Early Prediction of Wound Healing Outcome Based on Chronic Wound Registry Database.

Chronic wounds cause a number of unnecessary amputations due to a delay in proper treatment. To expedite timely treatment, this paper presents an algorithm which uses a logistic regression classifier to predict whether the wound will heal or not within a specified time. The prediction is made at three time-points: one month, three months, and six months from the first visit of the patient to the healthcare facility. This prediction is made using a systematically collected chronic wound registry and is based entirely on data collected during patients' first visit. The algorithm achieves an area under the receiver operating characteristic curve (AUC) of 0.75, 0.72, and 0.71 for the prediction at the three time-points, respectively.Clinical relevance- Using the proposed prediction model, the clinicians will have an early estimate of the time taken to heal thereby providing appropriate treatments. We hope this will ensure timely treatments and reduce the number of unnecessary amputations.

Neural correlates of learning in a linear discriminant analysis brain-computer interface paradigm.

Objective.With practice, the control of brain-computer interfaces (BCI) would improve over time; the neural correlate for such learning had not been well studied. We demonstrated here that monkeys controlling a motor BCI using a linear discriminant analysis (LDA) decoder could learn to make the firing patterns of the recorded neurons more distinct over a short period of time for different output classes to improve task performance.Approach.Using an LDA decoder, we studied two Macaque monkeys implanted with microelectrode arrays as they controlled the movement of a mobile robotic platform. The LDA decoder mapped high-dimensional neuronal firing patterns linearly onto a lower-dimensional linear discriminant (LD) space, and we studied the changes in the spatial coordinates of these neural signals in the LD space over time, and their correspondence to trial performance. Direction selectivity was quantified with permutation feature importance (FI).Main results.We observed that, within individual sessions, there was a tendency for the points in the LD space encoding different directions to diverge, leading to fewer misclassification errors, and, hence, improvement in task accuracy. Accuracy was correlated with the presence of channels with strong directional preference (i.e. high FI), as well as a varied population code (i.e. high variance in FI distribution).Significance.We emphasized the importance of studying the short-term/intra-sessional variations in neural representations during the use of BCI. Over the course of individual sessions, both monkeys could modulate their neural activities to create increasingly distinct neural representations.

Information sparseness in cortical microelectrode channels while decoding movement direction using an artificial neural network.

Implanted microelectrode arrays can directly pick up electrode signals from the primary motor cortex (M1) during movement, and brain-machine interfaces (BMIs) can decode these signals to predict the directions of contemporaneous movements. However, it is not well known how much each individual input is responsible for the overall performance of a BMI decoder. In this paper, we seek to quantify how much each channel contributes to an artificial neural network (ANN)-based decoder, by measuring how much the removal of each individual channel degrades the accuracy of the output. If information on movement direction was equally distributed among channels, then the removal of one would have a minimal effect on decoder accuracy. On the other hand, if that information was distributed sparsely, then the removal of specific information-rich channels would significantly lower decoder accuracy. We found that for most channels, their removal did not significantly affect decoder performance. However, for a subset of channels (16 out of 61), removing them significantly reduced the decoder accuracy. This suggests that information is not uniformly distributed among the recording channels. We propose examining these channels further to optimize BMIs more effectively, as well as understand how M1 functions at the neuronal level.

Intention Estimation Based Adaptive Unscented Kalman Filter for Online Neural Decoding.

The commonly used fixed discrete Kalman filters (DKF) in neural decoders do not generalize well to the actual relationship between neuronal firing rates and movement intention. This is due to the underlying assumption that the neural activity is linearly related to the output state. They also face the issues of requiring large amount of training datasets to achieve a robust model and a degradation of decoding performance over time. In this paper, an adaptive adjustment is made to the conventional unscented Kalman filter (UKF) via intention estimation. This is done by incorporating a history of newly collected state parameters to develop a new set of model parameters. At each time point, a comparative weighted sum of old and new model parameters using matrix squared sums is used to update the neural decoding model parameters. The effectiveness of the resulting adaptive unscented Kalman filter (AUKF) is compared against the discrete Kalman filter and unscented Kalman filter-based algorithms. The results show that the proposed new algorithm provides higher decoding accuracy and stability while requiring less training data.

