KIDS: kinematics-based (in)activity detection and segmentation in a sleep case study

TL;DR

This paper introduces a Bayesian framework using wearable sensors to detect and segment sleep activity and inactivity, providing a reliable, non-intrusive alternative to traditional sleep assessment methods with high accuracy.

Contribution

It presents a novel probabilistic approach based on joint kinematics for sleep activity detection, with effective visualization and clinical interpretability, advancing non-invasive sleep monitoring.

Findings

Achieved up to 99.2% F1-score in posture change detection

Attained 0.96 Pearson's correlation in inactivity segmentation

Demonstrated potential for home-based sleep movement analysis

Abstract

Sleep behaviour and in-bed movements contain rich information on the neurophysiological health of people, and have a direct link to the general well-being and quality of life. Standard clinical practices rely on polysomnography for sleep assessment; however, it is intrusive, performed in unfamiliar environments and requires trained personnel. Progress has been made on less invasive sensor technologies, such as actigraphy, but clinical validation raises concerns over their reliability and precision. Additionally, the field lacks a widely acceptable algorithm, with proposed approaches ranging from raw signal or feature thresholding to data-hungry classification models, many of which are unfamiliar to medical staff. This paper proposes an online Bayesian probabilistic framework for objective (in)activity detection and segmentation based on clinically meaningful joint kinematics, measured by a custom-made wearable sensor. Intuitive three-dimensional visualisations of kinematic timeseries were accomplished through dimension reduction based preprocessing, offering out-of-the-box framework explainability potentially useful for clinical monitoring and diagnosis. The proposed framework attained up to 99.2\% $F_1$-score and 0.96 Pearson's correlation coefficient in, respectively, the posture change detection and inactivity segmentation tasks. The work paves the way for a reliable home-based analysis of movements during sleep which would serve patient-centred longitudinal care plans.