Gait analysis is an indispensable tool for scientific assessment and treatment of individuals whose ability to walk is impaired. The high cost of installation and operation are a major limitation for wide-spread use in clinical routine.

Advances in Artificial Intelligence (AI) could significantly reduce the required instrumentation. A mobile phone could be all equipment necessary for 3D gait analysis. MediaPipe Pose provided by Google Research is such a Machine Learning approach for human body tracking from monocular RGB video frames that is detecting 3D-landmarks of the human body.

Aim of this study was to analyze the accuracy of gait phase detection based on the joint landmarks identified by the AI system.

Motion data from 10 healthy volunteers walking on a treadmill with a fixed speed of 4.5km/h (Callis, Sprintex, Germany) was sampled with a mobile phone (iPhone SE 2nd Generation, Apple). The video was processed with Mediapipe Pose (Version 0.9.1.0) using custom python software. Gait phases (Initial Contact - IC and Toe Off - TO) were detected from the angular velocities of the lower legs. For the determination of ground truth, the movement was simultaneously recorded with the AS-200 System (LaiTronic GmbH, Innsbruck, Austria).

The number of detected strides, the error in IC detection and stance phase duration was calculated.

In total, 1692 strides were detected from the reference system during the trials from which the AI-system identified 679 strides. The absolute mean error (AME) in IC detection was 39.3 ± 36.6 ms while the AME for stance duration was 187.6 ± 140 ms.

Landmark detection is a challenging task for the AI-system as can clearly be seen be the rate of only 40% detected strides. As mentioned by Fadillioglu et al., error in TO-detection is higher than in IC-detection.

A promising application of Mesenchymal stem cells (MSCs) is the treatment of non-unions. Substituting bone grafts, MSCs are directly injected into the fracture gap. High cell viability seems to be a prerequisite for therapeutic success. Administration of the MSCs via injection creates shear stresses possibly damaging or destroying the cells.

Aim of this study was to investigate the effect of the injection process on cell viability.

MSCs were isolated and cultivated from femoral tissue of five subjects undergoing arthroplasty. Prior to injection, the cells were identified as MSCs. After dissolving to a concentration of 1 Million cells/ml, 1 ml of the suspension was injected through a cannula of 200 mm length and 2 mm diameter (14 G) with flow rates of 38 and 100 ml/min. The viability of the MSCs at different flow rates was evaluated by staining to detect the healthy cell fraction. It was analyzed statistically against a control group via the Kruskal-Wallis-test and for equivalence via the TOST procedure. Significance level was set to 5 %, equivalence margin to 20 %.

The healthy cell fraction of the control group was 85.88 ± 2.98 %, 86.04 ± 2.53 % at 38 ml/min and 85.48 ± 1.64 % at 100 ml/min. There was no significant difference between the fraction of healthy cells (p = 0.99) for different volume flows, but a significant equivalence between the control group and the two volume flows (38 ml/min: p = 0.002, 100 ml/min: p = 0.001).

When injecting MSC solutions, e.g. into a non-union, the viability of the injected cells does not deterioriate significant. The injecting technique is therefore feasible.

Vacuum orthoses are being applied in the care of patients with foot and lower leg conditions, as ankle fractures or sprains. The lower leg is protected and immobilized, which increases mobility. Due to the design, the orthoses lead to a difference in leg length, i.e. the side with the orthosis becomes longer, which changes the gait kinematics. To prevent or mitigate the unfavourable effects of altered gait kinematics, leg length-evening devices (shoe lifts) are offered that are worn under the shoe on the healthy side. Our aim was to evaluate the effect of such a device on the normality of gait kinematics.

Gait analysis was conducted with 63 adult, healthy volunteers having signed an informed consent form that were asked to walk on a treadmill at a speed of 4.5km/h in three different conditions:

Data was sampled using the gait analysis system MCU 200 (LaiTronic GmbH, Austria). The positions of the joint markers were exported from the software and evaluated for the joint angles during the gait cycle using custom software (implemented in DIAdem 2017, National Instruments).

A normality score using a modification of the Gait Profile Score (GPS) was calculated in every 1%-interval of the gait cycle and evaluated with a Wilcoxon signed rank test.

The GPS value was reduced by 0.33° (0.66°) (median and IQR) while wearing the shoe lift. The effect was statistically significant, and very large (W = 1535.00, p < .001; r (rank biserial) = 0.52, 95% CI [0.29, 0.70]).

The significant reduction of the GPS value indicates a more normal gait kinematics while using the leg length-evening device on the contralateral shoe. This rather simple and inexpensive device thus might improve patient comfort and balance while using the vacuum orthoses.