Prefrontal Cortical Activation While Doing Mindfulness Task: a Pilot Functional Near-Infrared Spectroscopy Study.

Mindfulness interventions are increasingly used in clinical settings. Neurophysiological mechanisms underlying mindfulness offer objective evidence that can help us evaluate the efficacy of mindfulness. Recent advances in technology have facilitated the use of functional Near-Infrared Spectroscopy (fNIRS) as a light weight, portable, and relatively lower cost neuroimaging device as compared to functional Magnetic Resonance Imaging (fMRI). In contrast to numerous fMRI studies, there are scanty investigations using fNIRS to study mindfulness. Hence, this study was done to investigate the feasibility of using a continuous-wave multichannel fNIRS system to study cerebral cortex activations on a mindfulness task versus a baseline task. NIRS data from 14 healthy Asian subjects were collected. A statistical parametric mapping toolbox specific for statistical analysis of NIRS signal called NIRS_SPM was used to study the activations. The results from group analysis performed on the contrast of the mindfulness versus baseline tasks showed foci of activations on the left and central parts of the prefrontal cortex. The findings are consistent with prevailing fMRI studies and show promise of using fNIRS system for studying real-time neurophysiological cortical activations during mindfulness practice.

Decoding movement direction from cortical microelectrode recordings using an LSTM-based neural network.

Brain-machine interfaces (BMIs) allow individuals to communicate with computers using neural signals, and Kalman Filter (KF) are prevailingly used to decode movement directions from these neural signals. In this paper, we implemented a multi-layer long short-term memory (LSTM)based artificial neural network (ANN) for decoding BMI neural signals. We collected motor cortical neural signals from a nonhuman primate (NHP), implanted with microelectrode array (MEA) while performing a directional joystick task. Next, we compared the LSTM model in decoding the joystick trajectories from the neural signals against the prevailing KF model. The results showed that the LSTM model yielded significantly improved decoding accuracy measured by mean correlation coefficient (0.84, p < 10-7) than the KF model (0.72). In addition, using a principal component analysis (PCA)-based dimensionality reduction technique yielded slightly deteriorated accuracies for both the LSTM (0.80) and KF (0.70) models, but greatly reduced the computational complexity. The results showed that the LSTM decoding model holds promise to improve decoding in BMIs for paralyzed humans.

Effects of Stimulus Spatial Resolution on SSVEP Responses under Overt and Covert Attention.

Steady-State Visual Evoked Potentials (SSVEP) Brain-Computer Interface (BCI) relies on overt spatial attention to exhibit reliable steady-state responses. There is a promising potential to employ the SSVEP paradigm in with vision research and clinical use, for instance, for visual field assessment. In this study, we investigate the SSVEP characteristics with different spatial attention, the different number of stimuli, and different viewing/visual angles. We collected data from eleven subjects in three experiment sessions, lasting about forty minutes, including the setup and calibration. Our evaluation results show similar SSVEP responses between overt and covert attention in multiple stimuli scenarios in most of the visual angles. We do not find any significant differences in SSVEP responses in visual angles between single and multi stimuli in covert attention. From this study, we found that reliable SSVEP responses can be achieved with covert spatial attention regardless of visual angles and stimulus spatial resolution.

Sparse Ensemble Machine Learning to Improve Robustness of Long-Term Decoding in iBMIs.

