•This paper have succeeded in developing a one-D convolution neural network (1-D-CNN) for the detection of artifact-free segments of PPG signals.•This paper eliminated the requirement of ...data-dependent pulse segmentation step.•This paper is robust to variations in the PPG morphological waveforms within individual subjects due to motion or environmental changes.
Continuous monitoring of physiological parameters such as photoplethysmography (PPG) has attracted increased interest due to advances in wearable sensors. However, PPG recordings are susceptible to various artifacts, and thus reducing the reliability of PPG-driven parameters, such as oxygen saturation, heart rate, blood pressure and respiration. This paper proposes a one-dimensional convolution neural network (1-D-CNN) to classify five-second PPG segments into clean or artifact-affected segments, avoiding data-dependent pulse segmentation techniques and heavy manual feature engineering.
Continuous raw PPG waveforms were blindly allocated into segments with an equal length (5s) without leveraging any pulse location information and were normalized with Z-score normalization methods. A 1-D-CNN was designed to automatically learn the intrinsic features of the PPG waveform, and perform the required classification. Several training hyperparameters (initial learning rate and gradient threshold) were varied to investigate the effect of these parameters on the performance of the network. Subsequently, this proposed network was trained and validated with 30 subjects, and then tested with eight subjects, with our local dataset. Moreover, two independent datasets downloaded from the PhysioNet MIMIC II database were used to evaluate the robustness of the proposed network.
A 13 layer 1-D-CNN model was designed. Within our local study dataset evaluation, the proposed network achieved a testing accuracy of 94.9%. The classification accuracy of two independent datasets also achieved satisfactory accuracy of 93.8% and 86.7% respectively. Our model achieved a comparable performance with most reported works, with the potential to show good generalization as the proposed network was evaluated with multiple cohorts (overall accuracy of 94.5%).
This paper demonstrated the feasibility and effectiveness of applying blind signal processing and deep learning techniques to PPG motion artifact detection, whereby manual feature thresholding was avoided and yet a high generalization ability was achieved.
In this study, we evaluate a preload-based Starling-like controller for implantable rotary blood pumps (IRBPs) using left ventricular end-diastolic pressure (PLVED) as the feedback variable. ...Simulations are conducted using a validated mathematical model. The controller emulates the response of the natural left ventricle (LV) to changes in PLVED. We report the performance of the preload-based Starling-like controller in comparison with our recently designed pulsatility controller and constant speed operation. In handling the transition from a baseline state to test states, which include vigorous exercise, blood loss and a major reduction in the LV contractility (LVC), the preload controller outperformed pulsatility control and constant speed operation in all three test scenarios. In exercise, preload-control achieved an increase of 54% in mean pump flow (Formula: see text) with minimum loading on the LV, while pulsatility control achieved only a 5% increase in flow and a decrease in mean pump speed. In a hemorrhage scenario, the preload control maintained the greatest safety margin against LV suction. PLVED for the preload controller was 4.9 mmHg, compared with 0.4 mmHg for the pulsatility controller and 0.2 mmHg for the constant speed mode. This was associated with an adequate mean arterial pressure (MAP) of 84 mmHg. In transition to low LVC, Formula: see text for preload control remained constant at 5.22 L/min with a PLVED of 8.0 mmHg. With regards to pulsatility control, Formula: see text fell to the nonviable level of 2.4 L/min with an associated PLVED of 16 mmHg and a MAP of 55 mmHg. Consequently, pulsatility control was deemed inferior to constant speed mode with a PLVED of 11 mmHg and a Formula: see text of 5.13 L/min in low LVC scenario. We conclude that pulsatility control imposes a danger to the patient in the severely reduced LVC scenario, which can be overcome by using a preload-based Starling-like control approach.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
We used body-worn inertial sensors to quantify differences in semi-free-living gait between stairs and on normal flat ground in older adults, and investigated the utility of assessing gait on these ...terrains for predicting the occurrence of multiple falls. Eighty-two community-dwelling older adults wore two inertial sensors, on the lower back and the right ankle, during several bouts of walking on flat surfaces and up and down stairs, in between rests and activities of daily living. Derived from the vertical acceleration at the lower back, step rate was calculated from the signal's fundamental frequency. Step rate variability was the width of this fundamental frequency peak from the signal's power spectral density. Movement vigor was calculated at both body locations from the signal variance. Partial Spearman correlations between gait parameters and physiological fall risk factors (components from the Physiological Profile Assessment) were calculated while controlling for age and gender. Overall, anteroposterior vigor at the lower back in stair descent was lower in subjects with longer reaction times. Older adults walked more slowly on stairs, but they were not significantly slower on flat surfaces. Using logistic regression, faster step rate in stair descent was associated with multiple prospective falls over 12 months. No significant associations were shown from gait parameters derived during walking upstairs or on flat surfaces. These results suggest that stair descent gait may provide more insight into fall risk than regular walking and stair ascent, and that further sensor-based investigation into unsupervised gait on different terrains would be valuable.
