A State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in Healthcare

TL;DR

This article addresses the challenge of extracting meaningful long-term patterns from longitudinal wearable sensor data in healthcare. It synthesizes three core modeling perspectives—rhythms, routines, and stability metrics—and details practical methods ranging from COSINOR-based circadian analysis to eigen-behavior and sequence-based routine modeling, as well as various single- and multi-modal stability metrics. The authors discuss critical issues in data quality, windowing, change detection, and evaluation, and identify open research directions to improve generalizability and contextual interpretation. By bridging computational and clinical perspectives, the work aims to advance pervasive healthcare through robust, interpretable analyses of lifelong sensor data, enabling predictive, preventive, personalized, and participatory medicine.

Abstract

Wearable devices are increasingly used as tools for biomedical research, as the continuous stream of behavioral and physiological data they collect can provide insights about our health in everyday contexts. Long-term tracking, defined in the timescale of months of year, can provide insights of patterns and changes as indicators of health changes. These insights can make medicine and healthcare more predictive, preventive, personalized, and participative (The 4P's). However, the challenges in modeling, understanding and processing longitudinal data are a significant barrier to their adoption in research studies and clinical settings. In this paper, we review and discuss three models used to make sense of longitudinal data: routines, rhythms and stability metrics. We present the challenges associated with the processing and analysis of longitudinal wearable sensor data, with a special focus on how to handle the different temporal dynamics at various granularities. We then discuss current limitations and identify directions for future work. This review is essential to the advancement of computational modeling and analysis of longitudinal sensor data for pervasive healthcare.