Volume 68, Issue 4

Leg exercises through standing, cycling and walking with/without FES may be used to preserve lower limb muscle and bone health in persons with physical disability due to SCI. This study sought to examine the effectiveness of leg exercises on bone mineral density and muscle cross-sectional area based on their clinical efficacy in persons with SCI. Several literature databases were searched for potential eligible studies from the earliest return date to January 2022. The primary outcome targeted was the change in muscle mass/volume and bone mineral density as measured by CT, MRI and similar devices. Relevant studies indicated that persons with SCI that undertook FES- and frame-supported leg exercise exhibited better improvement in muscle and bone health preservation in comparison to those who were confined to frame-assisted leg exercise only. However, this observation is only valid for exercise initiated early (i.e., within 3 months after injury) and for ≥30 min/day for ≥ thrice a week and for up to 24 months or as long as desired and/or tolerable. Consequently, apart from the positive psychological effects on the users, leg exercise may reduce fracture rate and its effectiveness may be improved if augmented with FES.

Objectives Several studies have revealed that after spinal cord injury (SCI), in acute and sub-acute phase the spinal cord neurons below the injury are alive and could stimulate by use of electrical pulses. Spinal cord electrical stimulation could generate movement for paralyzed limbs and is a rehabilitation strategy for paralyzed patients. An innovative idea for controlling spinal cord electrical stimulation onset time is presented in current study. Methods In our method, the time of applying electrical pulse on the spinal cord is according to rat behavioral movement and two movements behaviors are recognized only based on rat EEG theta rhythm on the treadmill line. Briefly, 5 rats were placed on the treadmill and the animals experienced zero or 12 m/min speeds. Results These speeds were recognized based on EEG signals and off-line periodogram analysis. Finally, the electrical stimulation pulses had been applied to the spinal cord if the results of the EEG analysis had detected running behavior. Conclusions These findings may guide future research in utilizing theta rhythms for the recognition of animal motor behavior and designing electrical stimulation systems based on it.

Driver states are reported as one of the principal factors in driving safety. Distinguishing the driving driver state based on the artifact-free electroencephalogram (EEG) signal is an effective means, but redundant information and noise will inevitably reduce the signal-to-noise ratio of the EEG signal. This study proposes a method to automatically remove electrooculography (EOG) artifacts by noise fraction analysis. Specifically, multi-channel EEG recordings are collected after the driver experiences a long time driving and after a certain period of rest respectively. Noise fraction analysis is then applied to remove EOG artifacts by separating the multichannel EEG into components by optimizing the signal-to-noise quotient. The representation of data characteristics of the EEG after denoising is found in the Fisher ratio space. Additionally, a novel clustering algorithm is designed to identify denoising EEG by combining cluster ensemble and probability mixture model (CEPM). The EEG mapping plot is used to illustrate the effectiveness and efficiency of noise fraction analysis on the denoising of EEG signals. Adjusted rand index (ARI) and accuracy (ACC) are used to demonstrate clustering performance and precision. The results showed that the noise artifacts in the EEG were removed and the clustering accuracy of all participants was above 90%, resulting in a high driver fatigue recognition rate.

Millions of people around the world are affected by different kinds of epileptic seizures. A deep brain stimulator is now claimed to be one of the most promising tools to control severe epileptic seizures. The present study proposes Hodgkin-Huxley (HH) model-based Active Fault Tolerant Deep Brain Stimulator (AFTDBS) for brain neurons to suppress epileptic seizures against ion channel conductance variations using a Deep Neural Network (DNN). The AFTDBS contains the following three modules: (i) Detection of epileptic seizures using black box classifiers such as Support Vector Machine (SVM) and K-Nearest Neighbor (KNN), (ii) Prediction of ion channels conductance variations using Long Short-Term Memory (LSTM), and (iii) Development of Reconfigurable Deep Brain Stimulator (RDBS) to control epileptic spikes using Proportional Integral (PI) Controller and Model Predictive Controller (MPC). Initially, the synthetic data were collected from the HH model by varying ion channel conductance. Then, the seizure was classified into four groups namely, normal and epileptic due to variations in sodium ion-channel conductance, potassium ion-channel conductance, and both sodium and potassium ion-channel conductance. In the present work, current controlled deep brain stimulators were designed for epileptic suppression. Finally, the closed-loop performances and stability of the proposed control schemes were analyzed. The simulation results demonstrated the efficacy of the proposed DNN-based AFTDBS.

Objectives Atrial Tachycardia (AT) and Left Atrial Enlargement (LAE) are atrial diseases that are significant precursors to Atrial Fibrillation (AF). There are ML models for ECG classification; clinical features-based classification is required. The suggested work aims to create stacked ML models that categorize Sinus Rhythm (SR), Sinus Tachycardia (ST), AT, and LAE signals based on clinical parameters for AF prognosis. Methods The classification was based on thirteen clinical parameters, such as amplitude, time domain ECG aspects, and P-Wave Indices (PWI), such as the ratio of P-wave length and amplitude ((P (ms)/P (µV)), P-wave area (µV*ms), and P-wave terminal force (PTFV1(µV*ms). Apart from classifying the ECG signals, the stacked ML models prioritized the clinical features using a pie formula-based technique. Results The Stack 1 model achieves 99% accuracy, sensitivity, precision, and F1 score, while the Stack 2 model achieves 91%, 91%, 94%, and 92% for identifying SR, ST, LAE, and AT, respectively. Both stack models obtained a computational time of 0.06 seconds. PTFV1 (µV*ms), P (ms)/P (µV)), and P-wave area (µV*ms) were ranked as crucial clinical features. Conclusion Clinical feature-based stacking ML models may help doctors obtain insight into important clinical ECG aspects for early AF prediction.