Kidney development is key to the long-term health of the fetus. Renal volume and vascularity assessed by 3D ultrasound (3D-US) are known markers of wellbeing, however, a lack of real-time image ...segmentation solutions preclude these measures being used in a busy clinical environment. In this work, we aimed to automate kidney segmentation using fully convolutional neural networks (fCNNs). We used multi-parametric input fusion incorporating 3D B-Mode and power Doppler (PD) volumes, aiming to improve segmentation accuracy. Three different fusion strategies and their performance were assessed versus a single input (B-Mode) network. Early input-level fusion provided the best segmentation accuracy with an average Dice similarity coefficient (DSC) of 0.81 and Hausdorff distance (HD) of 8.96 mm, an improvement of 0.06 DSC and reduction of 1.43 mm HD compared to our baseline network. Compared to manual segmentation for all models, repeatability was assessed by intra-class correlation coefficients (ICC) indicating good to excellent reproducibility (ICC <inline-formula><tex-math notation="LaTeX">>=</tex-math></inline-formula> 0.93). The framework was extended to support multiple graphics processing units (GPUs) to better handle volumetric data, dense fCNN models, batch normalization and complex fusion networks. This work and available source code provides a framework to increase the parameter space of encoder-decoder style fCNNs across multiple GPUs and shows that application of multi-parametric 3D-US in fCNN training improves segmentation accuracy.
Cardiovascular disease is known as the number one cause of death globally, with elevated blood pressure (BP) being the single largest risk factor. Hence, BP is an important physiological parameter ...used as an indicator of cardiovascular health. The use of automated non-invasive blood pressure (NIBP) measurement devices is growing, as they can be used without expertise and BP measurement can be performed by patients at home. Non-invasive cuff-based monitoring is the dominant method for BP measurement. While the oscillometric technique is most common, some automated NIBP measurement methods have been developed based on the auscultatory technique. By utilizing (relatively) large BP data annotated by experts, models can be trained using machine learning and statistical concepts to develop novel NIBP estimation algorithms. Amongst artificial intelligence (AI) techniques, deep learning has received increasing attention in different fields due to its strength in data classification and feature extraction problems. This paper reviews AI-based BP estimation methods with a focus on recent advances in deep learning-based approaches within the field. Various architectures and methodologies proposed todate are discussed to clarify their strengths and weaknesses. Based on the literature reviewed, deep learning brings plausible benefits to the field of BP estimation. We also discuss some limitations which can hinder the widespread adoption of deep learning in the field and suggest frameworks to overcome these challenges.
A transverse intrafascicular multichannel electrode (TIME) may offer advantages over more conventional cuff electrodes including higher spatial selectivity and reduced stimulation charge ...requirements. However, the performance of TIME, especially in the context of non-conventional stimulation waveforms, remains relatively unexplored. As part of our overarching goal of investigating stimulation efficacy of TIME, we developed a computational toolkit that automates the creation and usage of in silico nerve models with TIME setup, which solves nerve responses using cable equations and computes extracellular potentials using finite element method (FEM).
We began by implementing a flexible and scalable Python / MATLAB-based toolkit for automatically creating models of nerve stimulation in the hybrid NEURON / COMSOL ecosystems. We then developed a sciatic nerve model containing 14 fascicles with 1,170 myelinated (A-type, 30%) and unmyelinated (C-type, 70%) fibers to study fiber responses over a variety of TIME arrangements (monopolar and hexapolar) and stimulation waveforms (kilohertz stimulation and cathodic ramp modulation). Main results: Our toolkit obviates the conventional need to re-create the same nerve in two disparate modeling environments and automates bi-directional transfer of results. Our population-based simulations suggested that kilohertz stimuli provide selective activation of targeted C fibers near the stimulating electrodes but also tended to activate non-targeted A fibers further away. However, C fiber selectivity can be enhanced by hexapolar TIME arrangements that confined the spatial extent of electrical stimuli. Improved upon prior findings, we devised a high-frequency waveform that incorporates cathodic DC ramp to completely remove undesirable onset responses. Conclusion: Our toolkit allows agile, iterative design cycles involving the nerve and TIME, while minimizing the potential operator errors during complex simulation. The nerve model created by our toolkit allowed us to study and optimize the design of next-generation intrafascicular implants for improved spatial and fiber-type selectivity. 
.
