Objective: To evaluate movement parameters for clinical use extracted from Microsoft Kinect V2 joints.

Background: Instrumental motor assessment has been proposed to increase objectivity but most current systems are time and cost intensive. After we established spatial accuracy of Kinect V2 skeleton joint data, we now explore the accuracy and reliability of derived kinematic parameters for possible clinical use.

Methods: We used Motognosis Labs in combination with Microsoft Kinect V2 and Software Development Kit (SDK) version 2.0. As reference, we used a 16-camera Vicon system (MX13+, Nexus 2.1) with the standard gait model. 19 healthy volunteers performed 6 different motor tasks with 3 to 5 repetitions. Motor assessments were designed to test specific motor functions of clinical interest and 31 kinematic parameters were extracted from smoothed joint movements with algorithms specific for each motor task. Accuracy of the KinectV2 parameters is reported as ICC(3,1), Pearson Correlation (p) and Limits of Agreement (LOA) against Vicon. Repeatability is reported as ICC(1,1) and Standard Error of Measurement (SEM).

Results: Most kinematic parameters showed good to excellent absolute agreement (ICC(3,1) .65 – 1.00) and consistency (Pearson correlation .75 – 1.00) between both systems. Accuracy was especially high for sway velocity in quiet stance, trunk movement and time needed for postural transitions, gait speed from short walks at different speed and cadence of footfalls while stepping in place. Lower accuracy was seen for trunk movement in roll direction while walking (ICC(3,1) of 0.43 – 0.65) and amplitude of knee motion while stepping on the spot (ICC(3,1) 0.12). Repeatability was acceptable for most parameters and of similar magnitude for both, Kinect V2 and Vicon (ICC(1,1) Kinect V2 .32 – 0.98, Vicon .28 – 0.98). Relative SEM was acceptable (<20%) for Kinect V2 in 23 of 31 parameters investigated; this included all parameters with high agreement outlined above.

Conclusions: We found excellent agreement between Kinect and Vicon gold standard as well as retest reliability for a variety of kinematic parameters extracted from different motor tasks of clinical interest. This supports Kinect V2 as potentially suitable for clinical use. However, our preliminary data are based on healthy subjects and reliability will have to be established in patient groups of interest before clinical applications.

« Back to 2016 International Congress

MDS Abstracts - https://www.mdsabstracts.org/abstract/evaluation-of-kinematic-parameters-of-potential-clinical-use-extracted-from-microsoft-kinect-v2-motor-assessments/