Detailed and formatted blog posts prior to April 2014 can be found in the following locations:

Using Kinect v2 to Control a Laser Visual Cue System to Improve the Mobility during Freezing of Gait in Parkinson’s Disease.

Journal of Healthcare Engineering. 2019 Feb 20;2019:3845462.

Amini A, Banitsas K

Link to article

Abstract

Different auditory and visual cues have been proven to be very effective in improving the mobility of people with Parkinson’s (PwP). Nonetheless, many of the available methods require user intervention and so on to activate the cues. Moreover, once activated, these systems would provide cues continuously regardless of the patient’s needs. This research proposes a new indoor method for casting dynamic/automatic visual cues for PwP based on their head direction and location in a room. The proposed system controls the behavior of a set of pan/tilt servo motors and laser pointers, based on the real-time skeletal information acquired from a Kinect v2 sensor. This produces an automatically adjusting set of laser lines that can always be in front of the patient as a guideline for where the next footstep would be placed. A user interface was also created that enables users to control and adjust the settings based on the preferences. The aim of this research was to provide PwP with an unobtrusive/automatic indoor system for improving their mobility during a Freezing of gait (FOG) incident. The results showed the possibility of employing such system, which does not rely on the subject’s input nor does it introduce any additional complexities to operate.

Posted in Kinect | Tagged , | Leave a comment

The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy.

Sensors (Basel). 2019 Apr 7;19(7)

Ma Y, Mithraratne K, Wilson NC, Wang X, Ma Y, Zhang Y.

Link to article

Abstract

The aim of this study is to evaluate if Kinect is a valid and reliable clinical gait analysis tool for children with cerebral palsy (CP), and whether linear regression and long short-term memory (LSTM) recurrent neural network methods can improve its performance. A gait analysis was conducted on ten children with CP, on two occasions. Lower limb joint kinematics computed from the Kinect and a traditional marker-based Motion Analysis system were investigated by calculating the root mean square errors (RMSE), the coefficients of multiple correlation (CMC), and the intra-class correlation coefficients (ICC2,k). Results showed that the Kinect-based kinematics had an overall modest to poor correlation (CMC-less than 0.001 to 0.70) and an angle pattern similarity with Motion Analysis. After the calibration, RMSE on every degree of freedom decreased. The two calibration methods indicated similar levels of improvement in hip sagittal (CMC-0.81 ± 0.10 vs. 0.75 ± 0.22)/frontal (CMC-0.41 ± 0.35 vs. 0.42 ± 0.37) and knee sagittal kinematics (CMC-0.85±0.07 vs. 0.87 ± 0.12). The hip sagittal (CMC-0.97±0.05) and knee sagittal (CMC-0.88 ± 0.12) angle patterns showed a very good agreement over two days. Modest to excellent reliability (ICC2,k-0.45 to 0.93) for most parameters renders it feasible for observing ongoing changes in gait kinematics.

KEYWORDS:

Kinect; cerebral palsy; gait analysis; kinematics; reliability; validity

Posted in Kinect | Leave a comment

Reliability and validity of the Kinect V2 for the assessment of lower extremity rehabilitation exercises.

Gait & Posture. 2019 Mar 26;70:330-335  [Epub ahead of print]

Wochatz M, Tilgner N, Mueller S, Rabe S, Eichler S, John M, Völler H, Mayer F.

Link to article

Abstract

BACKGROUND:

Besides its initial use as a video gaming system the Kinect might also be suitable to capture human movements in the clinical context. However, the system’s reliability and validity to capture rehabilitation exercises is unclear.

RESEARCH QUESTION:

The purpose of this study was to evaluate the test-retest reliability of lower extremity kinematics during squat, hip abduction and lunge exercises captured by the Kinect and to evaluate the agreement to a reference 3D camera-based motion system.

METHODS:

Twenty-one healthy individuals performed five repetitions of each lower limb exercise on two different days. Movements were simultaneously assessed by the Kinect and the reference 3D motion system. Joint angles and positions of the lower limb were calculated for sagittal and frontal plane. For the inter-session reliability and the agreement between the two systems standard error of measurement (SEM), bias with limits of agreement (LoA) and Pearson Correlation Coefficient (r) were calculated.

