🤖 AI Summary
Traditional summary metrics struggle to capture the heterogeneity in individual physical activity intensity distributions. This study proposes a novel approach that integrates wrist-worn accelerometer-derived individual activity intensity hazard functions with functional data analysis. By employing nonparametric modeling, log-transformation, and covariate-adjusted functional principal component analysis (FPCA), the method uncovers dominant modes of variation in population-level physical activity patterns. Moving beyond mean-based summaries, this framework offers a more flexible and interpretable characterization of heterogeneity. Applied to large-scale NHANES data, the approach successfully identifies significant differences in high- and low-intensity activity profiles across population subgroups, demonstrating its superior capability in describing and comparing physical activity distributions.
📝 Abstract
Physical activity plays a vital role in human health. Its entire distribution differs among people. Commonly used summary measures cannot describe this distributional pattern. We present a distribution-based analytical approach to describe physical activity by modeling individual-level activity-intensity patterns through hazard functions derived from wrist-worn accelerometer data. We analyzed minute-level Monitor-Independent Movement Summary (MIMS) data of 4297 adults with seven continuous days of device wear from the 2011- 2012 National Health and Nutrition Examination Survey (NHANES). We derived a nonparametric activity-intensity hazard using a survival-based approach for each individual on a common intensity grid, treating both the hazard curves from MIMS and their log-transformed MIMS as functional objects. We used functional principal component analysis (FPCA) on both scales of MIMS to characterize dominant modes of variation in activity-intensity distributions. Group-wise mean hazard functions showed little difference at lower intensity levels, while we observed a substantial difference at higher intensity levels. Our results demonstrate that hazard-based functional representations for capturing differences in physical activity intensity distributions across individuals offer a flexible and interpretable way to characterize heterogeneity. This approach works better than mean-based summaries and supports principled comparisons of physical activity patterns across population subgroups.