Search Results (2)

Falls are a major problem in hospitals, and physical or chemical restraints are commonly used to “protect” patients in hospitals and service users in hostels, especially elderly patients with dementia. However, physical and chemical restraints may be unethical, detrimental to mental health and associated with negative side effects. Building upon our previous development of the wandering behavior monitoring system “eNightLog”, we aimed to develop a non-contract restraint-free multi-depth camera system, “eNightTrack”, by incorporating a deep learning tracking algorithm to identify and notify about fall risks. Our system evaluated 20 scenarios, with a total of 307 video fragments, and consisted of four steps: data preparation, instance segmentation with customized YOLOv8 model, head tracking with MOT (Multi-Object Tracking) techniques, and alarm identification. Our system demonstrated a sensitivity of 96.8% with 5 missed warnings out of 154 cases. The eNightTrack system was robust to the interference of medical staff conducting clinical care in the region, as well as different bed heights. Future research should take in more information to improve accuracy while ensuring lower computational costs to enable real-time applications. Full article

Older people are increasingly dependent on others to support their daily activities due to geriatric symptoms such as dementia. Some of them stay in long-term care facilities. Elderly people with night wandering behaviour may lose their way, leading to a significant risk of injuries. The eNightLog system was developed to monitor the night-time bedside activities of older people in order to help them cope with this issue. It comprises a 3D time-of-flight near-infrared sensor and an ultra-wideband sensor for detecting human presence and to determine postures without a video camera. A threshold-based algorithm was developed to classify different activities, such as leaving the bed. The system is able to send alarm messages to caregivers if an elderly user performs undesirable activities. In this study, 17 sets of eNightLog systems were installed in an elderly hostel with 17 beds in 9 bedrooms. During the three-month field test, 26 older people with different periods of stay were included in the study. The accuracy, sensitivity and specificity of detecting non-assisted bed-leaving events was 99.8%, 100%, and 99.6%, respectively. There were only three false alarms out of 2762 bed-exiting events. Our results demonstrated that the eNightLog system is sufficiently accurate to be applied in the hostel environment. Machine learning with instance segmentation and online learning will enable the system to be used for widely different environments and people, with improvements to be made in future studies. Full article