layers. Clinical Trial: N/A