In-Home Older Adults' Activity Pattern Monitoring Using Depth Sensors: A Review

Machine Learning-Based Computer Vision for Depth Camera-Based Physiotherapy Movement Assessment: A Systematic Review

Machine learning-based computer vision techniques using depth cameras have shown potential in physiotherapy movement assessment. However, a comprehensive understanding of their implementation, effectiveness, and limitations remains needed. Following PRISMA guidelines, we systematically reviewed studies from 2020 to 2024 across Web of Science, Scopus, PubMed, and Astrophysics Data System to explore recent advancements. From 371 initially identified publications, 18 met the inclusion criteria for detailed analysis. The analysis revealed three primary implementation scenarios: local (50%), clinical (33.4%), and remote (22.3%). Depth cameras, particularly the Kinect series (65.4%), dominated data collection methods. Data processing approaches primarily utilized RGB-D (55.6%) and skeletal data (27.8%), with algorithms split between traditional machine learning (44.4%) and deep learning (41.7%). Key challenges included limited real-world validation, insufficient dataset diversity, and algorithm generalization issues, while machine learning-based computer vision systems demonstrated effectiveness in movement assessment tasks, further research is needed to address validation in clinical settings and improve algorithm generalization. This review provides a foundation for enhancing computer vision-based assessment tools in physiotherapy practice.

American Geriatrics Society response to the World Falls Guidelines

Falls are a major cause of preventable death, injury, and reduced independence in adults aged 65 years and older. The American Geriatrics Society and British Geriatrics Society (AGS/BGS) published a guideline in 2001, revised in 2011, addressing common risk factors for falls and providing recommendations to reduce fall risk in community-dwelling older adults. In 2022, the World Falls Guidelines (WFG) Task Force created updated, globally oriented fall prevention risk stratification, assessment, management, and interventions for older adults. Our objective was to briefly summarize the new WFG, compare them to the AGS/BGS guideline, and offer suggestions for implementation in the United States. We reviewed 11 of the 12 WFG topics related to community-dwelling older adults and agree with several additions to the prior AGS/BGS guideline, including assessment and intervention for hearing impairment and concern for falling, assessment and individualized exercises for older adults with cognitive impairment, and performing a standardized assessment such as STOPPFall before prescribing a medication that could potentially increase fall risk. Notable areas of difference include: (1) AGS continues to recommend screening all patients aged 65+ annually for falls, rather than just those with a history of falls or through opportunistic case finding; (2) AGS recommends continued use of the Timed Up and Go as a gait assessment, rather than relying on gait speed; and (3) AGS recommends clinical judgment on whether or not to check an ECG for those at risk for falling. Our review and translation of the WFG for a US audience offers guidance for healthcare and other providers and teams to reduce fall risk in older adults.

Informing existing technology acceptance models: a qualitative study with older persons and caregivers

New technologies can help older persons age in place and support their caregivers. However, they need to be accepted by the end-users to do so. Technology acceptance models, such as TAM and UTAUT and their extensions, use factors like performance expectancy and effort expectancy to explain acceptance. Furthermore, they are based on quantitative methods. Our qualitative study investigates factors fostering and hindering acceptance among older persons and their caregivers for a variety of assistive technologies, including wearables, ambient sensors at home with and without cameras and social companion robots. The goal of this paper is twofold: On the one hand, it investigates the factors of technology acceptance models in a qualitative setting. On the other hand, it informs these models with aspects currently overlooked by them. The results reveal that performance expectancy and effort expectancy are relevant for acceptance. We also find that reliability, anxiety around technology and different social aspects have an influence on acceptance of assistive technology in aged care for all end-user groups. Our findings can be used to update current technology acceptance models and provide in-depth knowledge about the currently used factors.

Design and Validation of Vision-Based Exercise Biofeedback for Tele-Rehabilitation

Tele-rehabilitation has the potential to considerably change the way patients are monitored from their homes during the care process, by providing equitable access without the need to travel to rehab centers or shoulder the high cost of personal in-home services. Developing a tele-rehab platform with the capability of automating exercise guidance is likely to have a significant impact on rehabilitation outcomes. In this paper, a new vision-based biofeedback system is designed and validated to identify the quality of performed exercises. This new system will help patients to refine their movements to get the most out of their plan of care. An open dataset was used, which consisted of data from 30 participants performing nine different exercises. Each exercise was labeled as "Correctly" or "Incorrectly" executed by five clinicians. We used a pre-trained 3D Convolution Neural Network (3D-CNN) to design our biofeedback system. The proposed system achieved average accuracy values of 90.57% ± 9.17% and 83.78% ± 7.63% using 10-Fold and Leave-One-Subject-Out (LOSO) cross validation, respectively. In addition, we obtained average F1-scores of 71.78% ± 5.68% using 10-Fold and 60.64% ± 21.3% using LOSO validation. The proposed 3D-CNN was able to classify the rehabilitation videos and feedback on the quality of exercises to help users modify their movement patterns.

Improvement in Quality of Life with Use of Ambient-Assisted Living: Clinical Trial with Older Persons in the Chilean Population

In Chile, 18% of the population is over 60 years old and is projected to reach 31% in three decades. An aging population demands the development of strategies to improve quality of life (QoL). In this randomized trial, we present the implementation and evaluation of the Quida platform, which consists of a network of unintrusive sensors installed in the houses of elderly participants to monitor their activities and provide assistance. Sixty-nine elderly participants were included. A significant increase in overall QoL was observed amongst participants allocated to the interventional arm (p < 0.02). While some studies point out difficulties monitoring users at home, Quida demonstrates that it is possible to detect presence and movement to identify patterns of behavior in the sample studied, allowing us to visualize the behavior of older adults at different time intervals to support their medical evaluation.