AGE-WELL Funded ProjectsOutputs
Title |
Category |
Date |
Authors |
Privacy Protecting Approaches for Automatic Detection of Behaviours of Risk in People with Dementia using Deep Learning KITE Research Institute at University Health Network, Toronto Rehab Institute, University Health Network | Scientific Excellence - Advancing Knowledge | 2022-10-19 | | Automatic Detection of Behaviours of Risk in People with Dementia using Unsupervised Deep Learning | Scientific Excellence - Advancing Knowledge | 2022-07-21 | Pratik Mishra | Privacy-Protecting Behaviours of Risk Detection in People with Dementia using VideosBackground: People living with dementia often exhibit behavioural and psychological symptoms of dementia that can put their and others’ safety at risk. Existing video surveillance systems in long-term care facilities can be used to monitor such behaviours of risk to alert the staf to prevent potential injuries or death in some cases. However, these behaviours of risk events are heterogeneous and infrequent in comparison to normal events. Moreover, analysing raw videos can also raise privacy concerns.
Purpose: In this paper, we present two novel privacy-protecting video-based anomaly detection approaches to detect behaviours of risks in people with dementia.
Methods: We either extracted body pose information as skeletons or used semantic segmentation masks to replace multiple humans in the scene with their semantic boundaries. Our work difers from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction. We used anonymized videos of normal activities to train customized spatiotemporal convolutional autoencoders and identify behaviours of risk as anomalies.
Results: We showed our results on a real-world study conducted in a dementia care unit with patients with dementia, containing approximately 21 h of normal activities data for training and 9 h of data containing normal and behaviours of risk events for testing. We compared our approaches with the original RGB videos and obtained a similar area under the receiver operating characteristic curve performance of 0.807 for the skeleton-based approach and 0.823 for the segmentation mask-based approach.
Conclusions: This is one of the frst studies to incorporate privacy for the detection of behaviours of risks in people with dementia. Our research opens up new avenues to reduce injuries in long-term care homes, improve the quality of life of residents, and design privacy-aware approaches for people living in the community KITE Research Institute at University Health Network, Toronto Rehab Institute, University Health Network | Scientific Excellence - Advancing Knowledge | 2023-01-21 | | dtFall – Decision Theoretic Framework to Report Unseen FallsNMO Project Toronto Rehab Institute, University Health Network, University of Waterloo | Scientific Excellence - Advancing Knowledge | 2016-05-16 | | X-Factor HMMs for detecting falls in the absence of fall-specific training data. Toronto Rehab Institute, University Health Network, University of Waterloo | Scientific Excellence - Advancing Knowledge | 2014-12-01 | | Multiple Imputation Approaches for One- Class Classification Toronto Rehab Institute, University Health Network, University of Waterloo | Scientific Excellence - Advancing Knowledge | 2012-05-01 | | Towards the detection of unusual temporal events during activities using HMMs Toronto Rehab Institute, University Health Network, University of Waterloo | Scientific Excellence - Advancing Knowledge | 2012-04-01 | | Detecting falls with X-Factor HMMs when the training data for falls is not available Toronto Rehab Institute, University Health Network, University of Waterloo | Scientific Excellence - Advancing Knowledge | 2016-01-01 | | Factors Affecting the Implementation, Use, and Adoption of Real-Time Location System Technology for Persons Living With Cognitive Disabilities in Long-term Care Homes: Systematic ReviewJournal paper published with JMIR (Journal of Medical Internet Research)
Grigorovich A, Kulandaivelu Y, Newman K, Bianchi A, Khan SS, Iaboni A, McMurray J
Factors Affecting the Implementation, Use, and Adoption of Real-Time Location System Technology for Persons Living With Cognitive Disabilities in Long-term Care Homes: Systematic Review. J Med Internet Res 2021;23(1):e22831
DOI: 10.2196/22831
PMID: 33470949AWCRP-2020-02 Brock University, Toronto Rehab Institute, University Health Network, KITE Research Institute at University Health Network, Wilfrid Laurier University | Scientific Excellence - Advancing Knowledge | 2021-01-01 | | Real-time location systems technology in the care of older adults with cognitive impairment living in residential care: A scoping reviewIntroduction: There has been growing interest in using real-time location systems (RTLS) in residential care settings. This technology has clinical applications for locating residents within a care unit and as a nurse call system, and can also be used to gather information about movement, location, and activity over time. RTLS thus provides health data to track markers of health and wellbeing and augment healthcare decisions. To date, no reviews have examined the potential use of RTLS data in caring for older adults with cognitive impairment living in a residential care setting.
Objective: This scoping review aims to explore the use of data from real-time locating systems (RTLS) technology to inform clinical measures and augment healthcare decision-making in the care of older adults with cognitive impairment who live in residential care settings.
Methods: Embase (Ovid), CINAHL (EBSCO), APA PsycINFO (Ovid) and IEEE Xplore databases were searched for published English-language articles that reported the results of studies that investigated RTLS technologies in persons aged 50 years or older with cognitive impairment who were living in a residential care setting. Included studies were summarized, compared and synthesized according to the study outcomes.
Results: A total of 27 studies were included. RTLS data were used to assess activity levels, characterization of wandering, cognition, social interaction, and to monitor a resident’s health and wellbeing. These RTLS-based measures were not consistently validated against clinical measurements or clinically important outcomes, and no studies have examined their effectiveness or impact on decision-making.
Conclusion: This scoping review describes how data from RTLS technology has been used to support clinical care of older adults with dementia. Research efforts have progressed from using the data to track activity levels to, most recently, using the data to inform clinical decision-making and as a predictor of delirium. Future studies are needed to validate RTLS-based health indices and examine how these indices can be used to inform decision-making.AWCRP-2020-02 Toronto Rehab Institute, University Health Network, University of Toronto, Toronto Rehab Institute/University of Toronto, KITE Research Institute at University Health Network | Scientific Excellence - Advancing Knowledge | 2022-11-10 | |
|
|