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

Wochatz, Monique; Tilgner, Nina; Mueller, Steffen; Rabe, Sophie; Eichler, Sarah; John, Mathias; Völler, Heinz; Mayer, Frank

doi:10.1016/j.gaitpost.2019.03.020

Cited by 44 publications

(40 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, as institutions integrate telemedicine into their practices, it will be important to provide exposure to this new technology in a graduated fashion. When possible, institutional adoption of telemedicine should include training on the differences between telemedicine and in-person visits, simulated visits, exposure of house staff to telemedicine and accounting for an “adjustment phase” for new providers [ 6 , 7 , 16 ], similar to the steps taken when onboarding a new provider to the practice.…”

Section: Discussionmentioning

confidence: 99%

Provider confidence in the telemedicine spine evaluation: results from a global study

et al. 2020

View full text Add to dashboard Cite

Purpose To utilize data from a global spine surgeon survey to elucidate (1) overall confidence in the telemedicine evaluation and (2) determinants of provider confidence. Methods Members of AO Spine International were sent a survey encompassing participant’s experience with, perception of, and comparison of telemedicine to in-person visits. The survey was designed through a Delphi approach, with four rounds of question review by the multi-disciplinary authors. Data were stratified by provider age, experience, telemedicine platform, trust in telemedicine, and specialty. Results Four hundred and eighty-five surgeons participated in the survey. The global effort included respondents from Africa (19.9%), Asia Pacific (19.7%), Europe (24.3%), North America (9.4%), and South America (26.6%). Providers felt that physical exam-based tasks (e.g., provocative testing, assessing neurologic deficits/myelopathy, etc.) were inferior to in-person exams, while communication-based aspects (e.g., history taking, imaging review, etc.) were equivalent. Participants who performed greater than 50 visits were more likely to believe telemedicine was at least equivalent to in-person visits in the ability to make an accurate diagnosis (OR 2.37, 95% C.I. 1.03–5.43). Compared to in-person encounters, video (versus phone only) visits were associated with increased confidence in the ability of telemedicine to formulate and communicate a treatment plan (OR 3.88, 95% C.I. 1.71–8.84). Conclusion Spine surgeons are confident in the ability of telemedicine to communicate with patients, but are concerned about its capacity to accurately make physical exam-based diagnoses. Future research should concentrate on standardizing the remote examination and the development of appropriate use criteria in order to increase provider confidence in telemedicine technology.

show abstract

Section: Discussionmentioning

confidence: 99%

Provider confidence in the telemedicine spine evaluation: results from a global study

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Our experiment is based on Kinect version 2.0, which provides pose estimations for 25 "skeleton" joints at 30 Hz and enables the tracking of a user's skeleton on a subset of joints [21]. A schematic of the Kinect, its sensor locations and its right-handed coordinate system is shown in Figure 4.…”

Section: Methodsmentioning

confidence: 99%

A Novel Method of Human Joint Prediction in an Occlusion Scene by Using Low-Cost Motion Capture Technique

Niu

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Microsoft Kinect, a low-cost motion capture device, has huge potential in applications that require machine vision, such as human-robot interactions, home-based rehabilitation and clinical assessments. The Kinect sensor can track 25 key three-dimensional (3D) “skeleton” joints on the human body at 30 frames per second, and the skeleton data often have acceptable accuracy. However, the skeleton data obtained from the sensor sometimes exhibit a high level of jitter due to noise and estimation error. This jitter is worse when there is occlusion or a subject moves slightly out of the field of view of the sensor for a short period of time. Therefore, this paper proposed a novel approach to simultaneously handle the noise and error in the skeleton data derived from Kinect. Initially, we adopted classification processing to divide the skeleton data into noise data and erroneous data. Furthermore, we used a Kalman filter to smooth the noise data and correct erroneous data. We performed an occlusion experiment to prove the effectiveness of our algorithm. The proposed method outperforms existing techniques, such as the moving mean filter and traditional Kalman filter. The experimental results show an improvement of accuracy of at least 58.7%, 47.5% and 22.5% compared to the original Kinect data, moving mean filter and traditional Kalman filter, respectively. Our method provides a new perspective for Kinect data processing and a solid data foundation for subsequent research that utilizes Kinect.

show abstract

“…The CAGS can also be used to assess postural control and general quality of motion while performing various movement tasks [59]. These devices have the advantage of being marker-less and portable, able to be used in the outpatient clinic, rehabilitation room and at home [62]. CAGS can use therapeutic training protocols that track a patient's progress, reporting on objective functional measures during rehabilitation stages.…”

Section: Commercial Gaming Technologymentioning

confidence: 99%

“…However, the Kinect accuracy is reported to be dependent on movement and user position: e.g., the accuracy decreases when the user is sitting [65]. Wochatz et al evaluated the reliability and validity of the Kinect in lower extremity rehabilitation exercises and reported that the variability was acceptable for joint angles and joint position during the squat, but not during the lunge [62]. Furthermore, there are problems reported with the accuracy of hand tracking [66].…”

Section: Commercial Gaming Technologymentioning

confidence: 99%

Advanced rehabilitation technology in orthopaedics—a narrative review

Kuroda

Young

Shoman

et al. 2020

International Orthopaedics (SICOT)

View full text Add to dashboard Cite

Introduction As the demand for rehabilitation in orthopaedics increases, so too has the development in advanced rehabilitation technology. However, to date, there are no review papers outlining the broad scope of advanced rehabilitation technology used within the orthopaedic population. The aim of this study is to identify, describe and summarise the evidence for efficacy for all advanced rehabilitation technologies applicable to orthopaedic practice. Methods The relevant literature describing the use of advanced rehabilitation technology in orthopaedics was identified from appropriate electronic databases (PubMed and EMBASE) and a narrative review undertaken. Results Advanced rehabilitation technologies were classified into two groups: hospital-based and home-based rehabilitation. In the hospital-based technology group, we describe the use of continuous passive motion and robotic devices (after spinal cord injury) and their effect on improving clinical outcomes. We also report on the use of electromagnetic sensor technology for measuring kinematics of upper and lower limbs during rehabilitation. In the home-based technology group, we describe the use of inertial sensors, smartphones, software applications and commercial game hardware that are relatively inexpensive, user-friendly and widely available. We outline the evidence for videoconferencing for promoting knowledge and motivation for rehabilitation as well as the emerging role of virtual reality. Conclusions The use of advanced rehabilitation technology in orthopaedics is promising and evidence for its efficacy is generally supportive.

show abstract

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

Cited by 44 publications

References 31 publications

Provider confidence in the telemedicine spine evaluation: results from a global study

Provider confidence in the telemedicine spine evaluation: results from a global study

A Novel Method of Human Joint Prediction in an Occlusion Scene by Using Low-Cost Motion Capture Technique

Advanced rehabilitation technology in orthopaedics—a narrative review

Contact Info

Product

Resources

About