As the population ages, health issues like injurious falls demand more attention. One solution is to use wearable devices to detect falls. Nevertheless, most of these devices raise obtrusiveness, and ...older people generally resist or might forget to wear them. The millimeter-wave (mmWave) radar technology was used in this study to unobtrusively detect human falls. Data were collected from healthy young volunteers with the radar mounted on the side wall (trial 1) or overhead (trial 2) of an experimental room. A set of features was manually extracted from the data point clouds, then multilayer perceptron (MLP), Random Forest (RF), k-nearest neighbor (KNN), and support vector machine (SVM) classifiers were applied on the features. Additionally, we devised a convolutional neural network (CNN)-based deep learning model for the underlying fall detection problem that receives a 3D representation of the point cloud data, known as occupancy grid, as the input. The optimal installation position of the radar sensor was unknown. Therefore, the sensor was mounted on side wall, and on the ceiling of the room to allow the performance comparison between these sensor placements. RF classifier achieved the best results in trial 2 (accuracy of 92.2%, recall of 0.881, precision of 0.805, and F1-score of 0.841), the proposed CNN model achieved slightly better results comparing to the RF method in trial 2 (accuracy of 92.3%, recall of 0.891, precision of 0.801, and F1-score of 0.844). These results suggest the development of an unobtrusive monitoring system for fall detection using mmWave radar is feasible.
Accelerometry offers a practical and low cost method of objectively monitoring human movements, and has particular applicability to the monitoring of free-living subjects. Accelerometers have been ...used to monitor a range of different movements, including gait, sit-to-stand transfers, postural sway and falls. They have also been used to measure physical activity levels and to identify and classify movements performed by subjects. This paper reviews the use of accelerometer-based systems in each of these areas. The scope and applicability of such systems in unsupervised monitoring of human movement are considered. The different systems and monitoring techniques can be integrated to provide a more comprehensive system that is suitable for measuring a range of different parameters in an unsupervised monitoring context with free-living subjects. An integrated approach is described in which a single, waist-mounted accelerometry system is used to monitor a range of different parameters of human movement in an unsupervised setting.
Electrical stimulation of neuronal tissue is a promising strategy to treat a variety of neurological disorders. The mechanism of neuronal activation by external electrical stimulation is governed by ...voltage-gated ion channels. This stimulus, typically brief in nature, leads to membrane potential depolarization, which increases ion flow across the membrane by increasing the open probability of these voltage-gated channels. In spiking neurons, it is activation of voltage-gated sodium channels (Na
channels) that leads to action potential generation. However, several other types of voltage-gated channels are expressed that also respond to electrical stimulation. In this study, we examine the response of voltage-gated potassium channels (K
channels) to brief electrical stimulation by whole cell patch-clamp electrophysiology and computational modeling. We show that nonspiking amacrine neurons of the retina exhibit a large variety of responses to stimulation, driven by different K
-channel subtypes. Computational modeling reveals substantial differences in the response of specific K
-channel subtypes that is dependent on channel kinetics. This suggests that the expression levels of different K
-channel subtypes in retinal neurons are a crucial predictor of the response that can be obtained. These data expand our knowledge of the mechanisms of neuronal activation and suggest that K
-channel expression is an important determinant of the sensitivity of neurons to electrical stimulation.
This paper describes the response of various voltage-gated potassium channels (K
channels) to brief electrical stimulation, such as is applied during prosthetic electrical stimulation. We show that the pattern of response greatly varies between K
channel subtypes depending on activation and inactivation kinetics of each channel. Our data suggest that problems encountered when artificially stimulating neurons such as cessation in firing at high frequencies, or "fading," may be attributed to K
-channel activation.
Work-related musculoskeletal disorders (WMSDs) are often caused by repetitive lifting, making them a significant concern in occupational health. Although wearable assist devices have become the norm ...for mitigating the risk of back pain, most spinal assist devices still possess a partially rigid structure that impacts the user’s comfort and flexibility. This paper addresses this issue by presenting a smart textile-actuated spine assistance robotic exosuit (SARE), which can conform to the back seamlessly without impeding the user’s movement and is incredibly lightweight. To detect strain on the spine and to control the smart textile automatically, a soft knitting sensor that utilizes fluid pressure as a sensing element is used. Based on the soft knitting hydraulic sensor, the robotic exosuit can also feature the ability of monitoring and rectifying human posture. The SARE is validated experimentally with human subjects (N = 4). Through wearing the SARE in stoop lifting, the peak electromyography (EMG) signals of the lumbar erector spinae are reduced by 22.8% ± 12 for lifting 5 kg weights and 27.1% ± 14 in empty-handed conditions. Moreover, the integrated EMG decreased by 34.7% ± 11.8 for lifting 5 kg weights and 36% ± 13.3 in empty-handed conditions. In summary, the artificial muscle wearable device represents an anatomical solution to reduce the risk of muscle strain, metabolic energy cost and back pain associated with repetitive lifting tasks.