Skip to main content

Big data against childhood Obesity

Periodic Reporting for period 3 - BigO (Big data against childhood Obesity)

Reporting period: 2019-12-01 to 2021-03-31

Childhood and adolescent obesity is a major global and European public health problem. Currently, public actions are detached from local needs, mostly including indiscriminate blanket policies and single-element strategies, limiting their efficacy and effectiveness. The need for community-targeted actions has long been obvious, but the lack of monitoring and evaluation framework and the methodological inability to objectively quantify the local community characteristics, in a reasonable timeframe, has hindered that. Fortunately, technological achievements in mobile and wearable electronics and Big Data infrastructures allow the engagement of European citizens in the data collection process, allowing us to reshape policies at a regional, national and European level. In BigO, that will be facilitated through the development of a platform, allowing the quantification of behavioural community patterns through Big Data provided by wearables and eHealth- devices. During the project, BigO will reach out to more than 25.000 school and age-matched obese children and adolescents as sources for community data. Comprehensive models of the obesity prevalence dependence matrix will be created, allowing, for the first time the data-driven effectiveness predictions about specific policies on a community and the real-time monitoring of the population response, supported by powerful real-time data visualisations. In short, BigO will provide an innovative new suite, allowing the Public Health Authorities to evaluate their communities based on their obesity prevalence risk and to take local action, based on objective evidence. BigO does not aim to redefine, from the ground-up, the existing obesity-related policy strategies targeting childhood obesity prevalence. BigO does, however, aim to redefine the way those strategies are designed and deployed in the European societies.
BigO developed an integrated platform that measures real-time obesogenic behaviours of children and adolescents, using their mobile devices, and offers aggregated localized information from all participants to public health scientists and policy makers.
On one side, myBigO app is a tool for children’s education supporting citizen science activities but also serves as a monitoring tool in obesity clinics. GPS and accelerometry are automatically measured while pictures of meals and of food advertisements are sent by the children. Subjective information on their habits and perceptions on their living environment are also collected. More than 30 indicators on physical activity, visits to food shops and recreational areas are calculated daily, offering objective measures for different geographies. Aggregated at geohash level, this localized behaviour information is free from identifiable elements and preserves children’s privacy. For the same areas, urban environment characteristics as well as national statistics are integrated. Combined behaviour and environment information is visualized in the open web application for policy makers, the Public Health Authorities (PHA) portal, including powerful dashboards for data exploration and analyses in different geographies. Analyses include inferences about the strength of relationships between the environment and obesogenic behaviors as well as prediction and monitoring of changes in behaviours upon modifications of environment parameters.
At the same time information per individual is accessible to clinicians via the dedicated Clinical Portal, to monitor correlations of obesity related behaviours with BMI. A School Portal manages recruitment of school students and monitoring of behaviours for the whole class, used for educational purposes. Students are recruited as citizen scientists in line with ethical guidelines and avoidance of stigmatization. Administration tools have also been integrated, allowing management of the different types of users, data and procedures.

The BigO platform has proved robust operation with the system being up and running 24-7 in more than 30 months supporting large-scale data collection at schools and clinics. BigO reached out to more than 21000 children with 5809 using the BigO app and contributing their data.
Through the interactive dashboards of the PHA portal, enormous potential has been demonstrated in objectively evaluating behaviours and quantifying localized problems at municipality and even neighbourhood level. Skipping school lunches for fast food eating in Stockholm schools close to food retailers, low levels of walking in suburban areas in Thessaloniki and changes of physical activity habits during COVID 19 lock down are some of the behaviours that have been “revealed” via objective measures for the first time. They have been mapped in comprehensive visualizations that were disseminated to local authorities and have subsequently triggered discussions for planning local measures with the aid of BigO.

The BigO platform can be commercialized via two products: “BIGO FOR HEALTH POLICY MAKERS” and “BIGO FOR CLINICIANS” and their exploitation is supported by a 5-year financial plan.
ΒigO has contributed to major advances in the technological field and has produced more than 15 scientific publications in peer-reviewed journals.
Novel methods for measuring children behaviour in real life conditions were designed, implemented and evaluated. The BigO mobile app and BigO analytics back-end engine use these novel signal processing and AI approaches to collect multimodal big behavioural data of participating children and to encode their daily habits, i.e. their dietary and physical activity profile.
BigO introduced a new privacy preserving framework for statistical analysis of sensitive behavioural data. This allows the detailed mapping of human behaviour on a spatial canvas (the canvas of geohashes). The resulting spatial distributions of behaviour are aligned with similar distributions of environment condition thus allowing the extraction of correlations between them.
BigO advanced health policy decision making tools by offering informative visualizations and analyses of obesity related localized behaviours in powerful dashboards together with local environment and socioeconomic characteristics.

BigO has contributed significantly in increasing the awareness about healthy living and in teaching young Europeans of Voluntarism, Citizen Science and Public Participation. More than 21000 children and adolescents in 6 European cities have been informed about healthy living and/or about becoming citizen scientists for childhood obesity research. About 6000 of them participated as citizen scientists and contributing their data.
The citizen-scientist paradigm is a further unique selling point (USP) of BigO given that public-patient participation is accepted good practice in the development of people-centred public health interventions and clinical management services. Already the national health agency in Sweden cites BigO study on food advertisements.

The rigour that BigO has applied to the use of Big Data and mobile technologies in this sensitive population is a major USP. It allows to contribute to the science and practice of public health (and clinical management) as well as the collection and use of Big Data in the solutions to real life problems.
Visual comparison of a behaviour index in an area during different time periods.
Screenshots of BigO mobile app depicting the recording of consumed drinks.
Physical activity and Food-retailer visitation for Larissa, Greece students
Screenshots of BigO mobile app: (welcome screen, mood question, citizen scientist points monitoring)
BigO platform overview. Data is collected by children and their environment
The BigO project flyer
Public Health Authorities Portal is the graphical front end for health policy makers.