ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features.

In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were detected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhythmia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance.

Non-Invasive Hemodynamics Monitoring System Based on Electrocardiography via Deep Convolutional Autoencoder.

This study evaluates cardiovascular and cerebral hemodynamics systems by only using non-invasive electrocardiography (ECG) signals. The Massachusetts General Hospital/Marquette Foundation (MGH/MF) and Cerebral Hemodynamic Autoregulatory Information System Database (CHARIS DB) from the PhysioNet database are used for cardiovascular and cerebral hemodynamics, respectively. For cardiovascular hemodynamics, the ECG is used for generating the arterial blood pressure (ABP), central venous pressure (CVP), and pulmonary arterial pressure (PAP). Meanwhile, for cerebral hemodynamics, the ECG is utilized for the intracranial pressure (ICP) generator. A deep convolutional autoencoder system is applied for this study. The cross-validation method with Pearson's linear correlation (R), root mean squared error (RMSE), and mean absolute error (MAE) are measured for the evaluations. Initially, the ECG is used to generate the cardiovascular waveform. For the ABP system-the systolic blood pressure (SBP) and diastolic blood pressures (DBP)-the R evaluations are 0.894 ± 0.004 and 0.881 ± 0.005, respectively. The MAE evaluations for SBP and DBP are, respectively, 6.645 ± 0.353 mmHg and 3.210 ± 0.104 mmHg. Furthermore, for the PAP system-the systolic and diastolic pressures-the R evaluations are 0.864 ± 0.003 mmHg and 0.817 ± 0.006 mmHg, respectively. The MAE evaluations for systolic and diastolic pressures are, respectively, 3.847 ± 0.136 mmHg and 2.964 ± 0.181 mmHg. Meanwhile, the mean CVP evaluations are 0.916 ± 0.001, 2.220 ± 0.039 mmHg, and 1.329 ± 0.036 mmHg, respectively, for R, RMSE, and MAE. For the mean ICP evaluation in cerebral hemodynamics, the R and MAE evaluations are 0.914 ± 0.003 and 2.404 ± 0.043 mmHg, respectively. This study, as a proof of concept, concludes that the non-invasive cardiovascular and cerebral hemodynamics systems can be potentially investigated by only using the ECG signal.

Genetic Deep Convolutional Autoencoder Applied for Generative Continuous Arterial Blood Pressure via Photoplethysmography.

Hypertension affects a huge number of people around the world. It also has a great contribution to cardiovascular- and renal-related diseases. This study investigates the ability of a deep convolutional autoencoder (DCAE) to generate continuous arterial blood pressure (ABP) by only utilizing photoplethysmography (PPG). A total of 18 patients are utilized. LeNet-5- and U-Net-based DCAEs, respectively abbreviated LDCAE and UDCAE, are compared to the MP60 IntelliVue Patient Monitor, as the gold standard. Moreover, in order to investigate the data generalization, the cross-validation (CV) method is conducted. The results show that the UDCAE provides superior results in producing the systolic blood pressure (SBP) estimation. Meanwhile, the LDCAE gives a slightly better result for the diastolic blood pressure (DBP) prediction. Finally, the genetic algorithm-based optimization deep convolutional autoencoder (GDCAE) is further administered to optimize the ensemble of the CV models. The results reveal that the GDCAE is superior to either the LDCAE or UDCAE. In conclusion, this study exhibits that systolic blood pressure (SBP) and diastolic blood pressure (DBP) can also be accurately achieved by only utilizing a single PPG signal.

Arrhythmia Evaluation in Wearable ECG Devices.

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation.

Chronic pudendal neuromodulation using an implantable microstimulator improves voiding function in diabetic rats.

Objective: Few studies have investigated the feasibility of using chronic pudendal neuromodulation for improving voiding function in patients with diabetes who are also experiencing urinary retention. The present study investigated the effects of chronic electrical stimulation (ES) of the sensory branch of the pudendal nerve on voiding function in diabetic rats. Approach: A custom-made implantable microstimulation system was designed and manufactured for chronic implantation in normal control (NC) and diabetic rats. After three or six weeks of pudendal neuromodulation, the intravesical pressure, external urethral sphincter electromyograms (EUS-EMGs), and urine flow rate (UFR) of all rats were simultaneously recorded to assess the effects of chronic pudendal ES on voiding function. Morphological changes in pudendal axons were assessed through hematoxylin and eosin (H&E) staining. Significance: This study demonstrated the feasibility of using chronic pudendal neuromodulation for improving voiding function in diabetic rats. These results may facilitate the development of an advanced neural prosthesis for restoring bladder function in clinical settings.

Contribution of Corticospinal Modulation and Total Electrical Energy for Peripheral-Nerve-Stimulation-Induced Neuroplasticity as Indexed by Additional Muscular Force.

