Search

Introduction: Gait impairments in Parkinson's disease (PD) are treated with dopaminergic medication or deep-brain stimulation (DBS), although the magnitude of the response is variable between individuals. Computer vision-based approaches have previously been evaluated for measuring the severity of parkinsonian gait in videos, but have not been evaluated for their ability to identify changes within individuals in response to treatment. This pilot study examines whether a vision-based model, trained on videos of parkinsonism, is able to detect improvement in parkinsonian gait in people with PD in response to medication and DBS use. Methods: A spatial–temporal graph convolutional model was trained to predict MDS-UPDRS-gait scores in 362 videos from 14 older adults with drug-induced parkinsonism. This model was then used to predict MDS-UPDRS-gait scores on a different dataset of 42 paired videos from 13 individuals with PD, recorded while ON and OFF medication and DBS treatment during the same clinical visit. Statistical methods were used to assess whether the model was responsive to changes in gait in the ON and OFF states. Results: The MDS-UPDRS-gait scores predicted by the model were lower on average (representing improved gait; p = 0.017, Cohen's d = 0.495) during the ON medication and DBS treatment conditions. The magnitude of the differences between ON and OFF state was significantly correlated between model predictions and clinician annotations (p = 0.004). The predicted scores were significantly correlated with the clinician scores (Kendall's tau-b = 0.301, p = 0.010), but were distributed in a smaller range as compared to the clinician scores. Conclusion: A vision-based model trained on parkinsonian gait did not accurately predict MDS-UPDRS-gait scores in a different PD cohort, but detected weak, but statistically significant proportional changes in response to medication and DBS use. Large, clinically validated datasets of videos captured in many different settings and treatment conditions are required to develop accurate vision-based models of parkinsonian gait. [ABSTRACT FROM AUTHOR]

We introduce the Toronto Older Adults Gait Archive, a gait dataset of 14 older adults containing 2D video recordings, and 2D (video pose tracking algorithms) and 3D (inertial motion capture) joint locations of the lower body. Participants walked for 60 seconds. We also collected participants' scores on four clinical assessments of gait and balance, namely the Tinneti performance-oriented mobility assessment (POMA-gait and -balance), the Berg balance scale (BBS), and the timed-up-and-go (TUG). Three human pose tracking models (Alphapose, OpenPose, and Detectron) were used to detect body joint positions in 2D video frames and a number of gait parameters were computed using 2D video-based and 3D motion capture data. To show an example usage of our datasets, we performed a correlation analysis between the gait variables and the clinical scores. Our findings revealed that the temporal but not the spatial or variability gait variables from both systems had high correlations to clinical scores. This dataset can be used to evaluate, or to enhance vision-based pose-tracking models to the specifics of older adults' walking. Measurement(s) Lower Extremity Gait, CTCAE Technology Type(s) digital camera • Accelerometer Sample Characteristic - Organism Homo Sample Characteristic - Environment nursing home Sample Characteristic - Location City of Toronto [ABSTRACT FROM AUTHOR]

Drug-induced parkinsonism affects many older adults with dementia, often causing gait disturbances. New advances in vision-based human pose- estimation have opened possibilities for frequent and unobtrusive analysis of gait in long-term care settings. This work leverages spatial-temporal graph convolutional network (ST-GCN) architectures and training procedures to predict clinical scores of parkinsonism in gait from video of individuals with dementia. We propose a two-stage training approach consisting of a self-supervised pretraining stage that encourages the ST-GCN model to learn about gait patterns before predicting clinical scores in the finetuning stage. The proposed ST-GCN models are evaluated on joint trajectories extracted from video and are compared against traditional (ordinal, linear, random forest) regression models and temporal convolutional network baselines. Three 2D human pose-estimation libraries (OpenPose, Detectron, AlphaPose) and the Microsoft Kinect (2D and 3D) are used to extract joint trajectories of 4787 natural walking bouts from 53 older adults with dementia. A subset of 399 walks from 14 participants is annotated with scores of parkinsonism severity on the gait criteria of the Unified Parkinson's Disease Rating Scale (UPDRS) and the Simpson-Angus Scale (SAS). Our results demonstrate that ST-GCN models operating on 3D joint trajectories extracted from the Kinect consistently outperform all other models and feature sets. Prediction of parkinsonism scores in natural walking bouts of unseen participants remains a challenging task, with the best models achieving macro-averaged F1-scores of 0.53 ± 0.03 and 0.40 ± 0.02 for UPDRS-gait and SAS-gait, respectively. Pre-trained model and demo code for this work is available.1 [ABSTRACT FROM AUTHOR]

