Joshua Nedrud

A Multiple Kernel Learning approach for human behavioral task classification using STN-LFP signal

Deep Brain Stimulation (DBS) has gained increasing attention as an effective method to mitigate Parkinsons disease (PD) disorders. Existing DBS systems are open-loop such that the system parameters are not adjusted automatically based on patients behavior. Classification of human behavior is an important step in the design of the next generation of DBS systems that are closed-loop. This paper presents a classification approach to recognize such behavioral tasks using the subthalamic nucleus (STN) Local Field Potential (LFP) signals. In our approach, we use the time-frequency representation (spectrogram) of the raw LFP signals recorded from left and right STNs as the feature vectors. Then these features are combined together via Support Vector Machines (SVM) with Multiple Kernel Learning (MKL) formulation. The MKL-based classification method is utilized to classify different tasks: button press, mouth movement, speech, and arm movement. Our experiments show that the lp-norm MKL significantly outperforms single kernel SVM-based classifiers in classifying behavioral tasks of five subjects even using signals acquired with a low sampling rate of 10 Hz. This leads to a lower computational cost.Deep Brain Stimulation (DBS) has gained increasing attention as an effective method to mitigate Parkinsons disease (PD) disorders. Existing DBS systems are open-loop such that the system parameters are not adjusted automatically based on patients behavior. Classification of human behavior is an important step in the design of the next generation of DBS systems that are closed-loop. This paper presents a classification approach to recognize such behavioral tasks using the subthalamic nucleus (STN) Local Field Potential (LFP) signals. In our approach, we use the time-frequency representation (spectrogram) of the raw LFP signals recorded from left and right STNs as the feature vectors. Then these features are combined together via Support Vector Machines (SVM) with Multiple Kernel Learning (MKL) formulation. The MKL-based classification method is utilized to classify different tasks: button press, mouth movement, speech, and arm movement. Our experiments show that the lp-norm MKL significantly outperforms single kernel SVM-based classifiers in classifying behavioral tasks of five subjects even using signals acquired with a low sampling rate of 10 Hz. This leads to a lower computational cost.

Single trial behavioral task classification using subthalamic nucleus local field potential signals

Deep Brain Stimulation (DBS) has been a successful technique for alleviating Parkinsons disease (PD) symptoms especially for whom drug therapy is no longer efficient. Existing DBS therapy is open-loop, providing a time invariant stimulation pulse train that is not customized to the patients current behavioral task. By customizing this pulse train to the patients current task the side effects may be suppressed. This paper introduces a method for single trial recognition of the patients current task using the local field potential (LFP) signals. This method utilizes wavelet coefficients as features and support vector machine (SVM) as the classifier for recognition of a selection of behaviors: speech, motor, and random. The proposed method is 82.4% accurate for the binary classification and 73.2% for classifying three tasks. These algorithms will be applied in a closed loop feedback control system to optimize DBS parameters to the patients real time behavioral goals.

Motor task event detection using Subthalamic Nucleus Local Field Potentials

Deep Brain Stimulation (DBS) provides significant therapeutic benefit for movement disorders such as Parkinsons disease. Current DBS devices lack real-time feedback (thus are open loop) and stimulation parameters are adjusted during scheduled visits with a clinician. A closed-loop DBS system may reduce power consumption and DBS side effects. In such systems, DBS parameters are adjusted based on patients behavior, which means that behavior detection is a major step in designing such systems. Various physiological signals can be used to recognize the behaviors. Subthalamic Nucleus (STN) Local Field Potential (LFP) is a great candidate signal for the neural feedback, because it can be recorded from the stimulation lead and does not require additional sensors. A practical behavior detection method should be able to detect behaviors asynchronously meaning that it should not use any prior knowledge of behavior onsets. In this paper, we introduce a behavior detection method that is able to asynchronously detect the finger movements of Parkinson patients. As a result of this study, we learned that there is a motor-modulated inter-hemispheric connectivity between LFP signals recorded bilaterally from STN. We used non-linear regression method to measure this connectivity and use it to detect the finger movements. Performance of this method is evaluated using Receiver Operating Characteristic (ROC).

Long-Term Task- and Dopamine-Dependent Dynamics of Subthalamic Local Field Potentials in Parkinson’s Disease

Subthalamic nucleus (STN) local field potentials (LFP) are neural signals that have been shown to reveal motor and language behavior, as well as pathological parkinsonian states. We use a research-grade implantable neurostimulator (INS) with data collection capabilities to record STN-LFP outside the operating room to determine the reliability of the signals over time and assess their dynamics with respect to behavior and dopaminergic medication. Seven subjects were implanted with the recording augmented deep brain stimulation (DBS) system, and bilateral STN-LFP recordings were collected in the clinic over twelve months. Subjects were cued to perform voluntary motor and language behaviors in on and off medication states. The STN-LFP recorded with the INS demonstrated behavior-modulated desynchronization of beta frequency (13–30 Hz) and synchronization of low gamma frequency (35–70 Hz) oscillations. Dopaminergic medication did not diminish the relative beta frequency oscillatory desynchronization with movement. However, movement-related gamma frequency oscillatory synchronization was only observed in the medication on state. We observed significant inter-subject variability, but observed consistent STN-LFP activity across recording systems and over a one-year period for each subject. These findings demonstrate that an INS system can provide robust STN-LFP recordings in ambulatory patients, allowing for these signals to be recorded in settings that better represent natural environments in which patients are in a variety of medication states.

