Dataset Information

Concurrent Validity of Zeno Instrumented Walkway and Video-Based Gait Features in Adults With Parkinson's Disease.

ABSTRACT:

Background

Parkinson's disease (PD) presents with motor symptoms such as bradykinesia, rigidity, and tremor that can affect gait. To monitor changes associated with disease progression or medication use, quantitative gait assessment is often performed during clinical visits. Conversely, vision-based solutions have been proposed for monitoring gait quality in non-clinical settings.

Methods

We use three 2D human pose-estimation libraries (AlphaPose, Detectron, OpenPose) and one 3D library (ROMP) to calculate gait features from color video, and correlate them with those extracted by a Zeno instrumented walkway in older adults with PD. We calculate video-based gait features using a manual and automated heel-strike detection algorithm, and compare the correlations when the participants walk towards and away from the camera separately.

Results

Based on analysis of 67 bidirectional walking bouts from 25 adults with PD, moderate to strong positive correlations were identified between the number of steps, cadence, as well as the mean and coefficient of variation of step width calculated from Zeno and video using 2D pose-estimation libraries. We noted that our automated heel-strike annotation method struggled to identify short steps.

Conclusion

Gait features calculated from 2D joint trajectories are more strongly correlated with the Zeno than analogous gait features calculated from ROMP. Based on our analysis, videos processed with 2D pose-estimation libraries can be used for longitudinal gait monitoring in individuals with PD. Future work will seek to improve the prediction of gait features using a comprehensive machine learning model to predict gait features directly from color video without relying on intermediate extraction of joint trajectories.

SUBMITTER: Sabo A

PROVIDER: S-EPMC9252334 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Walking ability is frequently assessed with the 10-meter walking test (10MWT), which may be instrumented with multiple Kinect v2 sensors to complement the typical stopwatch-based time to walk 10 meters with quantitative gait information derived from Kinect's 3D body point's time series. The current study aimed to evaluate a multi-Kinect v2 set-up for quantitative gait assessments during the 10MWT against a gold-standard motion-registration system by determining between-systems agreement for body point's time series, spatiotemporal gait parameters and the time to walk 10 meters. To this end, the 10MWT was conducted at comfortable and maximum walking speed, while 3D full-body kinematics was concurrently recorded with the multi-Kinect v2 set-up and the Optotrak motion-registration system (i.e., the gold standard). Between-systems agreement for body point's time series was assessed with the intraclass correlation coefficient (ICC). Between-systems agreement was similarly determined for the gait parameters' walking speed, cadence, step length, stride length, step width, step time, stride time (all obtained for the intermediate 6 meters) and the time to walk 10 meters, complemented by Bland-Altman's bias and limits of agreement. Body point's time series agreed well between the motion-registration systems, particularly so for body points in motion. For both comfortable and maximum walking speeds, the between-systems agreement for the time to walk 10 meters and all gait parameters except step width was high (ICC ≥ 0.888), with negligible biases and narrow limits of agreement. Hence, body point's time series and gait parameters obtained with a multi-Kinect v2 set-up match well with those derived with a gold standard in 3D measurement accuracy. Future studies are recommended to test the clinical utility of the multi-Kinect v2 set-up to automate 10MWT assessments, thereby complementing the time to walk 10 meters with reliable spatiotemporal gait parameters obtained objectively in a quick, unobtrusive and patient-friendly manner.

