Longitudinal Multimodal Sensing of Physical Activity and Well-Being in Older Adults
For researchers studying health monitoring in older adults, this work provides a benchmark and insights into the predictability of different health-related outcomes using wearable sensing data.
This study collected longitudinal multimodal data from 66 older adults in real-world settings and found that highly observable behavioral targets (e.g., activity levels) achieved robust predictive performance (macro-F1 65%), while more abstract clinical outcomes remained challenging. Historical features were the most informative predictors.
Wearable and mobile sensing technologies enable continuous monitoring of human behavior and health in real-world settings. However, predictive modeling in longitudinal multimodal data remains challenging, particularly when targeting complex or clinically derived outcomes. In this work, we present a longitudinal multimodal study of 66 older adults conducted in real-world conditions and combining wearable sensing, behavioral monitoring, and clinical assessments. This setting provides a rare opportunity to study an underrepresented population in long-term, into-the-wild conditions. Building on this dataset, we investigate how the alignment between sensed signals and target variables affects predictive performance across health-related tasks. We design a unified evaluation framework spanning tasks with increasing levels of observability, including Activity Levels prediction, Sleep Duration estimation, and Sleep Apnea Severity classification. Our results reveal a clear gradient of predictability: highly observable behavioral targets achieve robust performance (macro-F1 65%), while more abstract outcomes remain challenging despite consistent improvements over baseline models. Moreover, through explainability analysis, we show that historical features consistently emerge as the most informative predictors, highlighting the central role of longitudinal information.