People with dementia are at risk of mobility decline. In this study, we measured changes in quantitative gait measures over a maximum 10-week period during the course of a psychogeriatric admission in older adults with dementia, with the aims to describe mobility changes over the duration of the admission, and to determine which factors were associated with this change. Fifty-four individuals admitted to a specialized dementia inpatient unit participated in this study. A vision-based markerless motion capture system was used to record participants' natural gait. Mixed effect models were developed with gait measures as the dependent variables and clinical and demographic variables as predictors. We found that gait stability, step time, and step length decreased, and step time variability and step length variability increased over 10 weeks. Gait stability of men decreased more than that of women, associated with an increased sacrum mediolateral range of motion over time. In addition, the sacrum mediolateral range of motion decreased in those with mild neuropsychiatric symptoms over 10 weeks, but increased in those with more severe neuropsychiatric symptoms. Our study provides evidence of worsening of gait mechanics and control over the course of a hospitalization in older adults with dementia. Quantitative gait monitoring in hospital environments may provide opportunities to intervene to prevent adverse events, decelerate mobility decline, and monitor rehabilitation outcomes. [ABSTRACT FROM AUTHOR]

Background: Many of the available gait monitoring technologies are expensive, require specialized expertise, are time consuming to use, and are not widely available for clinical use. The advent of video-based pose tracking provides an opportunity for inexpensive automated analysis of human walking in older adults using video cameras. However, there is a need to validate gait parameters calculated by these algorithms against gold standard methods for measuring human gait data in this population.Methods: We compared quantitative gait variables of 11 older adults (mean age = 85.2) calculated from video recordings using three pose trackers (AlphaPose, OpenPose, Detectron) to those calculated from a 3D motion capture system. We performed comparisons for videos captured by two cameras at two different viewing angles, and viewed from the front or back. We also analyzed the data when including gait variables of individual steps of each participant or each participant's averaged gait variables.Results: Our findings revealed that, i) temporal (cadence and step time), but not spatial and variability gait measures (step width, estimated margin of stability, coefficient of variation of step time and width), calculated from the video pose tracking algorithms correlate significantly to that of motion capture system, and ii) there are minimal differences between the two camera heights, and walks viewed from the front or back in terms of correlation of gait variables, and iii) gait variables extracted from AlphaPose and Detectron had the highest agreement while OpenPose had the lowest agreement.Conclusions: There are important opportunities to evaluate models capable of 3D pose estimation in video data, improve the training of pose-tracking algorithms for older adult and clinical populations, and develop video-based 3D pose trackers specifically optimized for quantitative gait measurement. [ABSTRACT FROM AUTHOR]

Background: Impairments of gait and balance often progress through the course of dementia, and are associated with increased risk of falls. Summary: This systematic review provides a critical analysis of the evidence linking quantitative measures of gait and balance to fall risk in older adults with dementia. Various instrumented measures of gait and postural stability including gait speed and non-instrumented performance measures including Timed Up and Go were shown to be capable of distinguishing fallers from non-fallers. Key Messages: Existing reviews indicate that impairments of gait and balance are associated with increased risk of falls in cognitively intact older people. There are inconsistencies, however, regarding the characteristics most predictive of a fall. In order to advance fall prevention efforts, there is an important need to understand the relationship between gait, balance, and fall risk, particularly in high-risk populations such as individuals with dementia. [ABSTRACT FROM AUTHOR]

This paper presents a study to evaluate the concurrent validity of the Microsoft Kinect for Windows v2 for measuring the spatiotemporal parameters of gait. Twenty healthy adults performed several sequences of walks across a GAITRite mat under three different conditions: usual pace, fast pace, and dual task. Each walking sequence was simultaneously captured with two Kinect for Windows v2 and the GAITRite system. An automated algorithm was employed to extract various spatiotemporal features including stance time, step length, step time and gait velocity from the recorded Kinect v2 sequences. Accuracy in terms of reliability, concurrent validity and limits of agreement was examined for each gait feature under different walking conditions. The 95% Bland–Altman limits of agreement were narrow enough for the Kinect v2 to be a valid tool for measuring all reported spatiotemporal parameters of gait in all three conditions. An excellent intraclass correlation coefficient ( ICC 2, 1 ) ranging from 0.9 to 0.98 was observed for all gait measures across different walking conditions. The inter trial reliability of all gait parameters were shown to be strong for all walking types ( ICC 3, 1 > 0.73). The results of this study suggest that the Kinect for Windows v2 has the capacity to measure selected spatiotemporal gait parameters for healthy adults. [ABSTRACT FROM AUTHOR]

This article presents a single case study on the feasibility of using a low-cost and portable vision-based system (a Microsoft Kinect sensor) to monitor changes in movement patterns before and after a total hip replacement surgery. The primary subject was an older male adult with total hip replacement who performed two different functional tasks: walking and sit-to-stand. The tasks were recorded with a Kinect multiple times, starting from 1 d before the surgery until 9 wk after the surgery. An automated algorithm has been developed to extract the important spatiotemporal characteristics from the video recorded functional tasks (walking and sit-to-stand). Statistical analysis was then performed by Tryon C statistic to study changes in spatiotemporal characteristics between different stages before and after the surgery. The statistical analysis indicated significant difference and slight improvement between all measures from the presurgery to each postsurgery date. The study confirmed that the Kinect sensor and an automated algorithm have the potential to be integrated into a patient’s home to monitor changes in mobility during the recovery period. [ABSTRACT FROM AUTHOR]

