Personalised Nutrition: The PROTEIN project.
Professor of Nutrition and Dietetics, International Hellenic University, Thessaloniki, Greece
Chair of the Nutrition Working Group (NWG) of EASO
Chair of the ESND Obesity of the European Federation of the Associations of Dietitians (EFAD)
Health professionals are responsible for providing support around delivering dietary advice Ito their patients. Personalised nutrition can be applied by health professionals in two broad areas: firstly, for the dietary management of people with specific diseases like obesity, diabetes or CVD, or for individuals who need special nutritional support—for example, in pregnancy or old age. Personalised nutrition can also help in the development of more effective interventions for improving public health.
Personalisation can be based on analysis of current behavioural patterns, patient preferences, barriers, and objectives, and on biological evidence of differential responses to foods/nutrients given genotypic or phenotypic characteristics.
New technology has enabled multiple endogenous and exogenous factors to be studied at the same time, like epigenomics, metabolomics, microbiomics as well as multiple key environmental factors. The ability to measure “everything that matters” is now becoming a reality with the increasing availability of fitness trackers, mobile apps, and other devices. These enable individuals to monitor continuously multiple health related factors, such as physical activity, sleep, and vital signs—for example, blood pressure, heart rate, and stress levels. All these measurements should help health professionals to assist individuals in achieving a lasting dietary behaviour change which is beneficial for their health.
PROTEIN, an H2020 research project, aims to propose a radically novel holistic approach for personalised nutrition through an end-to-end ecosystem, providing personalised nutrition, advice and support which can aid in helping consumer/users to achieve long-term healthy and sustainable diet. The system will provide improved personalised nutrition support including short- and long-term dietary plans, physical activity plans, nutritional recommendations for use in restaurants and digital and bricks and mortar grocery stores and early warnings related to suboptimal eating patterns. In order to successfully fulfil these aforementioned goals, the PROTEIN system will consist of the following core technologies:
Multimodal sensing technologies: The system will support a variety of sensors to collect data from users such as: the smartphone (for analysing still photos of food and identifying the ingredients and calories on the plate), smart watch/band (for monitoring physical activity), mandometer (eating rate progression and cumulative meal characteristics, e.g., meal size and duration), bowel sound capturing belt (for gastrointestinal tract and the recognition of abnormal motility) a volatile organic compounds sensor (for the measurement of the volatile organic compounds, through exhaled breath analysis and continuous glucose monitoring sensor.
Mobile technologies: The PROTEIN mobile application suite offers a number of functionalities and provides to users/consumers personalised nutrition support in various real-life environments, e.g., grocery shops, restaurants and home. The mobile suite follows a unified interface design and constitutes the main means of interaction for the users with the system and the sensors.
Direct-to-consumer genetic testing, blood analysis and gut microbiome: Genetic information, blood parameters and gut microbiota will play significant role in the building user profiles, especially for users living with non-communicable diseases. This information will enable the system to provide better personalisation services to specific user subgroups and will also provide valuable insights into the effect of genetic variation, blood parameters and other factors like physical and psychological characteristics and lifestyle, dietary response and response to project provided advice.
Cloud computing and big data analytics: All data from the interaction of users with the system (mobile suite and sensors) will be anonymised and securely stored in the Cloud for being available anywhere/anytime. PROTEIN will adopt big data analytics and machine-learning techniques for effectively mining the underlying knowledge, by developing a sophisticated, European and internationally compliant, data management system, capable of processing and handling the large amounts of collected data, seamlessly and in compliance with data protection and security requirements.
Artificial Intelligence: The core of the proposed system is based on an ensemble of AI agents for user modelling, i.e., personalisation, and system adaptation in order to produce re-adaptable short- and long-term dietary and physical activity plans as well as nutritional advices tailored to user’s needs and driven by her/his personal preferences, physical activity levels, health status, physiological and socio-cultural characteristics.
Web technologies: The backbone of the system is an integrated information-driven web platform that provides dashboards for users, nutritionists and medical experts and can be used to create a collaborative user-nutritionist/medical expert partnership, i.e., a co-production of health, with the aim of optimising user nutrition and quality of life.
Gamification and games: A gamification strategy will be adopted in both the real-world, through mobile applications, and virtual environments, e.g., dietary games, in order to engage users to a healthy diet and motivate them to change their behaviour through rewards and competition. Special care will be given to the engagement of young population for the building of healthy dietary habits/behaviours.