Learning network for Advanced Behavioural Data Analysis

Project Information

LABDA

Grant agreement ID: 101072993

DOI

10.3030/101072993

EC signature date 14 July 2022

Start date 1 February 2023

End date 31 January 2027

Funded under

• Marie Skłodowska-Curie Actions (MSCA)

Total cost

No data

EU contribution

€ 2 881 036,80

Coordinated by

STICHTING AMSTERDAM UMC
Netherlands

Periodic Reporting for period 1 - LABDA (Learning network for Advanced Behavioural Data Analysis)

Reporting period: 2023-02-01 to 2025-01-31

Summary of the context and overall objectives of the project

Recently, there has been a paradigm shift from the isolated focus on the health impact of single behaviours (physical activity, sedentary behaviour, sleep) to the combined health effects of 24/7 movement behaviours. Technological advancements have led to wearable sensors providing rich time-series data. Such large-scale data require novel analysis methods to provide detailed insight into the links between multidimensional 24/7 movement behaviour and health, potential relevant subgroups, and relevant behavioural characteristics to target in interventions. In LABDA, leading researchers in advanced movement behaviour data analysis at the intersection of data science, method development, epidemiology, public health, and wearable technology are brought together to address this challenge.

Objective

LABDA aims to train a new generation of creative and innovative public health researchers with strong analytical and data science skills, and a deep understanding of all aspects of wearable sensor data analysis, that are able to develop sound analysis methods and apply these in various contexts. Via training-through-research, 12 doctoral fellows collaboratively work towards (i) sound and accessible methods for advanced 24/7 movement behaviour data analysis, (ii) linking multimodal data, and (iii) a taxonomy to enable interoperability and data harmonisation.

Impact

Results are combined in an open source LABDA toolbox supporting the accessibility of advanced analysis methods, including a decision tree to guide users to the optimal method for their (research) question and data. LABDA will gain evidence informing optimised, tailored public health recommendations and improved personal wearable feedback concerning 24/7 movement behaviour. After the project, LABDA fellows will be in an excellent position to pursue careers in academia (epidemiology, data science), commercial business (wearable technology, consultancy), or government (public health policy).

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

We succeeded in recruiting twelve highly talented fellows, who started their training and projects. We organized two successful LABDAcademies providing network wide training tailored to the needs of the fellows. A third LABDAcademy is organized in May 2025. All fellows wrote a personalised career plan, which they discussed in a one-on-one meeting with the training coordinator prof Schipperijn. All fellows started or even completed their first secondment and planned future secondments. In a monthly online LABDA meeting, coordinated and chaired by the fellows themselves, the fellows can present and ask feedback on their individual research projects or collaborative efforts such as a LABDA open science report or the LABDA toolbox. All the Fellows also have taken a role in supporting the specific coordinators (Career Coordinator, Jasper Schipperijn (SDU); Research Coordinator, Paul Jarle Mork (NTNU); Dissemination Coordinators, Fawad Taj (VUmc) and Andrew Kingsnorth (LU); and Diversity officer Lauren Sherar (LU). They support the coordinators with their tasks such as setting up and developing the LABDA training program or collecting information and creating posts for different communication and dissemination purposes. These roles provide them with invaluable transferable skills that they will be able to apply in their future careers and provides the opportunity to collaborate with fellows and PIs from different organizations. 

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Fellows are working on methodologies that can be applied to GPS and accelerometer data, thereby introducing innovation inspired by other research areas to the field of physical behaviour science. These methods will be available to be used in several datasets in the world. For example, one fellow worked on the intensity gradient, a metric that enabled insights into the importance of the intensity distribution of physical activity for health and mortality. However, this metric was originally developed for use with ENMO while many datasets use different epoch-level metrics. This study generated methods that enable wider application of the intensity gradient to other epoch-level metrics used in large-scale studies, such as NHANES.

Intersectionality is a sociological analytical framework for understanding how groups' and individuals' social and political identities result in unique combinations of discrimination and privilege. One fellow conducted a systematic review summarizing all studies in the field of sports and physical activity that applied an intersectional lens. This review will inform intersectional analytical approaches as well as summarize the evidence inequalities in physical activity. A number of fellows are conducting intersectional analyses on various datasets.