Using Physiological Markers to Assess Comfort during Neuromuscular Electrical Stimulation Induced Muscle Contraction in a Virtually Guided Environment: Pilot Study for a Path toward Combating ICU-Acquired Weakness.

We assessed the feasibility of implementing a virtually guided Neuromuscular Electrical Stimulation (NMES) protocol over the tibialis anterior (TA) muscle while collecting heart rate (HR), Numeric Pain Rating Scale (NPRS), and quality of contraction (QoC) data. We investigated if HR, NPRS, and QoC differ ON and OFF the TA motor point and explored potential relationships between heart rate variability (HRV) and the NPRS. Twelve healthy adults participated in this cross-sectional study. Three NMES trials were delivered ON and OFF the TA motor point. HR, QoC, and NPRS data were collected. There was no significant difference in HRV ON and OFF the motor point (p > 0.05). The NPRS was significantly greater OFF the motor point (p < 0.05). The QoC was significantly different between motor point configurations (p < 0.05). There was no correlation between the NPRS and HRV (p > 0.05, r = -0.129). We recommend non-electrical methods of measuring muscle activity for future studies. The NPRS and QoC can be administered virtually. Time-domain HRV measures could increase the validity of the protocol. The variables should be explored further virtually to enhance the protocol before eventual ICU studies.

Machine learning applications in imaging analysis for patients with pituitary tumors: a review of the current literature and future directions.

PURPOSE: To provide an overview of fundamental concepts in machine learning (ML), review the literature on ML applications in imaging analysis of pituitary tumors for the last 10 years, and highlight the future directions on potential applications of ML for pituitary tumor patients. METHOD: We presented an overview of the fundamental concepts in ML, its various stages used in healthcare, and highlighted the key components typically present in an imaging-based tumor analysis pipeline. A search was conducted across four databases (PubMed, Ovid, Embase, and Google Scholar) to gather research articles from the past 10 years (2009-2019) involving imaging related to pituitary tumor and ML. We grouped the studies by imaging modalities and analyzed the ML tasks in terms of the data inputs, reference standards, methodologies, and limitations. RESULTS: Of the 16 studies included in our analysis, 10 appeared in 2018-2019. Most of the studies utilized retrospective data and followed a semi-automatic ML pipeline. The studies included use of magnetic resonance imaging (MRI), facial photographs, surgical microscopic video, spectrometry, and spectroscopy imaging. The objectives of the studies covered 14 distinct applications and majority of the studies addressed a binary classification problem. Only five of the 11 MRI-based studies had an external validation or a holdout set to test the performance of a final trained model. CONCLUSION: Through our concise evaluation and comparison of the studies using the concepts presented, we highlight future directions so that potential ML applications using different imaging modalities can be developed to benefit the clinical care of pituitary tumor patients.

Fractal Geometry Meets Computational Intelligence: Future Perspectives.

Characterizations in terms of fractals are typically employed for systems with complex and multiscale descriptions. A prominent example of such systems is provided by the human brain, which can be idealized as a complex dynamical system made of many interacting subunits. The human brain can be modeled in terms of observable variables together with their spatio-temporal-functional relations. Computational intelligence is a research field bridging many nature-inspired computational methods, such as artificial neural networks, fuzzy systems, and evolutionary and swarm intelligence optimization techniques. Typical problems faced by means of computational intelligence methods include those of recognition, such as classification and prediction. Although historically conceived to operate in some vector space, such methods have been recently extended to the so-called nongeometric spaces, considering labeled graphs as the most general example of such patterns. Here, we suggest that fractal analysis and computational intelligence methods can be exploited together in neuroscience research. Fractal characterizations can be used to (i) assess scale-invariant properties and (ii) offer numeric, feature-based representations to complement the usually more complex pattern structures encountered in neurosciences. Computational intelligence methods could be used to exploit such fractal characterizations, considering also the possibility to perform data-driven analysis of nongeometric input spaces, therby overcoming the intrinsic limits related to Euclidean geometry.

Machine-learning assisted swallowing assessment: a deep learning-based quality improvement tool to screen for post-stroke dysphagia.