A hierarchical structure for human behavior classification using STN local field potentials

BACKGROUND Classification of human behavior from brain signals has potential application in developing closed-loop deep brain stimulation (DBS) systems. This paper presents a human behavior classification using local field potential (LFP) signals recorded from subthalamic nuclei (STN). METHOD A hierarchical classification structure is developed to perform the behavior classification from LFP signals through a multi-level framework (coarse to fine). At each level, the time-frequency representations of all six signals from the DBS leads are combined through an MKL-based SVM classifier to classify five tasks (speech, finger movement, mouth movement, arm movement, and random segments). To lower the computational cost, we alternatively use the inter-hemispheric synchronization of the LFPs to make three pairs out of six bipolar signals. Three classifiers are separately trained at each level of the hierarchical approach, which lead to three labels. A fusion function is then developed to combine these three labels and determine the label of the corresponding trial. RESULTS Using all six LFPs with the proposed hierarchical approach improves the classification performance. Moreover, the synchronization-based method reduces the computational burden considerably while the classification performance remains relatively unchanged. COMPARISON WITH EXISTING METHODS Our experiments on two different datasets recorded from nine subjects undergoing DBS surgery show that the proposed approaches remarkably outperform other methods for behavior classification based on LFP signals. CONCLUSION The LFP signals acquired from STNs contain useful information for recognizing human behavior. This can be a precursor for designing the next generation of closed-loop DBS systems.

An FFT-based synchronization approach to recognize human behaviors using STN-LFP signal

Classification of human behavior is a key step to developing closed-loop Deep Brain Stimulation (DBS) systems, which may decrease the power consumption and side effects of the existing systems. Recent studies have shown that the Local Field Potential (LFP) signals from both Subthalamic Nuclei (STN) of the brain can be used to recognize human behavior. Since the DBS leads implanted in each STN can collect three bipolar signals, the selection of a suitable pair of LFPs that achieves optimal recognition performance is still an open problem to address. Considering the presence of synchronized aggregate activity in the basal ganglia, this paper presents an FFT-based synchronization approach to automatically select a relevant pair of LFPs and use the pair together with an SVM-based MKL classifier for behavior recognition purposes. Our experiments on five subjects show the superiority of the proposed approach compared to other methods used for behavior classification.

Motor Task Detection From Human STN Using Interhemispheric Connectivity

Deep brain stimulation (DBS) provides significant therapeutic benefit for movement disorders, such as Parkinson’s disease (PD). Current DBS devices lack real-time feedback (thus are open loop) and stimulation parameters are adjusted during scheduled visits with a clinician. A closed-loop DBS system may reduce power consumption and side effects by adjusting stimulation parameters based on patient’s behavior. Subthalamic nucleus (STN) local field potential (LFP) is a great candidate signal for the neural feedback, because it can be recorded from the stimulation lead and does not require additional sensors. In this paper, we introduce a behavior detection method capable of asynchronously detecting the finger movements of PD patients. Our study indicates that there is a motor-modulated inter-hemispheric connectivity between LFP signals recorded bilaterally from the STN. We utilize a non-linear regression method to measure this inter-hemispheric connectivity for detecting finger movement. Our experimental results, using the recordings from 11 patients with PD, demonstrate that this approach is applicable for behavior detection in the majority of subjects (average area under curve of 70±12%).

Suppression of neurostimulation artifacts and adaptive clustering of Parkinson's patients behavioral tasks using EEG

Biological and biomedical signals, when adequately analyzed and processed, can be used to impart quantitative diagnosis during primary health care consultation to improve patient adherence to recommended treatments. For example, analyzing neural recordings from neurostimulators implanted in patients with neurological disorders can be used by a physician to adjust detrimental stimulation parameters to improve treatment. This work proposes advanced statistical signal processing and machine learning methodologies to assess neurostimulation from neural recordings. This is done using adaptive processing and unsupervised clustering methods applied to neural recordings to suppress neurostimulation artifacts and classify between various behavior tasks to assess the level of neurostimulation in patients.

A new approach for automated detection of behavioral task onset for patients with Parkinson's disease using subthalamic nucleus local field potentials

We present a new automated onset detection approach for behavioral tasks of patients with Parkinsons disease (PD) using Local Field Potential (LFP) signals collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are extracted and clustered in the feature space. A supervised Discrete Hidden Markov Models (DHMM) is employed and merged with Support Vector Machines (SVM) in a two-layer classifier to boost up the detection rate. According to our experimental results, the proposed approach can detect the onset of behaviors using LFP signals collected during DBS surgery with the accuracy of 84% while the acceptable delay is set to 1500 ms.

Causality graph learning on cortical information flow in Parkinson's disease patients during behaviour tests

Electroencephalographs (EEG) signals of the human brains represent electrical activities for a number of channels recorded over a the scalp. The main purpose of this paper is to investigate the interactions and causality of different parts of a brain using EEG signals recorded during a performance subjects of verbal fluency tasks. Subjects who have Parkinsons Disease (PD) have difficulties with mental tasks, such as switching between one behavior task and another. The behavior tasks include motor and phonemic fluency. This method uses verbal generation skills, activating different Brocas areas of the Brodmanns areas (BA44 and BA45). Advanced signal processing techniques are used in order to determine the activated frequency bands in the granger causality for verbal fluency tasks. The graph learning technique for channel strength is used to characterize the complex graph of Granger causality. Also, the support vector machine (SVM) method is used for training a classifier between two subjects with PD and two healthy controls. Neural data from the study was recorded at the Colorado Neurological Institute (CNI).