Real-World Data from the First U.S. Commercial Users of an Implantable Continuous Glucose Sensor.

Background: The Eversense® Continuous Glucose Monitoring (CGM) System, with the first 90-day implantable sensor, received FDA (Food and Drug Administration) approval in June 2018. No real-world experience has been published. Methods: Deidentified sensor glucose (SG) data from August 1, 2018 to May 11, 2019 in the Eversense Data Management System (DMS) were analyzed for the first 205 patients who reached a 90-day wear period on the Eversense CGM system. The mean SG, standard deviation (SD), median interquartile range, coefficient of variation (CV), glucose measurement index (GMI), and percent and time in minutes across glucose ranges were computed for the 24-h time period, the nighttime (00:00-06:00), and by 30-day wear periods. Sensor accuracy, sensor reinsertion rate, transmitter wear time, and safety data were assessed. Results: Of the 205 patients, 129 identified as type 1, 18 as type 2, and 58 were unreported. Fifty were CGM naive, 112 had prior CGM experience, and 43 were unreported. The mean SG was 161.8 mg/dL, SD was 57.4 mg/dL, CV was 0.35, and GMI was 7.18%. Percent SG at <54 mg/dL was 1.2% (18 min), <70 mg/dL was 4.1% (59.7 min), time in range (≥70-180 mg/dL) was 62.3% (897.7 min), >180-250 mg/dL was 21.9% (315.8 min), and >250 mg/dL was 11.6% (166.7 min). Nighttime values were similar. The glucometric values were similar over 30-day time periods of the sensor wear. The mean absolute relative difference (SD) using 27,708 calibration paired points against home blood glucose meters was 11.2% (11.3%). The sensor reinsertion rate was 78.5%. The median transmitter wear time was 83.6%. There were no related serious adverse events. Conclusion: The Eversense real-world data showed promising glycemic results, sensor accuracy, and safety. These data suggest that the Eversense CGM system is a valuable tool for diabetes management.

Increased prognostic accuracy of TBI when a brain electrical activity biomarker is added to loss of consciousness (LOC).

BACKGROUND: Extremely high accuracy for predicting CT+ traumatic brain injury (TBI) using a quantitative EEG (QEEG) based multivariate classification algorithm was demonstrated in an independent validation trial, in Emergency Department (ED) patients, using an easy to use handheld device. This study compares the predictive power using that algorithm (which includes LOC and amnesia), to the predictive power of LOC alone or LOC plus traumatic amnesia. PARTICIPANTS: ED patients 18-85years presenting within 72h of closed head injury, with GSC 12-15, were study candidates. 680 patients with known absence or presence of LOC were enrolled (145 CT+ and 535 CT- patients). METHODS: 5-10min of eyes closed EEG was acquired using the Ahead 300 handheld device, from frontal and frontotemporal regions. The same classification algorithm methodology was used for both the EEG based and the LOC based algorithms. Predictive power was evaluated using area under the ROC curve (AUC) and odds ratios. RESULTS: The QEEG based classification algorithm demonstrated significant improvement in predictive power compared with LOC alone, both in improved AUC (83% improvement) and odds ratio (increase from 4.65 to 16.22). Adding RGA and/or PTA to LOC was not improved over LOC alone. CONCLUSIONS: Rapid triage of TBI relies on strong initial predictors. Addition of an electrophysiological based marker was shown to outperform report of LOC alone or LOC plus amnesia, in determining risk of an intracranial bleed. In addition, ease of use at point-of-care, non-invasive, and rapid result using such technology suggests significant value added to standard clinical prediction.

Classification algorithms for the identification of structural injury in TBI using brain electrical activity.