Introduction: Post-stroke dysphagia is common and associated with significant morbidity and mortality, rendering bedside screening of significant clinical importance. Using voice as a biomarker coupled with deep learning has the potential to improve patient access to screening and mitigate the subjectivity associated with detecting voice change, a component of several validated screening protocols. Methods: In this single-center study, we developed a proof-of-concept model for automated dysphagia screening and evaluated the performance of this model on training and testing cohorts. Patients were admitted to a comprehensive stroke center, where primary English speakers could follow commands without significant aphasia and participated on a rolling basis. The primary outcome was classification either as a pass or fail equivalent using a dysphagia screening test as a label. Voice data was recorded from patients who spoke a standardized set of vowels, words, and sentences from the National Institute of Health Stroke Scale. Seventy patients were recruited and 68 were included in the analysis, with 40 in training and 28 in testing cohorts, respectively. Speech from patients was segmented into 1,579 audio clips, from which 6,655 Mel-spectrogram images were computed and used as inputs for deep-learning models (DenseNet and ConvNext, separately and together). Clip-level and participant-level swallowing status predictions were obtained through a voting method. Results: The models demonstrated clip-level dysphagia screening sensitivity of 71% and specificity of 77% (F1 = 0.73, AUC = 0.80 [95% CI: 0.78-0.82]). At the participant level, the sensitivity and specificity were 89 and 79%, respectively (F1 = 0.81, AUC = 0.91 [95% CI: 0.77-1.05]). Discussion: This study is the first to demonstrate the feasibility of applying deep learning to classify vocalizations to detect post-stroke dysphagia. Our findings suggest potential for enhancing dysphagia screening in clinical settings. https://github.com/UofTNeurology/masa-open-source.

A deep neural network approach for sentiment analysis of medically related texts: an analysis of tweets related to concussions in sports.

Annually, over three million people in North America suffer concussions. Every age group is susceptible to concussion, but youth involved in sporting activities are particularly vulnerable, with about 6% of all youth suffering a concussion annually. Youth who suffer concussion have also been shown to have higher rates of suicidal ideation, substance and alcohol use, and violent behaviors. A significant body of research over the last decade has led to changes in policies and laws intended to reduce the incidence and burden of concussions. However, it is also clear that youth engaging in high-risk activities like sport often underreport concussion, while others may embellish reports for specific purposes. For such policies and laws to work, they must operate effectively within a facilitative social context so understanding the culture around concussion becomes essential to reducing concussion and its consequences. We present an automated deep neural network approach to analyze tweets with sport-related concussion context to identify the general public's sentiment towards concerns in sport-related concussion. A single-layer and multi-layer convolutional neural networks, Long Short-Term Memory (LSTM) networks, and Bidirectional LSTM were trained to classify the sentiments of the tweets. Afterwards, we train an ensemble model to aggregate the predictions of our networks to provide a final decision of the tweet's sentiment. The system achieves an evaluation F1 score of 62.71% based on Precision and Recall. The trained system is then used to analyze the tweets in the FIFA World Cup 2018 to measure audience reaction to events involving concussion. The neural network system provides an understanding of the culture around concussion through sentiment analysis.

Using artificial neural networks to identify patients with concussion and postconcussion syndrome based on antisaccades.

OBJECTIVEArtificial neural networks (ANNs) have shown considerable promise as decision support tools in medicine, including neurosurgery. However, their use in concussion and postconcussion syndrome (PCS) has been limited. The authors explore the value of using an ANN to identify patients with concussion/PCS based on their antisaccade performance.METHODSStudy participants were prospectively recruited from the emergency department and head injury clinic of a large teaching hospital in Toronto. Acquaintances of study participants were used as controls. Saccades were measured using an automated, portable, head-mounted device preprogrammed with an antisaccade task. Each participant underwent 100 trials of the task and 11 saccade parameters were recorded for each trial. ANN analysis was performed using the MATLAB Neural Network Toolbox, and individual saccade parameters were further explored with receiver operating characteristic (ROC) curves and a logistic regression analysis.RESULTSControl (n = 15), concussion (n = 32), and PCS (n = 25) groups were matched by age and level of education. The authors examined 11 saccade parameters and found that the prosaccade error rate (p = 0.04) and median antisaccade latency (p = 0.02) were significantly different between control and concussion/PCS groups. When used to distinguish concussion and PCS participants from controls, the neural networks achieved accuracies of 67% and 72%, respectively. This method was unable to distinguish study patients with concussion from those with PCS, suggesting persistence of eye movement abnormalities in patients with PCS. The authors' observations also suggest the potential for improved results with a larger training sample.CONCLUSIONSThis study explored the utility of ANNs in the diagnosis of concussion/PCS based on antisaccades. With the use of an ANN, modest accuracy was achieved in a small cohort. In addition, the authors explored the pearls and pitfalls of this novel approach and identified important future directions for this research.