This paper presents a novel sparse ensemble based machine learning approach to enhance robustness of intracortical Brain Machine Interfaces (iBMIs) in the face of non-stationary distribution of input neural data across time. Each classifier in the ensemble is trained on a randomly sampled (with replacement) set of input channels. These sparse connections ensure that with a high chance, few of the base classifiers should be less affected by the variations in some of the recording channels. We have tested the generality of this technique on different base classifiers - linear discriminant analysis (LDA), support vector machine (SVM), extreme learning machine (ELM) and multilayer perceptron (MLP). Results show decoding accuracy improvements of up to ≈21 %, 13%, 19%, 10% in non-human primate (NHP) A and 7%, 9%, 7%, 9% in NHP B across test days while using the sparse ensemble approach over a single classifier model for LDA, SVM, ELM and MLP algorithms respectively. Furthermore, improvements of up to ≈7(14)%, 8(15)%, 9(19)%, 7(15)% in NHP A and 8(15)%, 12(20)%, 15(23)%, 12(19)% in NHP B over Random Forest (Long-short Term Memory) have been obtained by sparse ensemble LDA, SVM, ELM, MLP respectively.

Towards Intelligent Intracortical BMI (i 2BMI): Low-Power Neuromorphic Decoders That Outperform Kalman Filters.

Fully-implantable wireless intracortical Brain Machine Interfaces (iBMI) is one of the most promising next frontiers in the nascent field of neurotechnology. However, scaling the number of channels in such systems by another 10× is difficult due to power and bandwidth requirements of the wireless transmitter. One promising solution for that is to include more processing, up to the decoder, in the implant so that transmission data-rate is reduced drastically. Earlier work on neuromorphic decoder chips only showed classification of discrete states. We present results for continuous state decoding using a low-power neuromorphic decoder chip termed Spike-input Extreme Learning Machine (SELMA) that implements a nonlinear decoder without memory and its memory-based version with time-delayed bins, SELMA-bins. We have compared SELMA, SELMA-bins against state-of-the-art Steady-State Kalman Filter (SSKF), a linear decoder with memory, across two different datasets involving a total of 4 non-human primates (NHPs). Results show at least a 10% (20%) or more increase in the fraction of variance accounted for (FVAF) by SELMA (SELMA-bins) over SSKF across the datasets. Estimated energy consumption comparison shows SELMA (SELMA-bins) consuming ≈ 9 nJ/update (23 nJ/update) against SSKF's ≈ 7.4 nJ/update for an iBMI with a 10 degree of freedom control. Thus, SELMA yields better performance against SSKF while consuming energy in the same range as SSKF whereas SELMA-bins performs the best with moderately increased energy consumption, albeit far less than energy required for raw data transmission. This paves the way for reducing transmission data rates in future scaled iBMI systems.

Clustering Neural Patterns in Kernel Reinforcement Learning Assists Fast Brain Control in Brain-Machine Interfaces.

Neuroprosthesis enables the brain control on the external devices purely using neural activity for paralyzed people. Supervised learning decoders recalibrate or re-fit the discrepancy between the desired target and decoder's output, where the correction may over-dominate the user's intention. Reinforcement learning decoder allows users to actively adjust their brain patterns through trial and error, which better represents the subject's motive. The computational challenge is to quickly establish new state-action mapping before the subject becomes frustrated. Recently proposed quantized attention-gated kernel reinforcement learning (QAGKRL) explores the optimal nonlinear neural-action mapping in the Reproducing Kernel Hilbert Space (RKHS). However, considering all past data in RKHS is less efficient and sensitive to detect the new neural patterns emerging in brain control. In this paper, we propose a clustering-based kernel RL algorithm. New neural patterns emerge and are clustered to represent the novel knowledge in brain control. The current neural data only activate the nearest subspace in RKHS for more efficient decoding. The dynamic clustering makes our algorithm more sensitive to new brain patterns. We test our algorithm on both the synthetic and real-world spike data. Compared with QAGKRL, our algorithm can achieve a quicker knowledge adaptation in brain control with less computational complexity.

Robust Local Field Potential-based Neural Decoding by Actively Selecting Discriminative Channels.

