Sina Mehdizadeh1, Elham Dolatabadi1,2, Kimberley-Dale Ng1,3, Avril Mansfield1,4,5, Alastair Flint6,7, Babak Taati1,2,3,8, Andrea Iaboni1,6,7. 1. Toronto Rehabilitation Institute, University Health Network, Ontario, Canada. 2. Vector Institute for Artificial Intelligence, Toronto, Ontario, Canada. 3. Institute of Biomaterials and Biomedical Engineering, University of Toronto, Ontario, Canada. 4. Evaluative Clinical Sciences, Hurvitz Brain Sciences Program, Sunnybrook Research Institute, Toronto, Ontario, Canada. 5. Department of Physical Therapy, University of Toronto, Ontario, Canada. 6. Department of Psychiatry, University of Toronto, Ontario, Canada. 7. Centre for Mental Health, University Health Network, Toronto, Ontario, Canada. 8. Department of Computer Science, University of Toronto, Ontario, Canada.
Abstract
BACKGROUND: Gait impairments contribute to falls in people with dementia. In this study, we used a vision-based system to record episodes of walking over a 2-week period as participants moved naturally around their environment, and from these calculated spatiotemporal, stability, symmetry, and acceleration gait features. The aim of this study was to determine whether features of gait extracted from a vision-based system are associated with falls, and which of these features are most strongly associated with falling. METHODS: Fifty-two people with dementia admitted to a specialized dementia unit participated in this study. Thirty different features describing baseline gait were extracted from Kinect recordings of natural gait over a 2-week period. Baseline clinical and demographic measures were collected, and falls were tracked throughout the participants' admission. RESULTS: A total of 1,744 gait episodes were recorded (mean 33.5 ± 23.0 per participant) over a 2-week baseline period. There were a total of 78 falls during the study period (range 0-10). In single variable analyses, the estimated lateral margin of stability, step width, and step time variability were significantly associated with the number of falls during admission. In a multivariate model controlling for clinical and demographic variables, the estimated lateral margin of stability (p = .01) was remained associated with number of falls. CONCLUSIONS: Information about gait can be extracted from vision-based recordings of natural walking. In particular, the lateral margin of stability, a measure of lateral gait stability, is an important marker of short-term falls risk.
BACKGROUND: Gait impairments contribute to falls in people with dementia. In this study, we used a vision-based system to record episodes of walking over a 2-week period as participants moved naturally around their environment, and from these calculated spatiotemporal, stability, symmetry, and acceleration gait features. The aim of this study was to determine whether features of gait extracted from a vision-based system are associated with falls, and which of these features are most strongly associated with falling. METHODS: Fifty-two people with dementia admitted to a specialized dementia unit participated in this study. Thirty different features describing baseline gait were extracted from Kinect recordings of natural gait over a 2-week period. Baseline clinical and demographic measures were collected, and falls were tracked throughout the participants' admission. RESULTS: A total of 1,744 gait episodes were recorded (mean 33.5 ± 23.0 per participant) over a 2-week baseline period. There were a total of 78 falls during the study period (range 0-10). In single variable analyses, the estimated lateral margin of stability, step width, and step time variability were significantly associated with the number of falls during admission. In a multivariate model controlling for clinical and demographic variables, the estimated lateral margin of stability (p = .01) was remained associated with number of falls. CONCLUSIONS: Information about gait can be extracted from vision-based recordings of natural walking. In particular, the lateral margin of stability, a measure of lateral gait stability, is an important marker of short-term falls risk.
Authors: Kimberley-Dale Ng; Sina Mehdizadeh; Andrea Iaboni; Avril Mansfield; Alastair Flint; Babak Taati Journal: IEEE J Transl Eng Health Med Date: 2020-05-28 Impact factor: 3.316