Effects of high amylose corn starch and microbial transglutaminase on the textural and microstructural properties of wheat flour composite gels at high temperatures.

Textural and microstructural properties of composite gels (CGs), along with wheat flour and high amylose corn starch (Hylon VII) mixed with microbial transglutaminase (MTGase) at different levels and temperatures were investigated. The results showed by increasing Hylon starch content, the firmness increased and adhesiveness decreased. Indeed, high level of amylose and cross-linking formed by MTGase enhanced the gel elasticity and reduced adhesiveness. Moreover, MTGase had more effect on the firmness and provided more cross-linked intermolecular gel structures at high temperatures. By adding MTGase to the CG, the lowest peak viscosity and final viscosity were found for 15% of Hylon starch. As the more Hylon content in the CG, the more water solubility index was particularly obtained at high temperature. Scanning electron microscopy (SEM) results showed that MTGase and Hylon starch addition enhanced the structure. The differences in SEM of CG were reflected the pasting properties of the gels. Consequently, MTGase treated gels can withstand high temperature as well as maintain the overall structure of the samples gels. Therefore, the increment of Hylon to the CG gels supplied tighter, stronger, and denser protein network which were formed by MTGase cross-linking within the network of starch and proteins. PRACTICAL APPLICATIONS: Although, transglutaminase was practically used in the production of noodles and pasta in Japan, but there is little academic and industrial knowledge concerning its utilization in the pasta or noodles. Moreover, long shelf-life noodle/pasta products have become popular in the Japanese market and in the emergency conditions like as floods or earthquake, but they can be stored for at least 5 months by applying heat treatment at 95C. Here, high amylose corn starch as a resistant starch, wheat flour, and microbial transglutaminase (MTGase) were selected as the main components in the composite gel (CG) systems to elucidate the effects of MTGase and Hylon on the texture, microstructure, and pasting behavior of CGs at high temperatures to produce long-life noodle/pasta products (about 2 years) through retort processing.

Physicochemical, functional, and nutritional characteristics of stabilized rice bran form tarom cultivar.

Extrusion is a multistep thermal process which has been utilized in a wide spectrum of food preparations. The effect of extrusion processing on the physicochemical, nutritional, and functional properties of Tarom cultivar rice bran was studied. However, the color of rice bran was improved by extrusion processing, but the protein content was reduced in the stabilized rice bran, which can be related to the denaturation of protein. Extrusion had also a reduction significant effect on the phytic acid as well as vitamin E in rice bran. However, the content of niacin, riboflavin, pantothenic acid, and folic acid remained unchanged, but the dietary fiber was enhanced which has beneficial health effect on human consumption. In comparison with unstabilized rice bran, water holding capacity was enhanced, but the oil absorption capacity was reduced. Foaming capacity and foaming stability of extruded rice bran was more than that of untreated rice bran, although they were less than that of rice bran protein concentrate/isolate. In general, the extrusion process improves some functional and nutritional properties of rice bran which are valuable to industrial applications and have potential as ingredient in food to improve consumer health.

Discrimination and Characterization of Parkinsonian Rest Tremors by Analyzing Long-Term Correlations and Multifractal Signatures.