Local field potentials (LFPs) have been proposed as a neural decoding signal to compensate for spike signal deterioration in invasive brain-machine interface applications. However, the presence of redundancy among LFP signals at different frequency bands across multiple channels may affect the decoding performance. In order to remove redundant LFP channels, we proposed a novel Fisher-distance ratio-based method to actively batch select discriminative channels to maximize the separation between classes. Experimental evaluation was conducted on 5 non-consecutive days of data from a non-human primate. For data from each day, the first experimental session was used to generate the training model, which was then used to perform 4-class decoding of signals from other sessions. Decoding achieved an average accuracy of 79.55%, 79.02% and 79.40% using selected LFP channels for beta, low gamma and high gamma frequency bands, respectively. Compared with decoding using full LFP channels, decoding using selected LFP channels in high gamma band resulted in an increase of 8.67% in accuracy, even if this accuracy was still 7.26% lower than that of spike-based decoding. These results demonstrate the effectiveness of the proposed method in selecting discriminative LFP channels for neural decoding.

EEG Channel Selection Based on Correlation Coefficient for Motor Imagery Classification: A Study on Healthy Subjects and ALS Patient.

Brain-Computer Interface (BCI) provides an alternate channel of interaction for people with severe motor disabilities. The Common Spatial Pattern (CSP) algorithm is effective in extracting discriminative features from EEG data for motor imagery-based Brain-Computer Interface (BCI). CSP yields signal from various locations for better performance. In this study, we selected a subset of EEG channels using correlation coefficient of spectral entropy and compared the classification performance using the Filter Bank Common Spatial Pattern (FBCSP) algorithm. We conducted experiments on 4 healthy subjects and one Amyotrophic Lateral Sclerosis (ALS) patient. The results showed that the proposed channel selection method increased classification accuracy of all subjects from 1.25% to 8.22%. Optimal performance was obtained using between 13 to 24 channels, and channels located over the motor cortex zone possess higher probabilities of being selected. Comparing with the channels manually selected to over the motor cortex area, the correlation coefficient method is able to identify the optimal channel combination and improve the motor imagery decoding accuracy of Healthy and ALS subjects.

Boosting performance in brain-machine interface by classifier-level fusion based on accumulative training models from multi-day data.

The nonstationarity of neural signal is still an unresolved issue despite the rapid progress made in brain-machine interface (BMI). This paper investigates how to utilize the rich information and dynamics in multi-day data to address the variability in day-to-day signal quality and neural tuning properties. For this purpose, we propose a classifier-level fusion technique to build a robust decoding model by jointly considering the classifier outputs from multiple base-training models using multi-day data collected prior to test day. The data set used in this study consisted of recordings of 8 days from a non-human primate (NHP) during control of a mobile robot using a joystick. Offline analysis demonstrates the superior performance of the proposed method which results in 4.4% and 13.10% improvements in decoding (significant by one-way ANOVA and post hoc t-test) compared with the two baseline methods: 1) concatenating data from multiple days based on common effective channels, and 2) averaging accuracies across all base-training models. These results further validate the effectiveness of proposed method without recalibration of the model.

Stop state classification in intracortical brain-machine-interface.

Invasive brain-machine-interface (BMI) has the prospect to empower tetraplegic patients with independent mobility through the use of brain-controlled wheelchairs. For the practical and long-term use of such control systems, the system has to distinguish between stop and movement states and has to be robust to overcome non-stationarity in the brain signals. In this work, we investigates the non-stationarity of the stop state on neural data collected from a macaque trained to control a robotic platform to stop and move in left, right, forward directions We then propose a hybrid approach that employs both random forest and linear discriminant analysis (LDA). Using this approach, we performed offline decoding on 8 days of data collected over the course of three months during joystick control of the robotic platform. We compared the results of using the proposed approach with the use of LDA alone to perform direct classifications of stop, left, right and forward. The results showed an average performance increment of 22.7% using the proposed hybrid approach. The results yielded significant improvements during sessions where LDA showed a heavy bias towards the stop state. This suggests that the proposed hybrid approach addresses the non-stationarity in the stop state and subsequently facilitates a more accurate decoding of the movement states.

Reject option to reduce false prediction rates for EEG-motor imagery based BCI.

