Tackling school and community drivers of children's unhealthy diets in Arab cities

 

Children's eating behavior is one of the main pillars of a healthy life. Recent studies show that eating unhealthy food is highly associated with many chronic diseases including diabetes, obesity, and cancer. Such dietary habits are often shaped by complex factors influenced by the children's home, school, and neighborhood environments. However, studying the eating behaviors of children and analyzing the factors affecting them is currently done using traditional questionnaire-based methods, which often suffer from recall and bias issues. In this thesis, we developed a comprehensive approach to study children's food exposure and food consumption using deep learning.

Children’s health and development are profoundly affected by the foods they eat. Yet evidence shows that society is not giving infants, children, adolescents, and young people the support they need to eat the diets that will allow them to thrive. This is leading to unacceptably high levels of undernutrition (stunting and wasting), micronutrient deficiencies, and overweight and obesity - a triple burden. This document explores the daily lives of three children from different contexts. In their own words, these children show us how the foods they eat are powerfully influenced by the environments and systems in which they live.

Childhood obesity is a serious public health concern. Interventions to address this problem should not focus on biological and individual factors only, but they should target the factors in the child’s environment that affect his eating choices. Recent studies have shown that choice experiments are an important tool to assess children’s choices. The aim of this study is to explore why school aged children living in greater Beirut, make certain food choices, in the context of a real food modeling experiment. It also aims to understand to what degree the choices made in this choice experiment are similar to the real food choices they make in their life. Twenty-seven children in grades four, five and six played a game displaying a choice experiment. Then they were interviewed. Factors that were intended to be studies (food price, food placement, food preparation and mother’s/ peer’s influence), have been shown to affect children’s food choices in addition to new factors that emerged (Expected taste, the degree to which the food is considered by the child and food safety). The findings also revealed that this choice experiment reflects children’s real food choices. These findings can be used to inform policies aiming to address childhood obesity.

Children’s dietary habits are influenced by complex factors within their home, school and neighborhood environments. Identifying such influencers and assessing their effects is traditionally based on self- reported data which can be prone to recall bias. We developed a culturally acceptable machine-learning-based data-collection system to objectively capture school-children’s exposure to food (including food items, food advertisements, and food outlets) in two urban Arab centers: Greater Beirut, in Lebanon, and Greater Tunis, in Tunisia. Our machine-learning-based system consists of 1) a wearable camera that captures continuous footage of children’s environment during a typical school day, 2) a machine learning model that automatically identifies images related to food from the collected data and discards any other footage, 3) a second machine learning model that classifies food-related images into images that contain actual food items, images that contain food advertisements, and images that contain food outlets, and 4) a third machine learning model that classifies images that contain food items into two classes, corresponding to whether the food items are being consumed by the child wearing the camera or whether they are consumed by others. This manuscript reports on a user-centered design study to assess the acceptability of using wearable cameras to capture food exposure among school children in Greater Beirut and Greater Tunis. We then describe how we trained our first machine learning model to detect food exposure images using data collected from the Web and utilizing the latest trends in deep learning for computer vision. Next, we describe how we trained our other machine learning models to classify food-related images into their respective categories using a combination of public data and data acquired via crowdsourcing. Finally, we describe how the different components of our system were packed together and deployed in a real-world case study and we report on its performance.

Assessing the healthiness of food items in images has gained attention in both the computer vision and the nutrition fields. However, such task is generally a difficult one as food images are captured in various settings and thus are usually non-homogeneous. Moreover, assessing how healthy a food item is requires nutritional expertise and knowledge of the constituents of the food item and how it is processed. In this manuscript, we propose an end-to-end deep learning approach that can detect and localize various food items in a given food image using a customized object detection model. Our approach then assesses how healthy each detected food item is by classifying it into one or more of the four NOVA groups (Unprocessed Food, Processed Culinary Ingredients, Processed Food, and Ultra-processed Food). To train our food item detection model, we used two public datasets and a custom one we created ourselves and which contains images of food taken using wearable cameras. To train the NOVA food classifier, we use the custom dataset we created ourselves and that was manually labeled by expert nutritionists. Our food item detection model achieved a mAP of 0.90 and the NOVA food classifier achieved an average F1-score of 0.86 on test data.