GOAL: We analyze 48 signals of rest tremor velocity related to 12 distinct subjects affected by the Parkinson's disease. The subjects belong to two different groups, high- and low-amplitude rest tremors, with four and eight subjects, respectively. Each subject has been tested in four settings given by combining the use of deep brain stimulation and L-DOPA medication. METHODS: We develop two main feature-based representations of the signals, which are obtained by considering 1) the long-term correlations and multifractal properties, and 2) the power spectra. RESULTS: Our results show that, when medication is used, a qualitative change is observed in the related signals from anticorrelated to long term positively correlated. In addition, the medication effect yields statistically significant differences in both high- and low-amplitude tremor groups. We successively consider three different classification problems, involving the recognition of 1) the use of medication, 2) the use of deep brain stimulation, and 3) the membership to the high- and low-amplitude tremor groups. Classification results show that the best results are obtained with a parsimonious, two-dimensional (2-D) representation encoding the long-term correlations and multifractal properties of the signals. CONCLUSIONS: Long-term correlations and multifractal signatures of time series provided an effective tool to analyze Parkinsonian rest tremor signals. SIGNIFICANCE: The developed 2-D representation is a parsimonious and effective representation for rest tremor signals that could be adopted in clinical settings, even by considering resource-constrained scenarios.

A generative model for protein contact networks.

In this paper, we present a generative model for protein contact networks (PCNs). The soundness of the proposed model is investigated by focusing primarily on mesoscopic properties elaborated from the spectra of the graph Laplacian. To complement the analysis, we also study the classical topological descriptors, such as statistics of the shortest paths and the important feature of modularity. Our experiments show that the proposed model results in a considerable improvement with respect to two suitably chosen generative mechanisms, mimicking with better approximation real PCNs in terms of diffusion properties elaborated from the normalized Laplacian spectra. However, as well as the other network models, it does not reproduce with sufficient accuracy the shortest paths structure. To compensate this drawback, we designed a second step involving a targeted edge reconfiguration process. The ensemble of reconfigured networks denotes further improvements that are statistically significant. As an important byproduct of our study, we demonstrate that modularity, a well-known property of proteins, does not entirely explain the actual network architecture characterizing PCNs. In fact, we conclude that modularity, intended as a quantification of an underlying community structure, should be considered as an emergent property of the structural organization of proteins. Interestingly, such a property is suitably optimized in PCNs together with the feature of path efficiency.

Entropic One-Class Classifiers.

The one-class classification problem is a well-known research endeavor in pattern recognition. The problem is also known under different names, such as outlier and novelty/anomaly detection. The core of the problem consists in modeling and recognizing patterns belonging only to a so-called target class. All other patterns are termed nontarget, and therefore, they should be recognized as such. In this paper, we propose a novel one-class classification system that is based on an interplay of different techniques. Primarily, we follow a dissimilarity representation-based approach; we embed the input data into the dissimilarity space (DS) by means of an appropriate parametric dissimilarity measure. This step allows us to process virtually any type of data. The dissimilarity vectors are then represented by weighted Euclidean graphs, which we use to determine the entropy of the data distribution in the DS and at the same time to derive effective decision regions that are modeled as clusters of vertices. Since the dissimilarity measure for the input data is parametric, we optimize its parameters by means of a global optimization scheme, which considers both mesoscopic and structural characteristics of the data represented through the graphs. The proposed one-class classifier is designed to provide both hard (Boolean) and soft decisions about the recognition of test patterns, allowing an accurate description of the classification process. We evaluate the performance of the system on different benchmarking data sets, containing either feature-based or structured patterns. Experimental results demonstrate the effectiveness of the proposed technique.

Prediction of telephone calls load using Echo State Network with exogenous variables.

We approach the problem of forecasting the load of incoming calls in a cell of a mobile network using Echo State Networks. With respect to previous approaches to the problem, we consider the inclusion of additional telephone records regarding the activity registered in the cell as exogenous variables, by investigating their usefulness in the forecasting task. Additionally, we analyze different methodologies for training the readout of the network, including two novel variants, namely ν-SVR and an elastic net penalty. Finally, we employ a genetic algorithm for both the tasks of tuning the parameters of the system and for selecting the optimal subset of most informative additional time-series to be considered as external inputs in the forecasting problem. We compare the performances with standard prediction models and we evaluate the results according to the specific properties of the considered time-series.

Quantitative ultrasound spectroscopic imaging for characterization of disease extent in prostate cancer patients.