BACKGROUND: There is an urgent need for objective criteria adjunctive to standard clinical assessment of acute Traumatic Brain Injury (TBI). Details of the development of a quantitative index to identify structural brain injury based on brain electrical activity will be described. METHODS: Acute closed head injured and normal patients (n=1470) were recruited from 16 US Emergency Departments and evaluated using brain electrical activity (EEG) recorded from forehead electrodes. Patients had high GCS (median=15), and most presented with low suspicion of brain injury. Patients were divided into a CT positive (CT+) group and a group with CT negative findings or where CT scans were not ordered according to standard assessment (CT-/CT_NR). Three different classifier methodologies, Ensemble Harmony, Least Absolute Shrinkage and Selection Operator (LASSO), and Genetic Algorithm (GA), were utilized. RESULTS: Similar performance accuracy was obtained for all three methodologies with an average sensitivity/specificity of 97.5%/59.5%, area under the curves (AUC) of 0.90 and average Negative Predictive Validity (NPV)>99%. Sensitivity was highest for CT+ cases with potentially life threatening hematomas, where two of three classifiers were 100%. CONCLUSION: Similar performance of these classifiers suggests that the optimal separation of the populations was obtained given the overlap of the underlying distributions of features of brain activity. High sensitivity to CT+ injuries (highest in hematomas) and specificity significantly higher than that obtained using ED guidelines for imaging, supports the enhanced clinical utility of this technology and suggests the potential role in the objective, rapid and more optimal triage of TBI patients.

Spiking neural networks.

Most current Artificial Neural Network (ANN) models are based on highly simplified brain dynamics. They have been used as powerful computational tools to solve complex pattern recognition, function estimation, and classification problems. ANNs have been evolving towards more powerful and more biologically realistic models. In the past decade, Spiking Neural Networks (SNNs) have been developed which comprise of spiking neurons. Information transfer in these neurons mimics the information transfer in biological neurons, i.e., via the precise timing of spikes or a sequence of spikes. To facilitate learning in such networks, new learning algorithms based on varying degrees of biological plausibility have also been developed recently. Addition of the temporal dimension for information encoding in SNNs yields new insight into the dynamics of the human brain and could result in compact representations of large neural networks. As such, SNNs have great potential for solving complicated time-dependent pattern recognition problems because of their inherent dynamic representation. This article presents a state-of-the-art review of the development of spiking neurons and SNNs, and provides insight into their evolution as the third generation neural networks.

A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection.

A new Multi-Spiking Neural Network (MuSpiNN) model is presented in which information from one neuron is transmitted to the next in the form of multiple spikes via multiple synapses. A new supervised learning algorithm, dubbed Multi-SpikeProp, is developed for training MuSpiNN. The model and learning algorithm employ the heuristic rules and optimum parameter values presented by the authors in a recent paper that improved the efficiency of the original single-spiking Spiking Neural Network (SNN) model by two orders of magnitude. The classification accuracies of MuSpiNN and Multi-SpikeProp are evaluated using three increasingly more complicated problems: the XOR problem, the Fisher iris classification problem, and the epilepsy and seizure detection (EEG classification) problem. It is observed that MuSpiNN learns the XOR problem in twice the number of epochs compared with the single-spiking SNN model but requires only one-fourth the number of synapses. For the iris and EEG classification problems, a modular architecture is employed to reduce each 3-class classification problem to three 2-class classification problems and improve the classification accuracy. For the complicated EEG classification problem a classification accuracy in the range of 90.7%-94.8% was achieved, which is significantly higher than the 82% classification accuracy obtained using the single-spiking SNN with SpikeProp.

A spatio-temporal wavelet-chaos methodology for EEG-based diagnosis of Alzheimer's disease.

A spatio-temporal wavelet-chaos methodology is presented for analysis of EEGs and their delta, theta, alpha, and beta sub-bands for discovering potential markers of abnormality in Alzheimer's disease (AD). The non-linear dynamics of the EEG and EEG sub-bands are quantified in the form of the correlation dimension (CD), representing system complexity, and the largest Lyapunov exponent (LLE), representing system chaoticity. The methodology is applied to two groups of EEGs: healthy subjects and AD patients. The eyes open and eyes closed conditions are investigated to evaluate the effect of visual input and attention. EEGs from different loci in the brain are investigated to discover areas of the brain responsible for or affected by changes in CD and LLE. It is found that the wavelet-chaos methodology and the sub-band analysis developed in this research accurately characterizes the non-linear dynamics of non-stationary EEG-like signals with respect to the EEG complexity and chaoticity. It is concluded that changes in the brain dynamics are not spread out equally across the spectrum of the EEG and over the entire brain, but are localized to certain frequency bands and electrode loci. New potential markers of abnormality were discovered in this research for both eyes open and closed conditions.

Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection.

A novel principal component analysis (PCA)-enhanced cosine radial basis function neural network classifier is presented. The two-stage classifier is integrated with the mixed-band wavelet-chaos methodology, developed earlier by the authors, for accurate and robust classification of electroencephalogram (EEGs) into healthy, ictal, and interictal EEGs. A nine-parameter mixed-band feature space discovered in previous research for effective EEG representation is used as input to the two-stage classifier. In the first stage, PCA is employed for feature enhancement. The rearrangement of the input space along the principal components of the data improves the classification accuracy of the cosine radial basis function neural network (RBFNN) employed in the second stage significantly. The classification accuracy and robustness of the classifier are validated by extensive parametric and sensitivity analysis. The new wavelet-chaos-neural network methodology yields high EEG classification accuracy (96.6%) and is quite robust to changes in training data with a low standard deviation of 1.4%. For epilepsy diagnosis, when only normal and interictal EEGs are considered, the classification accuracy of the proposed model is 99.3%. This statistic is especially remarkable because even the most highly trained neurologists do not appear to be able to detect interictal EEGs more than 80% of the times.

Autonomic mechanisms and therapeutic implications of postural diabetic cardiovascular abnormalities.

BACKGROUND: Cardiovascular autonomic neuropathy (CAN) is a disorder of progressive autonomic dysfunction (AD) associated with diabetes and other chronic diseases. Orthostatic hypotension (OH) is one of the most incapacitating symptoms of CAN and AD. AD in OH can include sympathetic withdrawal (SW). To detect and diagnose SW, parasympathetic and sympathetic changes must be clearly differentiated from each other. This is accomplished by means of the novel autonomic nervous system (ANS) method based on the simultaneous spectral analyses of respiratory activity (RA) and heart rate variability (HRV). METHODS: We performed autonomic profiling of 184 (142 females) consecutive, arrhythmia-free patients with type 2 diabetes using the ANX-3.0 autonomic monitoring system. The patient cohort included 86 (64 female) patients for whom an alpha(1)-agonist was the only drug changed and increased from one test to the next; 37 (33 female) for whom the alpha(1)-agonist was discontinued; and 61 (45 female) who were on an alpha(1)-agonist, but for whom no drug changes were made. The tests averaged 3.1 +/- 1.4 months apart; midodrine (ProAmatine) was the alpha(1)-agonist prescribed. Of the group, 99 patients also had hypertension and 47 also had cardiovascular disease. No patient had supine hypertension. RESULTS: Changes in parameters from the HRV (without respiration) and ANS methods were compared with changes in heart rate and blood pressure (BP) as measured from one test (test N) to the next (test N + 1). SW with a BP drop of less than the clinical definition may be a trend that can be an early indicator of orthostasis. In this study, patients were treated with low-dose, short-term alpha(1)-agonist (vasopressor) therapy, which tended to correct the abnormal trend of SW with a drop in BP. Included in the findings was a systolic BP trend in response to vasopressor therapy of an (expected) initial increase in BP followed by an eventual decrease in systolic BP as SW was reversed. CONCLUSIONS: The ANS method enables quantitative assessment of CAN by independently and simultaneously quantifying the two branches of the ANS, sympathetic and parasympathetic. The ANS method modifies standard spectral analysis of HRV (without RA analysis) by incorporating spectral analysis of RA. The ANS method appears to model the normal and abnormal responses to upright posture and changes in vasopressor therapy with greater fidelity than the HRV method. Independent, simultaneous assessment of progressive parasympathetic and sympathetic dysfunction, autonomic imbalance, and responses of the two ANS branches to therapy seems to enable early detection and early intervention. Orthostasis, by way of example, illustrates that frequent, sensitive assessments of both ANS branches can improve the negative outcomes associated with CAN.

Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection.

A novel wavelet-chaos-neural network methodology is presented for classification of electroencephalograms (EEGs) into healthy, ictal, and interictal EEGs. Wavelet analysis is used to decompose the EEG into delta, theta, alpha, beta, and gamma sub-bands. Three parameters are employed for EEG representation: standard deviation (quantifying the signal variance), correlation dimension, and largest Lyapunov exponent (quantifying the non-linear chaotic dynamics of the signal). The classification accuracies of the following techniques are compared: (1) unsupervised k-means clustering; (2) linear and quadratic discriminant analysis; (3) radial basis function neural network; (4) Levenberg-Marquardt backpropagation neural network (LMBPNN). To reduce the computing time and output analysis, the research was performed in two phases: band-specific analysis and mixed-band analysis. In phase two, over 500 different combinations of mixed-band feature spaces consisting of promising parameters from phase one of the research were investigated. It is concluded that all three key components of the wavelet-chaos-neural network methodology are important for improving the EEG classification accuracy. Judicious combinations of parameters and classifiers are needed to accurately discriminate between the three types of EEGs. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy, a high value of 96.7%.

A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy.

A wavelet-chaos methodology is presented for analysis of EEGs and delta, theta, alpha, beta, and gamma subbands of EEGs for detection of seizure and epilepsy. The nonlinear dynamics of the original EEGs are quantified in the form of the correlation dimension (CD, representing system complexity) and the largest Lyapunov exponent (LLE, representing system chaoticity). The new wavelet-based methodology isolates the changes in CD and LLE in specific subbands of the EEG. The methodology is applied to three different groups of EEG signals: 1) healthy subjects; 2) epileptic subjects during a seizure-free interval (interictal EEG); 3) epileptic subjects during a seizure (ictal EEG). The effectiveness of CD and LLE in differentiating between the three groups is investigated based on statistical significance of the differences. It is observed that while there may not be significant differences in the values of the parameters obtained from the original EEG, differences may be identified when the parameters are employed in conjunction with specific EEG subbands. Moreover, it is concluded that for the higher frequency beta and gamma subbands, the CD differentiates between the three groups, whereas for the lower frequency alpha subband, the LLE differentiates between the three groups.

Alzheimer's disease: models of computation and analysis of EEGs.

In a recent article the authors presented a comprehensive review of research performed on computational modeling of Alzheimer's disease (AD) and its markers with a focus on computer imaging, classification models, connectionist neural models, and biophysical neural models. The popularity of imaging techniques for detection and diagnosis of possible AD stems from the relative ease with which neurological markers can be converted to visual markers. However, due to the expense of specialized experts and equipment involved in the use of imaging techniques, a subject of significant research interest is detecting markers in EEGs obtained from AD patients. In this article, the authors present a state-of-the-art review of models of computation and analysis of EEGs for diagnosis and detection of AD. This review covers three areas: time-frequency analysis, wavelet analysis, and chaos analysis. The vast number of physiological parameters involved in the poorly understood processes responsible for AD yields a large combination of parameters that can be manipulated and studied. A combination of parameters from different investigation modalities seems to be more effective in increasing the accuracy of detection-and diagnosis.

Alzheimer's disease and models of computation: imaging, classification, and neural models.

Prediction or early-stage diagnosis of Alzheimer's disease (AD) requires a comprehensive understanding of the underlying mechanisms of the disease and its progression. Researchers in this area have approached the problem from multiple directions by attempting to develop (a) neurological (neurobiological and neurochemical) models, (b) analytical models for anatomical and functional brain images, (c) analytical feature extraction models for electroencephalograms (EEGs), (d) classification models for positive identification of AD, and (e) neural models of memory and memory impairment in AD. This article presents a state-of-the-art review of research performed on computational modeling of AD and its markers. The review covers the following approaches: computer imaging, classification models, connectionist neural models, and biophysical neural models. It is concluded that a mixture of markers and a combination of novel computational techniques such as neural computing, chaos theory, and wavelets can increase the accuracy of algorithms for automated detection and diagnosis of AD.