Abstract
ObjectivesTraditional methods for creating food composition databases struggle to cope with the large number of products and the rapid pace of turnover in the food supply. This paper introduces Food Label Information Program (FLIP), a big data approach to the evaluation of the Canadian food supply and presents the latest methods used in the development of this database.MethodsThe Food Label Information Program (FLIP) is a database of Canadian food and beverage package labels by brand name. The latest iteration of the FLIP, FLIP 2020, was developed using website “scraping” to collect food labeling information (e.g., nutritional composition, price, product images, ingredients, brand, etc.) on all foods and beverages available on seven major Canadian e-grocery retailer websites between May 2020 and February 2021.ResultsThe University of Toronto's Food Label Information Program (FLIP) 2020 was developed in three phases: Phase 1, database development and enhancements; Phase 2, data capture and management of food products and nutrition information; Phase 3, data processing and food categorizing. A total of 74,445 products available on websites of seven retailers and 2 location-specific duplicate retailers were collected for FLIP 2020. Of 57,006 food and beverage products available on seven retailers, nutritional composition data were available for about 60% of the products and ingredients were available for about 45%. Data for energy, protein, carbohydrate, fat, sugar, sodium and saturated fat were present for 54–65% of the products, while fiber information was available for 37%. Food products were classified under multiple categorization systems, including Health Canada's Table of Reference Amounts, Health Canada's sodium categories for guiding benchmark sodium levels, sugar-focused categories and categories specific to various global nutrient profiling models.ConclusionsFLIP is a powerful tool for evaluating and monitoring the Canadian food supply environment. The comprehensive sampling and granularity of collection provides power for revealing analyses of the relationship between nutritional quality and marketing of branded foods, timely observation of product reformulation and other changes to the Canadian food supply.
Highlights
The study of nutritional epidemiology relies on understanding the association between nutrient consumption and health outcomes and usually involves monitoring the nutritional quality of food consumed by a population [1]
To address these research gaps, we aimed to develop a product- and brand-specific comprehensive database containing nutrition information for a diverse array of packaged foods and beverages in the Canadian food supply
Given the common usage of big data techniques in collecting, storing, processing and analyzing data, applied in many fields across non-profit, scientific, business and public sectors, this paper introduces FLIP 2020, an Artificial Intelligence (AI)-enhanced/powered Optical Character Recognition (OCR) (AI-enhanced OCR) approach to the collection and evaluation of the Canadian packaged food and beverage supply and presents the methods used in the development of this database
Summary
The study of nutritional epidemiology relies on understanding the association between nutrient consumption and health outcomes and usually involves monitoring the nutritional quality of food consumed by a population [1]. Such studies rely on the assessments of dietary intakes based on the collection of nutrition information from food composition tables or databases [1]. Despite the dominant role of these packaged foods and beverages in the diets of populations, existing food composition databases are limited in their ability to capture accurate nutrient content information for specific products due to the complex and dynamic nature of the national food supplies [4–6]. Most national food composition databases include aggregate nutrition information for only a limited number of generic food items. Using the CNF to analyze changes in the food supply or Canadian population dietary intakes poses several challenges due to its lack of scheduled comprehensive and systematic updating, the use of some non-Canadian food composition data, and aggregated data for packaged foods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
