Human gait-labeling uncertainty and a hybrid model for gait segmentation.

Motion capture systems are widely accepted as ground-truth for gait analysis and are used for the validation of other gait analysis systems. To date, their reliability and limitations in manual labeling of gait events have not been studied. Objectives: Evaluate manual labeling uncertainty and introduce a hybrid stride detection and gait-event estimation model for autonomous, long-term, and remote monitoring. Methods: Estimate inter-labeler inconsistencies by computing the limits-of-agreement. Develop a hybrid model based on dynamic time warping and convolutional neural network to identify valid strides and eliminate non-stride data in inertial (walking) data collected by a wearable device. Finally, detect gait events within a valid stride region. Results: The limits of inter-labeler agreement for key gait events heel off, toe off, heel strike, and flat foot are 72, 16, 24, and 80 ms, respectively; The hybrid model's classification accuracy for stride and non-stride are 95.16 and 84.48%, respectively; The mean absolute error for detected heel off, toe off, heel strike, and flat foot are 24, 5, 9, and 13 ms, respectively, when compared to the average human labels. Conclusions: The results show the inherent labeling uncertainty and the limits of human gait labeling of motion capture data; The proposed hybrid-model's performance is comparable to that of human labelers, and it is a valid model to reliably detect strides and estimate the gait events in human gait data. Significance: This work establishes the foundation for fully automated human gait analysis systems with performances comparable to human-labelers.

Real-Time Gait Phase Detection on Wearable Devices for Real-World Free-Living Gait.

Detecting gait phases with wearables unobtrusively and reliably in real-time is important for clinical gait rehabilitation and early diagnosis of neurological diseases. Due to hardware limitations of microcontrollers in wearable devices (e.g., memory and computation power), reliable real-time gait phase detection on the microcontrollers remains a challenge, especially for long-term real-world free-living gait. In this work, a novel algorithm based on a reduced support vector machine (RSVM) and a finite state machine (FSM) is developed to address this. The RSVM is developed by exploiting the cascaded K-means clustering to reduce the model size and computation time of a standard SVM by 88% and a factor of 36, with only minor degradation in gait phase prediction accuracy of around 4%. For each gait phase prediction from the RSVM, the FSM is designed to validate the prediction and correct misclassifications. The developed algorithm is implemented on a microcontroller of a wearable device and its real-time (on the fly) classification performance is evaluated by twenty healthy subjects walking along a predefined real-world route with uncontrolled free-living gait. It shows a promising real-time performance with an accuracy of 91.51%, a sensitivity of 91.70%, and a specificity of 95.77%. The algorithm also demonstrates its robustness with varying walking conditions.

Integrated Pedal System for Data Driven Rehabilitation.

We present a system capable of providing visual feedback for ergometer training, allowing detailed analysis and gamification. The presented solution can easily upgrade any existing ergometer device. The system consists of a set of pedals with embedded sensors, readout electronics and wireless communication modules and a tablet device for interaction with the users, which can be mounted on any ergometer, transforming it into a full analytical assessment tool with interactive training capabilities. The methods to capture the forces and moments applied to the pedal, as well as the pedal's angular position, were validated using reference sensors and high-speed video capture systems. The mean-absolute error (MAE) for load is found to be 18.82 N, 25.35 N, 0.153 Nm for Fx, Fz and Mx respectively and the MAE for the pedal angle is 13.2°. A fully gamified experience of ergometer training has been demonstrated with the presented system to enhance the rehabilitation experience with audio visual feedback, based on measured cycling parameters.

Turbulent Systolic Flow Downstream of a Bioprosthetic Aortic Valve: Velocity Spectra, Wall Shear Stresses, and Turbulent Dissipation Rates.

Every year, a quarter million patients receive prosthetic heart valves in aortic valve replacement therapy. Prosthetic heart valves are known to lead to turbulent blood flow. This turbulent flow field may have adverse effects on blood itself, on the aortic wall and on the valve performance. A detailed characterization of the turbulent flow downstream of a valve could yield better understanding of its effect on shear-induced thrombocyte activation, unphysiological wall shear stresses and hemodynamic valve performance. Therefore, computational simulations of the flow past a bioprosthetic heart valve were performed. The computational results were validated against experimental measurements of the turbulent flow field with tomographic particle image velocimetry. The turbulent flow was analyzed for disturbance amplitudes, dissipation rates and shear stress distributions. It was found that approximately 26% of the hydrodynamic resistance of the valve was due to turbulent dissipation and that this dissipation mainly took place in a region about one valve diameter downstream of the valve orifice. Farther downstream, the turbulent fluctuations became weaker which was also reflected in the turbulent velocity spectra of the flow field. Viscous shear stresses were found to be in the range of the critical level for blood platelet activation. The turbulent flow led to elevated shear stress levels along the wall of the ascending aorta with strongly fluctuating and chaotic wall shear stress patterns. Further, we identified leaflet fluttering at 40 Hz which was connected to repeated shedding of vortex rings that appeared to feed the turbulent flow downstream of the valve.

An Intracardiac Flow Based Electromagnetic Energy Harvesting Mechanism for Cardiac Pacing.

Contemporary cardiac implantable electronic devices such as pacemakers or event recorders are powered by primary batteries. Device replacement due to battery depletion may cause complications and is costly. The goal of energy harvesting devices is to power the implant with energy from intracorporeal power sources such as vibrations and blood flow. By replacing primary batteries with energy harvesters, reinterventions can be avoided and the size of the total device might be reduced. This paper introduces a device with a lever, which is deflected by the blood stream within the right ventricular outflow tract (RVOT), an attractive site for cardiac pacing. The resulting torque is converted to electrical energy by an electromagnetic mechanism. The blood flow harvester weighs 6.4 g and has a volume of 2 cm3, making the harvester small enough for catheter implantation. It was tested in an experimental setup mimicking flow conditions in the RVOT. The blood flow harvester generated a mean power of 14.39 ± 8.38 µW at 60 bpm (1 Hz) and up to 82.64 ± 17.14 µW at 200 bpm (3.33 Hz) during bench experiments at 1 m/s peak flow velocity. Therefore, it presents a viable alternative to power batteryless and leadless cardiac pacemakers.