Highlights • Vision-based pose-tracking sensors were used for the assessment of gait over time. • Installation in a dementia unit was feasible and acceptable with a high recruitment rate. • Spatiotemporal measures of gait and their variability were extracted from sensor data. Abstract Background Gait and balance functions decline through the course of dementia, and can serve as a marker of changes in physical status and falls risk. We have developed a technology (AMBIENT), based on a vision-based sensor, which enables the frequent, accurate, and unobtrusive measurement of gait and balance. Objective The objective of this study was to examine the feasibility of using AMBIENT technology for frequent assessment of mobility in people with dementia within an inpatient setting. In particular, we examined technical feasibility, and the feasibility of participant recruitment, data collection and analysis. Methods AMBIENT was installed in a specialized dementia inpatient unit. AMBIENT captured gait bouts as the participants walked within the view of the sensor during their daily routine and computed the spatiotemporal parameters of gait. Results Twenty participants (age: 76.9 ± 6.7 years, female: 50%) were recruited over a period of 6 months. We recorded a total of 3843 gait bouts, of which 1171 could be used to extract gait data. On average, 58 ± 47 walking sequences per person were collected over a recording period of 28 ± 20 days. We were able to consistently extract six quantitative parameters of gait, consisting of stride length, stride time, cadence, velocity, step length asymmetry, and step time asymmetry. Significance This study demonstrates the feasibility of longitudinal tracking of gait in a dementia inpatient setting. This technology has important potential applications in monitoring functional status over time, and the development of dynamic falls risk assessments. [ABSTRACT FROM AUTHOR]

To develop a prognostic model to predict the probability of a short-term fall (within the next 7 to 30 days) in older adults with dementia. Prospective observational study. Fifty-one individuals with dementia at high risk of falls from a specialized dementia inpatient unit. Clinical and demographic measures were collected and a vision-based markerless motion capture was used to record the natural gait of participants over a 2-week baseline. Falls were tracked throughout the length of stay. Cox proportional hazard regression analysis was used to build a prognostic model to determine fall-free survival probabilities at 7 days and at 30 days. The model's discriminative ability was also internally validated. Fall history and gait stability (estimated margin of stability) were statistically significant predictors of time to fall and included in the final prognostic model. The model's predicted survival probabilities were close to observed values at both 7 and 30 days. The area under the receiver operating curve was 0.80 at 7 days, and 0.67 at 30 days and the model had a discrimination performance (the Harrel concordance index) of 0.71. Our short-term falls risk model had fair to good predictive and discrimination ability. Gait stability and recent fall history predicted an imminent fall in our population. This provides some preliminary evidence that the degree of gait instability may be measureable in natural everyday gait to allow dynamic falls risk monitoring. External validation of the model using a separate data set is needed to evaluate model's predictive performance. [ABSTRACT FROM AUTHOR]

Measures of gait center of pressure (COP) can be recorded using simple available technologies in clinical settings and thus can be used to characterize gait quality in older adults and its relationship to falls. The aim of this systematic review was to investigate the association between measures of gait COP and aging and falls. A comprehensive search of electronic databases including MEDLINE, Embase, Cochrane Central Register of Controlled Trials, CINAHL (EBSCO), Ageline (EBSCO) and Scopus was performed. The initial search yielded 2809 papers. After removing duplicates and applying study inclusion/exclusion criteria, 34 papers were included in the review. Gait COP has been examined during three tasks: normal walking, gait initiation, and obstacle negotiation. The majority of studies examined mean COP position and velocity as outcome measures. Overall, gait in older adults was characterized by more medial COP trajectory in normal walking and lower average anterior-posterior and medio-lateral COP displacements and velocity in both gait initiation and obstacle crossing. Moreover, findings suggest that Tai chi training can enhance older adults' balance control during gait initiation as demonstrated by greater COP backward, medial and forward shift in all three phases of gait initiation. These findings should be interpreted cautiously due to inadequacy of evidence as well as methodological limitations of the studies such as small sample size, limited numbers of 'fallers', lack of a control group, and lack of interpretation of COP outcomes with respect to fall risk. COP measures can be adopted to assess fall-related gait changes in older adults but more complex measures of COP that reveal the dynamic nature of COP behavior in step-to-step variations are needed to adequately characterize gait changes in older adults. • A review was done to examine how COP was characterized in older adults' walking. • Gait COP is examined during normal walking, gait initiation, and obstacle crossing. • Mean COP position and velocity were the most common COP measures. [ABSTRACT FROM AUTHOR]