Feasibility of the Depth Camera-based Physical Health Monitoring System for Elderly Living Alone

Objective: This study aimed to evaluate the validity of a depth camera-based system for monitoring physical function and assessing its feasibility for accurately monitoring activities of daily living. Design: Cross-sectional study. Methods: Twenty-three participants performed 15 activities of daily living within a living laboratory designed to simulate a home environment. The activities were monitored using a depth camera system capable of classifying actions into standing, sitting, and lying down, with a conventional video camera employed for recording. The duration of each activity, as measured by the system, was compared with direct observations made by a physical therapist, which were analyzed using motion analysis software. The association between these two measurement approaches was assessed using correlation analysis, coefficient of determination, intraclass correlation coefficient (ICC), and Bland-Altman plots. Results: Our findings showed that standing activities had the highest correlation (r 0.847) between the system measurements ＝ and physical therapist observations, followed by sitting (r 0.817) and lying down (r 0.734), showing lower correlations. ＝ ＝ However, the ICC and Bland-Altman plots revealed notable differences between the two measurement methods, particularly for activities that involved lying down. Conclusions: The depth camera-based physical monitoring system showed promise in distinguishing between standing, sitting, and lying down activities in home environments. However, the current study also highlighted some enhancements needed for capturing lying down activities.