The Filter Bank Common Spatial Pattern (FBCSP) algorithm had been shown to be effective in performing multi-class Electroencephalogram (EEG) decoding of motor imagery using the one-versus-the-rest approach on the BCI Competition IV Dataset IIa. In this paper, we propose a method to reduce false detection rates of decoding through a rejection option based on the difference in the posterior probability computed by the Naïve Bayesian classifier. We applied the proposed approach on the BCI Competition IV Dataset IIa, and the results showed a decrease in the false detection rates from 34.6 % to 6.9%, while average decoded trials decreased from 93.2% to 34.2% using a rejection threshold between 0.1 and 0.9. We subsequently formulated a method to optimize the rejection threshold based on the maximum F0.5 score. The optimal rejection threshold yielded an average decrease in false detection rate to 19.1% with an average of 67.5% of trials decoded. The results showed the feasibility of decreasing false detection rates at a cost of rejection. Nevertheless, the results suggest that the use of reject option (RO) may be used as a training feedback system to train subjects' overt and covert EEG control strategies for better (dexterity and safety) continuous control of external device.

Optimized temporal pattern of brain stimulation designed by computational evolution.

Brain stimulation is a promising therapy for several neurological disorders, including Parkinson's disease. Stimulation parameters are selected empirically and are limited to the frequency and intensity of stimulation. We varied the temporal pattern of deep brain stimulation to ameliorate symptoms in a parkinsonian animal model and in humans with Parkinson's disease. We used model-based computational evolution to optimize the stimulation pattern. The optimized pattern produced symptom relief comparable to that from standard high-frequency stimulation (a constant rate of 130 or 185 Hz) and outperformed frequency-matched standard stimulation in a parkinsonian rat model and in patients. Both optimized and standard high-frequency stimulation suppressed abnormal oscillatory activity in the basal ganglia of rats and humans. The results illustrate the utility of model-based computational evolution of temporal patterns to increase the efficiency of brain stimulation in treating Parkinson's disease and thereby reduce the energy required for successful treatment below that of current brain stimulation paradigms.

Frequency-dependent, transient effects of subthalamic nucleus deep brain stimulation on methamphetamine-induced circling and neuronal activity in the hemiparkinsonian rat.

Methamphetamine-induced circling is used to quantify the behavioral effects of subthalamic nucleus (STN) deep brain stimulation (DBS) in hemiparkinsonian rats. We observed a frequency-dependent transient effect of DBS on circling, and quantified this effect to determine its neuronal basis. High frequency STN DBS (75-260Hz) resulted in transient circling contralateral to the lesion at the onset of stimulation, which was not sustained after the first several seconds of stimulation. Following the transient behavioral change, DBS resulted in a frequency-dependent steady-state reduction in pathological ipsilateral circling, but no change in overall movement. Recordings from single neurons in globus pallidus externa (GPe) and substantia nigra pars reticulata (SNr) revealed that high frequency, but not low frequency, STN DBS elicited transient changes in both firing rate and neuronal oscillatory power at the stimulation frequency in a subpopulation of GPe and SNr neurons. These transient changes were not sustained, and most neurons exhibited a different response during the steady-state phase of DBS. During the steady-state, DBS produced elevated neuronal oscillatory power at the stimulus frequency in a majority of GPe and SNr neurons, and the increase was more pronounced during high frequency DBS than during low frequency DBS. Changes in oscillatory power during both transient and steady-state DBS were highly correlated with changes in firing rates. These results suggest that distinct neural mechanisms were responsible for transient and sustained behavioral responses to STN DBS. The transient contralateral turning behavior following the onset of high frequency DBS was paralleled by transient changes in firing rate and oscillatory power in the GPe and SNr, while steady-state suppression of ipsilateral turning was paralleled by sustained increased synchronization of basal ganglia neurons to the stimulus pulses. Our analysis of distinct frequency-dependent transient and steady-state responses to DBS lays the foundation for future mechanistic studies of the immediate and persistent effects of DBS.

Prediction and detection of seizures from simultaneous thalamic and scalp electroencephalography recordings.