RESULTS:

Parameters indicated varying reliability for the assessed joint angles and positions and decreasing reliability with increasing task complexity. Across all exercises, measurement deviations were shown especially for small movement amplitudes. Variability was acceptable for joint angles and positions during the squat, partially acceptable during the hip abduction and predominately inacceptable during the lunge. The agreement between systems was characterized by systematic errors. Overestimations by the Kinect were apparent for hip flexion during the squat and hip abduction/adduction during the hip abduction exercise as well as for the knee positions during the lunge. Knee and hip flexion during hip abduction and lunge were underestimated by the Kinect.

SIGNIFICANCE:

The Kinect system can reliably assess lower limb joint angles and positions during simple exercises. The validity of the system is however restricted. An application in the field of early orthopedic rehabilitation without further development of post-processing techniques seems so far limited.

KEYWORDS:

Agreement; Markerless motion capture system; Reproducibility; Telerehabilitation

Posted in Kinect | Leave a comment

Study: Reflexion Health Virtual Therapy System Reduces Rehab Costs

Reflexion Health, which has developed a “virtual physical therapy” system for patients recovering from surgery, said results from a randomized controlled clinical trial completed by nearly 300 people showed patients who used the technology saved the healthcare industry an average of $2,745 compared to those who underwent traditional physical therapy.

Link

Posted in Kinect, Media/News | Leave a comment

Effect of the Wii Sports Resort on the improvement in attention, processing speed and working memory in moderate stroke.

J Neuroeng Rehabil. 2019 Feb 28;16(1):32

Unibaso-Markaida I1Iraurgi I2Ortiz-Marqués N2Amayra I2Martínez-Rodríguez S2.

Link

Abstract

BACKGROUND:

Stroke is the most common neurological disease in the world. After the stroke, some people suffer a cognitive disability. Commercial videogames have been used after stroke for physical rehabilitation; however, their use in cognitive rehabilitation has hardly been studied. The objectives of this study were to analyze attention, processing speed, and working memory in patients with moderate stroke after an intervention with Wii Sports Resort and compared these results with a control group.

METHODS:

A pre-post design study was conducted with 30 moderate stroke patients aged 65 ± 15. The study lasted eight weeks. 15 participated in the intervention group and 15 belong to the control group. They were assessed in attention and processing speed (TMT-A and B) and working memory (Digit Span of WAIS-III). Parametric and effect size tests were used to analyze the improvement of those outcomes and compared both groups.

RESULTS:

At the baseline, there was no difference between TMT-A and B. A difference was found in the scalar score of TMT-B, as well as in Digit Backward Span and Total Digit Task. In TMT-A and B, the intervention group had better scores than the control group. The intervention group in the Digit Forward Span and the Total Digit obtained a moderate effect size and the control group also obtained a moderate effect size in Total Digit. In the Digit scalar scores, the control group achieved better results than the intervention group.

CONCLUSIONS:

The results on attention, processing speed and working memory improved in both groups. However, according to the effect sizes, the intervention group achieved better results than the control group. In addition, the attention and processing speed improved more than the working memory after the intervention. Although more studies are needed in this area, the results are encouraging for cognitive rehabilitation after stroke.

KEYWORDS:

Attention; Cognition; Moderate stroke; Nintendo Wii sports resort; Processing speed; Working memory

Posted in Wii | Tagged , , | Leave a comment

Virtual Rehabilitation through Nintendo Wii in Poststroke Patients: Follow-Up.

Journal of Stroke Cerebrovascular Disease. 2018 Feb;27(2):494-498.

Authors – Carregosa A, Aguiar Dos Santos LR, Masruha MR, Coêlho MLDS, Machado TC, Souza DCB, Passos GLL, Fonseca EP, Ribeiro NMDS, de Souza Melo A.

Link

Abstract


Abstract
OBJECTIVE:
To evaluate in the follow-up the sensory-motor recovery and quality of life patients 2 months after completion of the Nintendo Wii console intervention and determine whether learning retention was obtained through the technique.

