Qinematic Posture Scan software is intended to be used by health and wellness service providers in workplaces, gyms, clinics and retail outlets. It is a semi-automated service that records, measures and reports carefully selected movements that are essential to optimal performance and a good standard of living.
Using an off-the-shelf 3D video camera that records at 30 frames per second, Qinematic’s markerless scanning is affordable and accessible for everyone. The Microsoft Kinect sensor, with software development kit (SDK) and native skeletal tracking, has been validated as a tool for postural and balance assessment in peer reviewed scientific literature (1, 2, 3). It has demonstrated reliability in measurement, and inter-reliability in assessment and re-assessment. Qinematic's scientists have identified the strengths and weaknesses of the Kinect sensor, improved on the native tracking algorithms (4), and packaged a service with a very practical user interface that feels more like a game than a human movement laboratory.
The Kinect sensor has its limitations, and does not scan everything well. For example, the frame rate (30fps) is not high enough for recording a golf swing, or running. Furthermore, there are some movements that cannot be scanned with just one sensor because the body parts are not visible all of the time. In these cases, the high-end laboratory equipment should be used, such as Qualysis and Vicon. However, not many people have the budget, time and knowledge to operate these labs. Qinematic is the first line of assessment for health providers to identify who needs further clinical or laboratory assessment, who needs simple advice and maybe a few corrective exercises, who has ‘ideal’ movement and who has ‘normal’ variation. Qinematic offers a fast, convenient way to record and analyse simple functional movements that are the building blocks of more complex movements.
Optimal standing balance, posture and movement patterns in tasks such as side bending and squat are essential for activities of daily living, work tasks and sports performance. These movements are assessed daily in gyms and clinics around the world, and many studies associate them with detection of existing injury and risk of injury. Definitions of ideal, normal and dysfunctional movement have been under discussion for decades. Qinematic hopes to shed some light on the discussion by researching big data on movement patterns from ‘practice-based’ evidence, instead of small ‘evidence-based’ studies that typically involve 40-500 people, and inevitably say little more than ‘more research needs to be done in this area’.
Licensed health professionals in western countries are required to demonstrate ‘evidence based practice’, and are increasingly obliged to show clinical outcomes to justify reimbursement. ‘Intuitive health’ needs to be supported by objective, and preferably ‘digital health’ measures. Studies (5) show that both experienced and novice health professionals have some difficulty in observing and documenting function consistently, especially observation involving multiple body parts (eg. movement in the trunk, hips and the knees at the same time). To define a problem (diagnosis) and choose a course of action (further assessment or intervention), the normality of the movement (or dysfunction) should be determined, directly or remotely using quantitative information. Traditional qualitative visual assessment, can now be captured by Qinematic as 3D video, digitised and reported as quantitative information.
Qinematic does not score performance, diagnose problems or offer advice about interventions. Qinematic accurately and consistently records and measures intersegmental kinematics of the whole body, offering unbiased and objective measures, as well as the possibility to playback the performance in 3D, and see the movements from different perspectives. After all, movement is three dimensional.
Repeat scanning is intended to give an objective view of performance over time. The scan can be administered by the end user, and involves standardised instructions, a uniform calibration procedure, and error detection features that ask a person to repeat a movement if the performance is unusual. This improves the objectivity of the scan procedure, and allows scanning in natural environments such as homes, gyms and workplaces.
Please note – our own research has shown that although the scan device and the procedure are standardised, this does not guarantee that a person performing even simple movements will repeat a functional task the same way each time they get scanned. Unless of course they have unusually stereotypical movements, characteristic of a well-rehearsed dancer, or a person with chronic back pain, or 6 months of knee rehabilitation. During quiet standing, we sway around a central equilibrium point without ever remaining exactly still as we maintain orientation to the world. Are these examples of variability in movement considered errors in motor performance, or are they normal output of a healthy motor system? There is mounting evidence of the importance of variability in normal movement, which reveals variation not as error, but as a necessary condition for function (6).
What is considered normal healthy variation (behavioural variation and not statistical variation) will emerge as we analyse intersegmental kinematics using big data analysis, instead of small data statistics. Qinematic will re-define ideal, normal and dysfunctional movement patterns, and thereafter consider scoring a performance. In the meantime, although the literature supports the Kinect sensor as a valid measurement tool, it is still up to the health provider to decide what to do with the measures, and what they mean for their clients.
Human Movement Scientist
Course Manager – Transforming Healthcare, Karolinska Institute, Sweden
Founder – Qinematic AB
1. Yeung, L. F., Cheng, K. C., Fong, C. H., Lee, W. C., & Tong, K. Y. . (2014) Evaluation of the Microsoft Kinect as a clinical assessment tool of body sway. Gait & Posture, 40(4), 532-538.
2. Clark, R. A., Pua, Y. H., Fortin, K., Ritchie, C., Webster, K. E., Denehy, L., & Bryant, A. L. (2012). Validity of the Microsoft Kinect for assessment of postural control. Gait & posture, 36(3), 372-377.
3. Clark, RA et al (2015) Reliability and concurrent validity of the Microsoft Xbox One Kinect for assessment of standing balance and postural control. Gait Posture. 2015 Jul;42(2):210-3.
4. Otte K. et al (2016) Accuracy and Reliability of the Kinect Version 2 for Clinical Measurement of Motor Function, PLoS One. 11(11)
5. Gianola S. et al. (2017) Single leg squat performance in physically and non-physically active individuals: a cross-sectional study, BMC Musculoskeletal Disorders 18:299
6. Regina T Harbourne, Nicholas Stergiou (2009) Movement Variability and the Use of Nonlinear Tools: Principles to Guide Physical Therapist Practice, Phys Ther. 2009 Mar; 89(3): 267–282.
Conclusions from some studies
Clark et al. (2012)
The Kinect SDK provides the ability to differentiate postural control strategies using an inexpensive, portable and widely available system could provide clinical and research benefits in a variety of patient populations. Our results suggest that the Microsoft Kinect provides anatomical landmark displacement and trunk angle data which possesses excellent concurrent validity when compared to data obtained from a 3D camera-based motion analysis system.
Clark et al. (2015)
The Kinect V2 has the potential to be used as a reliable and valid tool for the assessment of some aspects of balance performance.
Yeung et al. (2014)
To conclude, this study compared three Total Body Centre of Mass (TBCM) sway assessment tools: a Kinect system, a motion capture system, and a force plate. The Kinect system demonstrated comparable intra-session reliability and accuracy in TBCM sway measurements to the motion capture system and the force plate. The Kinect and Vicon systems demonstrated comparable reliability and were sensitive to different tasks. Overall, Kinect is a cost-effective alternative to a motion capture and force plate system for clinical assessment of TBCM sway.
Otte et al. (2016)
Given that this system is low-cost, portable and does not require any sensors to be attached to the body, it could provide numerous advantages when compared to established marker- or wearable sensor based system. The Kinect V2 has the potential to be used as a reliable and valid clinical measurement tool.