OBJECTIVE The authors explored the feasibility of seizure detection and prediction using signals recorded from the anterior thalamic nucleus, a major target for deep brain stimulation (DBS) in the treatment of epilepsy. METHODS Using data from 5 patients (13 seizures in total), the authors performed a feasibility study and analyzed the performance of a seizure prediction and detection algorithm applied to simultaneously acquired scalp and thalamic electroencephalography (EEG). The thalamic signal was obtained from DBS electrodes. The applied algorithm used the similarity index as a nonlinear measure for seizure identification, with patient-specific channel and threshold selection. Receiver operating characteristic (ROC) curves were calculated using data from all patients and channels to compare the performance between DBS and EEG recordings. RESULTS Thalamic DBS recordings were associated with a mean prediction rate of 84%, detection rate of 97%, and false-alarm rate of 0.79/hr. In comparison, scalp EEG recordings were associated with a mean prediction rate of 71%, detection rate of 100%, and false-alarm rate of 1.01/hr. From the ROC curves, when considering all channels, DBS outperformed EEG for both detection and prediction of seizures. CONCLUSIONS This is the first study to compare automated seizure detection and prediction from simultaneous thalamic and scalp EEG recordings. The authors have demonstrated that signals recorded from DBS leads are more robust than EEG recordings and can be used to predict and detect seizures. These results indicate feasibility for future designs of closed-loop anterior nucleus DBS systems for the treatment of epilepsy.

Independent Mobility Achieved through a Wireless Brain-Machine Interface.

Individuals with tetraplegia lack independent mobility, making them highly dependent on others to move from one place to another. Here, we describe how two macaques were able to use a wireless integrated system to control a robotic platform, over which they were sitting, to achieve independent mobility using the neuronal activity in their motor cortices. The activity of populations of single neurons was recorded using multiple electrode arrays implanted in the arm region of primary motor cortex, and decoded to achieve brain control of the platform. We found that free-running brain control of the platform (which was not equipped with any machine intelligence) was fast and accurate, resembling the performance achieved using joystick control. The decoding algorithms can be trained in the absence of joystick movements, as would be required for use by tetraplegic individuals, demonstrating that the non-human primate model is a good pre-clinical model for developing such a cortically-controlled movement prosthetic. Interestingly, we found that the response properties of some neurons differed greatly depending on the mode of control (joystick or brain control), suggesting different roles for these neurons in encoding movement intention and movement execution. These results demonstrate that independent mobility can be achieved without first training on prescribed motor movements, opening the door for the implementation of this technology in persons with tetraplegia.

Failure to suppress low-frequency neuronal oscillatory activity underlies the reduced effectiveness of random patterns of deep brain stimulation.

Subthalamic nucleus (STN) deep brain stimulation (DBS) is an established treatment for the motor symptoms of Parkinson's disease (PD). However, the mechanisms of action of DBS are unknown. Random temporal patterns of DBS are less effective than regular DBS, but the neuronal basis for this dependence on temporal pattern of stimulation is unclear. Using a rat model of PD, we quantified the changes in behavior and single-unit activity in globus pallidus externa and substantia nigra pars reticulata during high-frequency STN DBS with different degrees of irregularity. Although all stimulus trains had the same average rate, 130-Hz regular DBS more effectively reversed motor symptoms, including circling and akinesia, than 130-Hz irregular DBS. A mixture of excitatory and inhibitory neuronal responses was present during all stimulation patterns, and mean firing rate did not change during DBS. Low-frequency (7-10 Hz) oscillations of single-unit firing times present in hemiparkinsonian rats were suppressed by regular DBS, and neuronal firing patterns were entrained to 130 Hz. Irregular patterns of DBS less effectively suppressed 7- to 10-Hz oscillations and did not regularize firing patterns. Random DBS resulted in a larger proportion of neuron pairs with increased coherence at 7-10 Hz compared with regular 130-Hz DBS, which suggested that long pauses (interpulse interval >50 ms) during random DBS facilitated abnormal low-frequency oscillations in the basal ganglia. These results suggest that the efficacy of high-frequency DBS stems from its ability to regularize patterns of neuronal firing and thereby suppress abnormal oscillatory neural activity within the basal ganglia.