Project description:ImportanceRegaining the ability to walk safely is a high priority for adults with vestibular loss. Thus, practitioners need comprehensive knowledge of vestibulopathic gait to design, provide, and/or interpret outcomes of interventions. To date, few studies have characterized the effects of vestibular loss on gait.ObjectivesTo investigate the use of an instrumented 2-minute walk test in adults with vestibular loss, to further characterize vestibulopathic gait, and to assess whether those with chronic vestibular loss have enduring gait deficits.Design, setting, and participantsThis cross-sectional study, conducted between April 3, 2018, and June 27, 2019, recruited adults 20 to 79 years of age from an academic, tertiary, hospital-based, ambulatory care setting who were healthy or had confirmed unilateral or bilateral vestibular hypofunction. Of the 43 adults who were screened from convenience and referred samples, 2 declined, and 7 were excluded because of health conditions.ExposuresThe main exposure was the instrumented 2-minute walk test, which was conducted with participants using wearable inertial measurement units while they walked a 10-m path at their self-selected speed and turned 180° in their self-selected direction at either end.Main outcomes and measuresThe primary measures were spatiotemporal gait metrics (eg, stride length [SL] and peak whole-body turning velocity). Multivariate analysis of variance was used to assess between-group differences. Validity was assessed using the area under the curve from receiver operator characteristic analyses.ResultsData from 17 healthy adults (mean [SD] age, 39.27 [11.20] years; 13 [76%] female) and 13 adults with vestibular loss (mean [SD] age, 60.50 [10.81] years; 6 [46%] female) were analyzed. Very large between-group differences were found for SL (left) (estimated marginal mean [SE] for healthy vs vestibular groups, 1.47 [0.04] m vs 1.31 [0.04] m; Cohen d, 1.35; 95% CI, 0.18-2.52), SL (right) (estimated marginal mean [SE] for healthy vs vestibular groups, 1.46 [0.04] m vs 1.29 [0.04] m; Cohen d, 1.44; 95% CI, 0.25-2.62), and peak turn velocity (estimated marginal mean [SE] for healthy vs vestibular groups, 240.17 [12.78]°/s vs 189.74 [14.70]°/s; Cohen d, 1.23; 95% CI, 0.07-2.40). The area under the curve was 0.79 (95% CI, 0.62-0.95) for SL (left), 0.81 (95% CI, 0.64-0.97) for SL (right), and 0.86 (95% CI, 0.72-0.99) for peak turn velocity.Conclusions and relevanceIn this cross-sectional study, instrumented gait analysis had good discriminative validity and revealed persistent deficits in gait stability in those with chronic vestibular loss. The findings of this study suggest that these clinically and functionally meaningful deficits could be targets for vestibular rehabilitation.

Project description:BackgroundWalking speed is used to assess functional status, predict recovery, prescribe exercise, and track functional progress after stroke. Determining concurrent validity ensures that results from different tests of walking speed can be compared or used interchangeably. The GAITRite electronic walkway and the 10-m walk test (10MWT) are popular measurement tools of walking speed in the laboratory and in clinical settings, respectively.Research questionDo walking speeds in chronic stroke survivors measured with the 10-m walk test and GAITRite electronic walkway demonstrate concurrent validity?Methods77 participants with chronic stroke performed four trials of 10MWT and four trials of GAITRite-two trials at comfortable walking speed and two trials at maximal walking speed. Intraclass correlations [ICC (3,1), absolute agreement] and Bland-Altman plots were used to assess the relationship between gait speed from these two measures.ResultsWalking speed showed poor to good absolute agreement between 10MWT and GAITRite for comfortable walking speed [ICC: 0.77 (95% CI: 0.46, 0.89; P < 0.001)] and excellent absolute agreement for maximal walking speed [ICC: 0.94 (95% CI: 0.91, 0.96; P < 0.001)]. Mean difference value (systematic bias) was different from 0 for comfortable walking [10MWT was faster; P < 0.001 (95% CI: 0.05, 0.10)] but not for maximal walking [P = 0.16 (95% CI: -0.01, 0.04)]. Limits of agreement were broad (comfortable walking speed, 0.43; maximal walking speed, 0.37), and there was proportional bias at both speeds whereby participants who walked faster tended to have a faster walking speed during 10MWT vs. GAITRite (comfortable walking speed, R2 = 0.22, P < 0.001; maximal walking speed, R2 = 0.08, P = 0.01).SignificanceSystematic bias, proportional bias, and broad limits of agreement suggest that caution should be used when comparing walking speeds from 10MWT and GAITRite. It may not be appropriate to use them interchangeably. Conducting 10MWT and GAITRite tests at maximal walking speeds may allow more accurate comparisons between measures.