BACKGROUND: Protocols to induce motor related neuroplasticity are usually directed to central neural structures such as the motor cortex or the spinal cord. OBJECTIVE: Herein, we aimed to evaluate the effects of peripheral nerve stimulation using a current intensity (stimulation intensity) approach to understand the contribution of the corticospinal system and total energy to electrically-induced neuroplasticity. METHODS: Electrical stimulation trains of lower intensity, interlaced with 2-s bursts of higher intensity, were applied to anesthetized rabbits. Nerve blocks were applied to the proximal side of the stimulation site with identical stimulation trains in a different session to block the contribution of corticospinal volleys during intensity-modulated electrical stimulation. RESULTS: Additional force corresponding to additional recruitment of motoneurons was observed when a 2-s burst of high intensity was present (burst/constant: 24.7 ± 3.6%/2.09 ± 4.8%; p < .001). Additional force was absent in sessions when the neural pathway to the spinal cord was blocked (unblocked/blocked: 29.3 ± 3.8%/-2.49 ± 4.8%; p < .001). CONCLUSIONS: The results suggest that induced neuroplasticity indexed by the additional force is dependent on the total energy applied and connectivity to central structures. These results give additional evidence for the contribution of two factors for induced neuroplasticity: (i) modulation by corticospinal structures and (ii) total energy of stimulation. Further protocols should explore simultaneous peripheral and central stimulation.

Effects of pudendal neuromodulation on bladder function in chronic spinal cord-injured rats.

BACKGROUND/PURPOSE: Few studies have investigated the feasibility of using pudendal neuromodulation to regulate bladder function in spinal cord-injured (SCI) animals. The present study aimed to determine the effects of electrical activation of the pudendal sensory branch on improving voiding functions in rats 6 weeks after a spinal cord injury and to explore the underlying neuromodulatory mechanisms. METHODS: Two urodynamic measurements were used to assess the effects of electrical stimulation (ES) on bladder and urethral functions: simultaneous recordings of the intravesical pressure (IVP) during continuous isotonic transvesical infusion (i.e., isotonic IVP) and external urethral sphincter (EUS) electromyography (EUS-EMG), and simultaneous recordings of transvesical pressure under isovolumetric conditions (i.e., isovolumetric IVP) and urethral perfusion pressure (UPP). RESULTS: Six weeks after the SCI, the rats showed voiding dysfunction, as indicated by abnormal cystometric measurements (e.g., increased volume threshold, increased contraction amplitude, and increased residual volume, and decreased voided volume). The voiding efficiency (VE) decreased to 13% after the SCI, but increased to 22-34% after applying pudendal afferent stimulation. In addition, pudendal stimulation significantly increased the EUS burst period and increased the difference between the UPP and the high-frequency oscillation (HFO) baselines, and changed the time offset between bladder and EUS activities. These findings suggest that pudendal afferent stimulation improved the VE by prolonging the micturition interval, decreased the urethral resistance, and recovered detrusor-sphincter dyssynergia during the voiding phase. CONCLUSION: This study demonstrates the feasibility of using pudendal neuromodulation in chronic SCI rats. These results could aid in developing an advanced neural prosthesis to restore bladder function in clinical settings.

Pudendal neuromodulation with a closed-loop control strategy to improve bladder functions in the animal study.

The aim of this study was to develop a new closed-loop control strategy for improving bladder emptying and verify its performance in animal experiments. Two channel outputs of electrical currents triggered by intravesical pressure (IVP)-feedback signals were set to automatically regulate the rat's pudendal nerve for selective nerve stimulation and blocking. Under this experimental design, a series of in-vivo animal experiments were conducted on anesthetized rats. Our results showed that the IVP-feedback control strategy for dual-channel pudendal neuromodulation performed well in animal experiments and could be utilized to selectively stimulate and block the pudendal nerve to augment bladder contraction and restore external urethral sphincter (EUS) bursting activity to simultaneously improve bladder emptying. This study demonstrates the feasibility of the IVP-based feedback-control strategy with animal experiments, and the results could provide a basis for developing a sophisticated neural prosthesis for restoring bladder function in clinical use or the relative neurophysiological study.

Clinical effects of combined bilateral arm training with functional electrical stimulation in patients with stroke.

Cerebral vascular disease (or stroke) is the main cause of disabilities in adults. Upper-limb dysfunction after stroke usually exists, leading to severe limits of motor capabilities as well as daily activities. Therefore, effective treatment interventions for upper-limb rehabilitation after stroke are needed. Based on the neurophysiological evidence and clinical measures, combined bilateral arm training (BAT) with functional electric stimulation (FES) could improve hand function in stroke patients. In this study, we attempt to combine BAT with FES applying to the post-stroke paretic arm. A linear guide platform with FES feedback control was developed to execute the training of bilateral reaching movements. 35 stroke subjects were recruited and divided into two groups (BAT with FES and BAT alone). 23 participants completed this experiment with 3-week intervention. According to our preliminary results, a favorable trend toward improvement in experimental group (BAT with FES) existed after treatment and at follow-up. Further analysis would be conducted to investigate the kinematic change on motor performance. Moreover, various treatment doses as well as more functional approaches would also be considered for better effects of upper limb rehabilitation after stroke.

Safety measures implemented for modular functioning electrical stimulators.

The modular architecture allows for greater flexibility in the building of neural prostheses with a variety of channels but may result in unpredictable accidents under circumstances such as sensor displacements, improper coordination of the connected modules and malfunction of any individual module. A novel fail-safe interface is offered as a solution that puts in place the necessary safety measures when building a module based functional electrical stimulator. By using a single reference line in the interconnecting bus of the modules, various commands would immediately be directed to each module so that proper actions may be taken.