For many people January is a time to set healthy eating goals after the excesses of the festive period. Knowing which foods to opt for and which to avoid or working out how much you should eat can be a complicated process.
Professor Boulos, an expert in digital health at the University of the Highlands and Islands, is part of a group of researchers which have suggested there is potential to develop powerful and comprehensive systems which can help users make healthy choices tailored to their personal circumstances.
A new breed of “automated food scanner” apps, devices and methods is emerging which aim at identifying the exact nature of food and drinks in our diet.
Methods include: barcode scanning, weighing with portable electronic scales, vision-based measurement of volume/weight/portion size by smartphone camera photos, remote food and drink recognition by crowdsourced volunteers or dieticians using smartphone photos of meals sent over the Internet and/or Near Infrared spectroscopy (using a handheld sensor/scanner communicating wirelessly with a specialised smartphone app).
However, these methods are of limited value if we cannot further reason with the identified food and drink items in the context of a user’s health conditions and preferences.
Many of these methods connect to lookup databases to match and identify a scanned food or drink item and report the results back to the user. Such databases are based on ontologies – formal namings of sets of concepts within a domain. In smart e-health systems, food ontologies offer efficient and flexible means to capture knowledge about dietary concepts.
My research partners and I reviewed a number of existing food ontologies that can, with appropriate modifications and additions and along with other relevant non-food ontologies, supplement these databases in an attempt to progress from the mere automated identification of food and drinks to an application which can reason with identified items to better assist users in making healthy choices tailored to their circumstances.
The ontologies reviewed included:
- FoodWiki – a food consumption mobile e-health system which aims to help patients to avoid unhealthy ingredients that could worsen their health condition
- FOODS: A Food-Oriented Ontology-Driven System – Diabetes Edition – a food menu recommender system for people with diabetes
- Open Food Facts – a global food database based on contributions from individuals around the world which allows users to learn about food nutritional information and compare products from around the world.
Although none of the reviewed ontologies is fully comprehensive in scope and coverage (some are meant for very specific uses), they are good examples to learn from and might also form a basis to be expanded for future developments towards a universal comprehensive “smart diet assessment and recommendation” engine/application for consumers and patients with various diet-sensitive conditions worldwide.
Existing ontologies and their applications hint at the potential of the “powerful and smarter semantic reasoning with food data” that can be achieved if such ontologies are combined with other relevant non-food ontologies.
Delivering an “Internet of Food”
This kind of advanced application and reasoning requires a detailed knowledge of (or ontologies about):
- Individual user’s characteristics and health status/medical history
- The best, current clinical evidence about nutrition/dietetics and disease conditions
- Knowledge about different foods and drinks, local cuisine characteristics/cooking habits, commercial food/drink product offerings, etc. Variation by country and region should also be taken into consideration, given that people frequently travel these days for short or prolonged periods for work or leisure.
These complementary types of knowledge and the corresponding ontologies are key to delivering a smart “Internet of Food” which, much like the wider concept of the “Internet of Things”, would employ devices with electronics, software, sensors and network connectivity to create opportunities for more direct integration between the physical world and computer-based systems to improve efficiency and accuracy. Such an Internet of food could provide context and user-specific diet insights and “intelligent” recommendations based on individual’s health needs, circumstances and profiles at any given time.
For example, if gluten is identified as part of the composition of a scanned food item (from a food ontology) and we know the user who is about to ingest that food suffers from coeliac disease (from user’s health profile/medical history instance of a user model ontology) and we know that eating foods containing gluten can trigger a range of symptoms in people with celiac disease (from best current clinical evidence in a disease ontology), we can warn the user to avoid eating that food item.
Such an application could also help to advise users about any essential ingredients lacking in their diet or about their intake of substances with cumulative toxicity so they can stay within recommended limits. People with diabetes could benefit from a closer look at the carbohydrates profile of their diet and those with hypertension and cardiovascular disease might appreciate automated checks on the amounts of salt and saturated fats in their meals.
There is a growing demand for healthcare services to help people make informed choices about their wellbeing, including the foods and drinks they consume. Improper eating can contribute to or precipitate diseases, such as diabetes, hypertension, some types of cancer and some types of allergies.
To enable lay users and healthcare professionals to gain access to relevant medical knowledge about food products in e-health systems that integrate different technologies and data sources, semantic frameworks containing machine-readable annotations (ontology) about food and other relevant domains (e.g., clinical medicine, individual user profiles) are critical for the successful delivery of such smart e-health systems.
The ultimate goal is to progress beyond the mere identification of the details of what is on the user’s plate to answering the key question about “how good or healthy is the food given the user’s individual health condition, personal needs and preferences” and making recommendations for specific, personalised dietary improvements.
– – –
This post has been developed from the paper “Towards an “Internet of Food”: Food Ontologies for the Internet of Things” which was published in Volume 7, Issue 4 of the Future Internet journal. The paper was written by:
- Professor Maged N. Kamel Boulos – The Alexander Graham Bell Centre for Digital Health, University of the Highlands and Islands, Scotland
- Abdulslam Yassine – Distributed and Collaborative Virtual Environments Research (DISCOVER) Lab, University of Ottawa, Canada
- Shervin Shirmohammadi – College of Engineering and Natural Sciences, Istanbul Şehir University, Turkey
- Chakkrit Snae Namahoot – Faculty of Science, Naresuan University, Thailand
- Michael Brückner – Faculty of Education, Naresuan University, Thailand