Three-dimensional quantitative ultrasound spectroscopic imaging of prostate was investigated clinically for the noninvasive detection and extent characterization of disease in cancer patients and compared to whole-mount, whole-gland histopathology of radical prostatectomy specimens. Fifteen patients with prostate cancer underwent a volumetric transrectal ultrasound scan before radical prostatectomy. Conventional-frequency (~5MHz) ultrasound images and radiofrequency data were collected from patients. Normalized power spectra were used as the basis of quantitative ultrasound spectroscopy. Specifically, color-coded parametric maps of 0-MHz intercept, midband fit, and spectral slope were computed and used to characterize prostate tissue in ultrasound images. Areas of cancer were identified in whole-mount histopathology specimens, and disease extent was correlated to that estimated from quantitative ultrasound parametric images. Midband fit and 0-MHz intercept parameters were found to be best associated with the presence of disease as located on histopathology whole-mount sections. Obtained results indicated a correlation between disease extent estimated noninvasively based on midband fit parametric images and that identified histopathologically on prostatectomy specimens, with an r(2) value of 0.71 (P<.0001). The 0-MHz intercept parameter demonstrated a lower level of correlation with histopathology. Spectral slope parametric maps offered no discrimination of disease. Multiple regression analysis produced a hybrid disease characterization model (r(2)=0.764, P<.05), implying that the midband fit biomarker had the greatest correlation with the histopathologic extent of disease. This work demonstrates that quantitative ultrasound spectroscopic imaging can be used for detecting prostate cancer and characterizing disease extent noninvasively, with corresponding gross three-dimensional histopathologic correlation.

Low-frequency quantitative ultrasound imaging of cell death in vivo.

PURPOSE: Currently, no clinical imaging modality is used routinely to assess tumor response to cancer therapies within hours to days of the delivery of treatment. Here, the authors demonstrate the efficacy of ultrasound at a clinically relevant frequency to quantitatively detect changes in tumors in response to cancer therapies using preclinical mouse models. METHODS: Conventional low-frequency and corresponding high-frequency ultrasound (ranging from 4 to 28 MHz) were used along with quantitative spectroscopic and signal envelope statistical analyses on data obtained from xenograft tumors treated with chemotherapy, x-ray radiation, as well as a novel vascular targeting microbubble therapy. RESULTS: Ultrasound-based spectroscopic biomarkers indicated significant changes in cell-death associated parameters in responsive tumors. Specifically changes in the midband fit, spectral slope, and 0-MHz intercept biomarkers were investigated for different types of treatment and demonstrated cell-death related changes. The midband fit and 0-MHz intercept biomarker derived from low-frequency data demonstrated increases ranging approximately from 0 to 6 dBr and 0 to 8 dBr, respectively, depending on treatments administrated. These data paralleled results observed for high-frequency ultrasound data. Statistical analysis of ultrasound signal envelope was performed as an alternative method to obtain histogram-based biomarkers and provided confirmatory results. Histological analysis of tumor specimens indicated up to 61% cell death present in the tumors depending on treatments administered, consistent with quantitative ultrasound findings indicating cell death. Ultrasound-based spectroscopic biomarkers demonstrated a good correlation with histological morphological findings indicative of cell death (r2=0.71, 0.82; p<0.001). CONCLUSIONS: In summary, the results provide preclinical evidence, for the first time, that quantitative ultrasound used at a clinically relevant frequency, in addition to high-frequency ultrasound, can detect tissue changes associated with cell death in vivo in response to cancer treatments.

Feedback associative memory based on a new hybrid model of generalized regression and self-feedback neural networks.

The focus of this paper is to propose a hybrid neural network model for associative recall of analog and digital patterns. This hybrid model consists of self-feedback neural network structures (SFNN) in parallel with generalized regression neural networks (GRNN). Using a new one-shot learning algorithm developed in the paper, pattern representations are first stored as the asymptotically stable fixed points of the SFNN. Then in the retrieving process, each pattern is applied to the GRNN to make the corresponding initial condition and to initiate the dynamical equations of the SFNN that should in turn output the corresponding representation. In this way, the corresponding stored patterns are retrieved even under high noise degradation. Moreover, contrary to many associative memories, the proposed hybrid model is without any spurious attractors and can store both binary and real-value patterns without any preprocessing. Several simulations confirm the theoretical analyses of the model. Results indicate that the performance of the hybrid model is better than that of recurrent associative memory and competitive with other classes of networks.