There exist many approaches which try to recommend healthy diets. Most of them, however, are mainly observational, use food diaries, and have led to erroneous recommendations by assuming that the same diet is right for all people.
But new tools, findings and emerging information technologies have changed the landscape for nutritional science and underscored the need to better individualise nutritional guidance. Personalised nutrition refers to tailored nutritional recommendations aimed at the promotion, maintenance of health and prevention against diseases through diet [1].
Digital tools have allowed the development of solutions to support users’ food choices and deliver nutritional guidance
The advent of portable computers, smartphones and tablets, has led to the development of an ever-increasing number of intelligent systems and applications which support users’ food choices in different contexts, such as identifying and selecting food ingredients, food products and recipes. Commonly, the goal of such applications is to support choices that are within the users’ preferences but, at the same time, are healthy for them and in line with their dietary targets [2].
There is a need to develop solutions that offer personalised dietary advice based on individuals’ physical and behavioural traits
Currently, diet personalisation in the context of such applications is mainly addressed to heterogeneous groups of population, depending on variables such as age, gender or physical state among others. Beyond this approach, a more accurate personalisation strategy is also used based on adapting some components of the diet to the genetic profile of the subject, while considering a limited number of phenotypical traits. Nevertheless, according to the International Society of Nutrigenetics and Nutrigenomics, ethical and legal regulations have not yet been established and are urgently needed to provide support to enable universal and personalised applications [3].
PREVENTOMICS’ Nutritional Recommender System (NRS)
In this landscape, one of the main goals of PREVENTOMICS project is to design a holistic, sustainable and usable approach for integrating and translating the clinical findings and dietary advices stemming from the results of nutritional science, into actionable insights for everyday use by end users with the aim to assist individuals in achieving a lasting dietary behaviour change that is beneficial for health.
More specifically, PREVENTOMICS aims to increase the user perception of diet-related personalisation by enabling an open ecosystem where food mobile apps can be integrated in order to leverage nutritional knowledge and provide recommendations tailored to the needs of individual users.
Food Mobile Apps will be able to integrate PREVENTOMICS’ Nutritional Recommender System to provide personalised suggestions to their users
Potentially, any application that can influence users’ food choices (including for example apps for healthy diets, weight loss, online food ordering, medical apps etc.) can use the PREVENTOMICS Nutritional Recommender System (NRS) to generate personalised food related suggestions.
The PREVENTOMICS NRS implements the necessary algorithms and required analytics services for combining genetic, biological, nutritional and psychological data in order to provide the knowledge related to the nutrition plan the user needs to follow for a healthy life. Moreover, it provides secure Application Programming Interfaces (APIs) so that third party food apps can access this information with the consent of the end user.
The User Journey of PREVENTOMICS’ personalised programme
The PREVENTOMICS user journey starts at the office of an affiliated professional (usually a nutritionist), where the user receives information about the benefits of our approach. The professional asks the user to:
- Create a PREVENTOMICS account
- Fill a set of questionnaires
- Provide blood, urine and saliva samples so that a set of biomarkers can be extracted.
A PREVENTOMICS personalised nutritional profile is created as soon as the test results are available and are imported to the PREVENTOMICS NRS.
At that point, the user is notified to enter his personalised PREVENTOMICS dashboard, where he can browse the generated profile, including his metabolomic cluster and a personalised list of recommended food ingredients and foods that he/she should consume for a healthy life. Part of the user’s profile is a personalised behavioural change support programme that consists of a set of DO actions that can nudge users to follow healthier lifestyles.
Once the user’s information is fed into the system, the user will be able to get personalised dietary and lifestyle habits recommendations
Third party application providers can integrate the PREVENTOMICS profile by asking the user to provide his consent through an OAuth 2.0 based authorization process.
Practically, a food app would integrate a “Use my PREVENTOMICS profile” option. When users select that option, they will be asked to login to their PREVENTOMICS account and authorise the third-party food app to access their profile.