METHODS:
Five hemiplegics patients participated in the study, of whom 3 were male with an average age of 54.8 years (SD = 4.6). Everyone practiced Nintendo Wii therapy for 2 months (50 minutes/day, 2 times/week, during 16 sessions). Each session lasting 60 minutes, under a protocol in which only the games played were changed, plus 10 minutes of stretching. In the first session, tennis and hula hoop games were used; in the second session, football (soccer) and boxing were used. For the evaluation, the Fulg-Meyer and Short Form Health Survey 36 (SF-36) scales were utilized. The patients were immediately evaluated upon the conclusion of the intervention and 2 months after the second evaluation (follow-up).

RESULTS:
Values for the upper limb motor function sub-items and total score in the Fugl-Meyer scale evaluation and functional capacity in the SF-36 questionnaire were sustained, indicating a possible maintenance of the therapeutic effects.

CONCLUSION:
The results suggest that after Nintendo Wii therapy, patients had motor learning retention, achieving a sustained benefit through the technique.

Copyright © 2018 National Stroke Association. Published by Elsevier Inc. All rights reserved.

Posted in Wii | Tagged , , | Leave a comment

Validation of a Kinect V2 based rehabilitation game

Mengxuan M, Rachel Proffitt , Marjorie Skubic

PLoS One. 2018; 13(8): (August 24, 2018)

Link

Abstract


Abstract

Interactive technologies are beneficial to stroke recovery as rehabilitation interventions; however, they lack evidence for use as assessment tools. Mystic Isle is a multi-planar fullbody rehabilitation game developed using the Microsoft Kinect® V2. It aims to help stroke patients improve their motor function and daily activity performance and to assess the motions of the players. It is important that the assessment results generated from Mystic Isle are accurate. The Kinect V2 has been validated for tracking lower limbs and calculating gait-specific parameters. However, few studies have validated the accuracy of the Kinect® V2 skeleton model in upper-body movements. In this paper, we evaluated the spatial accuracy and measurement validity of a Kinect-based game Mystic Isle in comparison to a goldstandard optical motion capture system, the Vicon system. Thirty participants completed six trials in sitting and standing. Game data from the Kinect sensor and the Vicon system were recorded simultaneously, then filtered and sample rate synchronized. The spatial accuracy was evaluated using Pearson’s r correlation coefficient, signal to noise ratio (SNR) and 3D distance difference. Each arm-joint signal had an average correlation coefficient above 0.9 and a SNR above 5. The hip joints data had less stability and a large variation in SNR. Also, the mean 3D distance difference of joints were less than 10 centimeters. For measurement validity, the accuracy was evaluated using mean and standard error of the difference, percentage error, Pearson’s r correlation coefficient and intra-class correlation (ICC). Average errors of maximum hand extent of reach were less than 5% and the average errors of mean and maximum velocities were about 10% and less than 5%, respectively. We have demonstrated that Mystic Isle provides accurate measurement and assessment of movement relative to the Vicon system.

Posted in Kinect | Tagged , , , , | Comments Off on Validation of a Kinect V2 based rehabilitation game

Effects of virtual reality training using Nintendo Wii and treadmill walking exercise on balance and walking for stroke patients.

J Phys Ther Sci. 2016 Nov;28(11):3112-3115.

Bang YS1, Son KH2, Kim HJ2.

Link

Abstract

[Purpose] The purpose of this study is to investigate the effects of virtual reality training using Nintendo Wii on balance and walking for stroke patients. [Subjects and Methods] Forty stroke patients with stroke were randomly divided into two exercise program groups: virtual reality training (n=20) and treadmill (n=20). The subjects underwent their 40-minute exercise program three times a week for eight weeks. Their balance and walking were measured before and after the complete program. We measured the left/right weight-bearing and the anterior/posterior weight-bearing for balance, as well as stance phase, swing phase, and cadence for walking. [Results] For balance, both groups showed significant differences in the left/right and anterior/posterior weight-bearing, with significant post-program differences between the groups. For walking, there were significant differences in the stance phase, swing phase, and cadence of the virtual reality training group. [Conclusion] The results of this study suggest that virtual reality training providing visual feedback may enable stroke patients to directly adjust their incorrect weight center and shift visually. Virtual reality training may be appropriate for patients who need improved balance and walking ability by inducing their interest for them to perform planned exercises on a consistent basis.

