Background.
Physical activity (PA) is a recognized boon for older adults, enhancing their overall well-being and mitigating health risks. Nevertheless, to encourage active lifestyles in this demographic, it is vital to understand the factors influencing PA. Conventional approaches predominantly rely on supervised cross-sectional evaluations, presuming both the stability of PA determinants over time and their isolated components. However, the complex nature of real-life dynamics often involves temporal variability in individual-level determinants. Digital phenotyping (DP), employing data recruited from personal digital devices, enables the continuous, unsupervised and real-time quantification of an individual's behavior within their natural context. This approach offers more ecological and dynamic assessments, revolutionizing our understanding of the intricacies underlying individual PA patterns in their environmental context.
Objective.
This paper aims to design a robust research protocol for the DP of PA behavior among healthy community-dwelling older adults aged 65 and above by employing a novel measurement approach.
Methods.
Observational data will be collected over a two-week period to assess various functions combining both cross-sectional and longitudinal data collection methods. Patterns of PA behavior and factors affecting PA outcomes will be detected in order to identify digital phenotypes related to PA. The measurements are based on the Behavior Change Wheel and include self-reporting and clinical assessments for cross-sectional data collection and ecological momentary assessment as well as time series collection for longitudinal data. The statistical analysis involves machine learning which will handle data complexity. Unsupervised learning will be used to uncover patterns, and supervised learning to identify variables. The analysis will be conducted in RStudio (v3.6.3) with significance set at 0.05.
Discussion.
A novel approach to understanding older adults' PA behavior will be used in this study. Challenges include varying technology adoption, usability, and unproven validity of health tech. Ethical considerations, representativeness, participant engagement, and machine learning expertise are also key aspects of the study's success. This study offers promise in bridging traditional and dynamic assessment methods for older adults' PA behavior to promote active lifestyles.
Trial registration:
Clinical Trials.gov: NCT06094374