PREVENTOMICS Nutritional Recommender System demonstration in three use cases
The PREVENTOMICS ecosystem is kick-started with three innovative integrations showcasing significant potential in diverse and complementary contexts:
Apps for food retailers
Our goal is to show how PREVENTOMICS improves the customer experience and fidelity at retail food stores. The PREVENTOMICS Nutritioanl Recommender System is currently being integrated into a micro-site for ALDI Spain supermarkets, enabling users to receive personalised ALDI food product recommendations with the aim to ensure a healthy living.
Apps for diet recommendations
Our goal is to show how PREVENTOMICS can support apps providing advanced diet recommendations for disease management and prevention. The PREVENTOMICS Nutritional Recommender System is currently being integrated into Metadieta’s app for dieticians, allowing them to provide personalised diets to their clients, which include patients with diabetes and obesity.
Apps for recipes recommendations
Our goal is to show how PREVENTOMICS can support apps providing personalised recipes recommendations considering end-users needs and nutritional profile. The PREVENTOMICS Nutritional Recommender System is currently being integrated into th SimpleFeast App, a company providing healthy food meals, allowing its clients to get personalised recommendations of recipes.
If you are interested in becoming part of the PREVENTOMICS open ecosystem contact us at info[at]preventomics.eu
Authors
Efthimios (Thimios) Bothos, PhD
Senior researcher in the Institute of Information and Computer and Communication Systems at the National and Technical University of Athens (NTUA). He holds a diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA, Greece), an MSc in “Engineering-Economic Systems” and a PhD on Social Computing systems. His current research interests include methods for Creativity, Ιnnovation Management and Ιdea Εvaluation, Information Aggregation Systems, Recommendation and Personalization Systems, and Behavioural change support systems for sustainable lifestyles.
Babis Magoutas, PhD
Research and Innovation Manager at the Institute of Information and Computer and Communication Systems of the National Technical University of Athens (NTUA). He holds a PhD in adaptive information systems (2010), an MBA in techno-economic systems (2006) and a diploma degree in electrical and computer engineering (2003), all from NTUA. His current research interests include information personalization, behavioural change support systems and machine learning. During his time at ICCS he has been involved in or managed research bids that resulted to grants of over 4M euros, while he has managed the work of ICCS in more than twelve EC projects. Dr. Magoutas has published more than 51 papers in international peer-reviewed journals and conferences, has 3 best papers awards, while he has co-organized workshops dealing with big data, open data and behavioural change support systems.
Gregoris Mentzas, Prof.
Full Professor of Management Information Systems, School of Electrical and Computer Engineering, National Technical University of Athens and Director of the Information Management Unit (IMU). His area of expertise is information technology management and his research concerns knowledge management, big data management in multi-cloud environments and prescriptive analytics. He has published 4 books and more than 200 papers in international peer-reviewed journals and conferences, has 5 best papers awards, sits on the editorial board of five international journals and has served as (co-)Chair or Program Committee Member in more than 55 international conferences. Gregoris has led or contributed in more than 50 European research and development projects. His experience includes twelve years of management consulting in corporate strategy and information systems strategy. He holds a Diploma Degree in Engineering (1984) and a Ph.D. in Operations Research and Information Systems (1988) both from NTUA.
References
[1] Betts J, Gonzalez J. Personalised nutrition: what makes you so special? Nutri Bull. (2016) 41:353–9. doi: 10.1111/nbu.12238
[2] Ntalaperas D., Bothos E., Perakis K., Magoutas B. and Mentzas G. (2015), DISYS: An Intelligent System for Personalized Nutritional Recommendations in Restaurants. 19th Panhellenic Conference on Informatics (PCI) 2015
[3] Kohlmeier, M., De Caterina, R., Ferguson, L. R., Görman, U., Allayee, H., Prasad, C., … Martinez, J. A. (2016). Guide and Position of the International Society of Nutrigenetics/Nutrigenomics on Personalized Nutrition: Part 2 – Ethics, Challenges and Endeavors of Precision Nutrition. Journal of Nutrigenetics and Nutrigenomics, 9(1), 28–46. https://doi.org/10.1159/000446347.