 

Posted in Wii | Tagged , , | Comments Off on Effects of virtual reality training using Nintendo Wii and treadmill walking exercise on balance and walking for stroke patients.

Upper extremity movement reliability and validity of the Kinect version 2

Link

Purpose: Studies have shown that marker-less motion detection systems, such as the first generation Kinect (Kinect 1), have good reliability and potential for clinical application. Studies of the second generation Kinect (Kinect 2) have shown a large range of accuracy relative to balance and joint localization; however, few studies have investigated the validity and reliability of the Kinect 2 for upper extremity motion. This investigation compared reliability and validity among the Kinect 1, Kinect 2 and a video motion capture (VMC) system for upper extremity movements.

Design: One healthy, adult male performed six upper extremity movements during two separate sessions. All movements were recorded on the Kinect 1, Kinect 2 and VMC simultaneously. Data were analyzed using MATLAB (Natick, MA), Microsoft Excel (Redmond, WA), and SPSS (Armonk, NY).

Results: Results indicated good reliability for both Kinects within a day; results between days were inconclusive for both devices due to the inability to exactly repeat the desired movements. Range of motion (ROM) magnitudes for both Kinects were different from the VMC, yet patterns of motion were very highly correlated for both devices.

Conclusion: Simple transformations of Kinect data could bring magnitudes in line with those of the VMC, allowing the Kinects to be used in a clinical setting.

  • Implications for Rehabilitation
  • The clinical implications of the investigation support the notion that the Kinects could be used in the clinical setting if an understanding of their limitations exists.

  • Using the Kinects to make assessments with a given data collection session is acceptable. Using the Kinects to make comparisons across different days such as before or after an intervention should be approached with caution.

  • The Kinect 2 provides a more cost effective option compared to the VMC. Additionally, the Kinect is more portable, requires less time to set-up, and takes up less space, thus increasing its overall usability compared to the VMC.

Posted in Kinect | Tagged , , , | Leave a comment

Using data from the Microsoft Kinect 2 to determine postural stability in healthy subjects: A feasibility trial

Dehbandi B, Barachant A, Smeragliuolo AH, Long JD, Bumanlag SJ, He V, et al. (2017) Using data from the Microsoft Kinect 2 to determine postural stability in healthy subjects: A feasibility trial. PLoS ONE 12(2): e0170890. doi:10.1371/journal.pone.0170890

Link

Abstract

The objective of this study was to determine whether kinematic data collected by the Microsoft Kinect 2 (MK2) could be used to quantify postural stability in healthy subjects. Twelve subjects were recruited for the project, and were instructed to perform a sequence of simple postural stability tasks. The movement sequence was performed as subjects were seated on top of a force platform, and the MK2 was positioned in front of them. This sequence of tasks was performed by each subject under three different postural conditions: “both feet on the ground” (1), “One foot off the ground” (2), and “both feet off the ground” (3). We compared force platform and MK2 data to quantify the degree to which the MK2 was returning reliable data across subjects. We then applied a novel machine-learning paradigm to the MK2 data in order to determine the extent to which data from the MK2 could be used to reliably classify different postural conditions. Our initial comparison of force plate and MK2 data showed a strong agreement between the two devices, with strong Pearson correlations between the trunk centroids “Spine_Mid” (0.85 ± 0.06), “Neck” (0.86 ± 0.07) and “Head” (0.87 ± 0.07), and the center of pressure centroid inferred by the force platform. Mean accuracy for the machine learning classifier from MK2 was 97.0%, with a specific classification accuracy breakdown of 90.9%, 100%, and 100% for conditions 1 through 3, respectively. Mean accuracy for the machine learning classifier derived from the force platform data was lower at 84.4%. We conclude that data from the MK2 has sufficient information content to allow us to classify sequences of tasks being performed under different levels of postural stability. Future studies will focus on validating this protocol on large populations of individuals with actual balance impairments in order to create a toolkit that is clinically validated and available to the medical community.

Posted in Kinect | Tagged , , , | Leave a comment