Objectives Currently, a multitude of machine learning techniques are available for the diagnosis of hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) by utilizing electrocardiography (ECG) data. However, these methods rely on digital versions of ECG data, while in practice, numerous ECG data still exist in paper form. As a result, the accuracy of the existing machine learning diagnostic models is suboptimal in practical scenarios. In order to enhance the accuracy of machine learning models for diagnosing cardiomyopathy, we propose a multimodal machine learning model capable of diagnosing both HCM and DCM. Methods Our study employed an artificial neural network (ANN) for feature extraction from both the echocardiogram report form and biochemical examination data. Furthermore, a convolutional neural network (CNN) was utilized for feature extraction from the electrocardiogram (ECG). The resulting extracted features were subsequently integrated and inputted into a multilayer perceptron (MLP) for diagnostic classification. Results Our multimodal fusion model achieved a precision of 89.87%, recall of 91.20%, F1 score of 89.13%, and precision of 89.72%. Conclusions Compared to existing machine learning models, our proposed multimodal fusion model has achieved superior results in various performance metrics. We believe that our method is effective.

Objectives The identification of the intersegmental plane is a major interoperative challenges during pulmonary segmentectomies. The objective of this pilot study is to test the feasibility of lung perfusion assessment by Hyperspectral Imaging for identification of the intersegmental plane. Methods A pilot study (clinicaltrials.org: NCT04784884) was conducted in patients with lung cancer. Measuring tissue oxygenation (StO 2 ; upper tissue perfusion), organ hemoglobin index (OHI), near-infrared index (NIR; deeper tissue perfusion) and tissue water index (TWI), the Hyperspectral Imaging measurements were carried out in inflated (P vent ) and deflated pulmonary lobes (P nV ) as well as in deflated pulmonary lobes with divided circulation (P nVC ) before dissection of the lobar bronchus. Results A total of 341 measuring points were evaluated during pulmonary lobectomies. Pulmonary lobes showed a reduced StO2 (P vent : 84.56% ± 3.92 vs. P nV : 63.62% ± 11.62 vs. P nVC : 39.20% ± 23.57; p<0.05) and NIR-perfusion (P vent : 50.55 ± 5.62 vs. P nV : 47.55 ± 3.38 vs. P nVC : 27.60 ± 9.33; p<0.05). There were no differences of OHI and TWI between the three groups. Conclusions This pilot study demonstrates that HSI enables differentiation between different ventilated and perfused pulmonary tissue as a precondition for HSI segment mapping.

Objectives Hyperspectral imaging is an emerging imaging modality that beginning to gain attention for medical research and has an important potential in clinical applications. Nowadays, spectral imaging modalities such as multispectral and hyperspectral have proven their ability to provide important information that can help to better characterize the wound. Oxygenation changes in the wounded tissue differ from normal tissue. This causes the spectral characteristics to be different. In this study, it is classified cutaneous wounds with neighbourhood extraction 3-dimensional convolutional neural network method. Methods The methodology of hyperspectral imaging performed to obtain the most useful information about the wounded and normal tissue is explained in detail. When the hyperspectral signatures of wounded and normal tissues are compared on the hyperspectral image, it is revealed that there is a relative difference between them. By taking advantage of these differences, cuboids that also consider neighbouring pixels are generated, and a uniquely designed 3-dimensional convolutional neural network model is trained with the cuboids to extract both spatial and spectral information. Results The effectiveness of the proposed method was evaluated for different cuboid spatial dimensions and training/testing rates. The best result with 99.69% was achieved when the training/testing rate was 0.9/0.1 and the cuboid spatial dimension was 17. It is observed that the proposed method outperforms the 2-dimensional convolutional neural network method and achieves high accuracy even with much less training data. The obtained results using the neighbourhood extraction 3-dimensional convolutional neural network method show that the proposed method highly classifies the wounded area. In addition, the classification performance and the2computation time of the neighbourhood extraction 3-dimensional convolutional neural network methodology were analyzed and compared with existing 2-dimensional convolutional neural network. Conclusions As a clinical diagnostic tool, hyperspectral imaging, with neighbourhood extraction 3-dimensional convolutional neural network, has yielded remarkable results for the classification of wounded and normal tissues. Skin color does not play any role in the success of the proposed method. Since only the reflectance values of the spectral signatures are different for various skin colors. For different ethnic groups, The spectral signatures of wounded tissue and the spectral signatures of normal tissue show similar spectral characteristics among themselves.

The strength of zirconia ceramic materials used in restorations is dependent upon sintering. Varying sintering protocols may affect the biaxial flexural strength of zirconia materials. This in vitro study was conducted to investigate the effects of sintering parameters on the biaxial flexural strength of monolithic zirconia. Two different monoblock zirconia ceramics were used. Following coloration, samples of both types of ceramics were divided into groups according to whether or not biaxial flexural strength testing was performed directly after sintering or following thermocycling. Biaxial flexural strength data was analysed with a Shapiro Wilk normality test, followed by 1-way ANOVA, Tukey post hoc tests for inter-group comparisons, and paired samples t-tests for intra-group comparisons. A significant difference was found between the biaxial flexural strengths of Zircon X and Upcera ceramics before thermocycling (p<0.05). In both Zircon X and Upcera ceramic groups, the thermocycling process created a significant difference in the biaxial flexural strength values of the ceramic samples in Group 6 (p<0.05) which had the slowest heating rate and longest holding time. The zirconia ceramics have higher BFS at higher heating rates either before or after thermocycling. The holding time has significant effects on thermocycling and flexural strength. The zirconia achieved its optimum strength when it sintered at longer time regardless of heating rates.