Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

The significance of the sympathetic nervous system in the pathophysiology of periodic leg movements in sleep

STUDY OBJECTIVES: Periodic leg movements in sleep (PLMS) are frequently accompanied by arousals and autonomic activation, but the pathophysiologic significance of these manifestations is unclear. DESIGN: Changes in heart rate variability (HRV), HRV spectra, and electroencephalogram (EEG) spectra associated with idiopathic PLMS were compared with changes associated with isolated leg movements and respiratory-related leg movements during sleep. Furthermore, correlations between electromyographic activity, HRV changes, and EEG changes were assessed. SETTING: Sleep laboratory. PATIENTS: Whole-night polysomnographic studies of 24 subjects fulfilling the criteria of either periodic leg movements disorder (n = 8), obstructive sleep apnea syndrome (n = 7), or normal polysomnography (n = 9) were used. MEASUREMENTS AND RESULTS: Spectral HRV changes started before all EEG changes and up to 6 seconds before the onset of all types of leg movements. An initial weak autonomic activation was followed by a sympathetic activation, an increase of EEG delta activity, and finally a progression to increased higher-frequency EEG rhythms. After movement onset, HRV indicated a vagal activation, and, the EEG, a decrease in spindle activity. Sympathetic activation, as measured by HRV spectra, was greater for PLMS than for all other movement types. In EEG, gamma synchronization began 1 to 2 seconds earlier for isolated leg movements and respiratory-related leg movements than for PLMS. Significant correlations were found between autonomic activations and electromyographic activity, as well as between autonomic activations and EEG delta activity, but not between higher-frequency EEG rhythms and EMG activity or HRV changes. CONCLUSIONS: These results suggest a primary role of the sympathetic nervous system in the generation of PLMS.

Native EEG and treatment effects in neuroleptic-naïve schizophrenic patients: time and frequency domain approaches

Time domain analysis of electroencephalography (EEG) can identify subsecond periods of quasi-stable brain states. These so-called microstates assumingly correspond to basic units of cognition and emotion. On the other hand, Global Field Synchronization (GFS) is a frequency domain measure to estimate functional synchronization of brain processes on a global level for each EEG frequency band [Koenig, T., Lehmann, D., Saito, N., Kuginuki, T., Kinoshita, T., Koukkou, M., 2001. Decreased functional connectivity of EEG theta-frequency activity in first-episode, neuroleptic-naive patients with schizophrenia: preliminary results. Schizophr Res. 50, 55-60.]. Using these time and frequency domain analyzes, several previous studies reported shortened microstate duration in specific microstate classes and decreased GFS in theta band in drug naïve schizophrenia compared to controls. The purpose of this study was to investigate changes of these EEG parameters after drug treatment in drug naïve schizophrenia. EEG analysis was performed in 21 drug-naive patients and 21 healthy controls. 14 patients were reevaluated 2-8 weeks (mean 4.3) after the initiation of drug administration. The results extended findings of treatment effect on brain functions in schizophrenia, and imply that shortened duration of specific microstate classes seems a state marker especially in patients with later neuroleptic responsive, while lower theta GFS seems a state-related phenomenon and that higher gamma GFS is a trait like phenomenon.

Compositional protein analysis of high density lipoproteins in hypercholesterolemia by shotgun LC-MS/MS and probabilistic peptide scoring

A protein of a biological sample is usually quantified by immunological techniques based on antibodies. Mass spectrometry offers alternative approaches that are not dependent on antibody affinity and avidity, protein isoforms, quaternary structures, or steric hindrance of antibody-antigen recognition in case of multiprotein complexes. One approach is the use of stable isotope-labeled internal standards; another is the direct exploitation of mass spectrometric signals recorded by LC-MS/MS analysis of protein digests. Here we assessed the peptide match score summation index based on probabilistic peptide scores calculated by the PHENYX protein identification engine for absolute protein quantification in accordance with the protein abundance index as proposed by Mann and co-workers (Rappsilber, J., Ryder, U., Lamond, A. I., and Mann, M. (2002) Large-scale proteomic analysis of the human spliceosome. Genome Res. 12, 1231-1245). Using synthetic protein mixtures, we demonstrated that this approach works well, although proteins can have different response factors. Applied to high density lipoproteins (HDLs), this new approach compared favorably to alternative protein quantitation methods like UV detection of protein peaks separated by capillary electrophoresis or quantitation of protein spots on SDS-PAGE. We compared the protein composition of a well defined HDL density class isolated from plasma of seven hypercholesterolemia subjects having low or high HDL cholesterol with HDL from nine normolipidemia subjects. The quantitative protein patterns distinguished individuals according to the corresponding concentration and distribution of cholesterol from serum lipid measurements of the same samples and revealed that hypercholesterolemia in unrelated individuals is the result of different deficiencies. The presented approach is complementary to HDL lipid analysis; does not rely on complicated sample treatment, e.g. chemical reactions, or antibodies; and can be used for projective clinical studies of larger patient groups.

Cortical and subcortical correlates of electroencephalographic alpha rhythm modulation

Neural correlates of electroencephalographic (EEG) alpha rhythm are poorly understood. Here, we related EEG alpha rhythm in awake humans to blood-oxygen-level-dependent (BOLD) signal change determined by functional magnetic resonance imaging (fMRI). Topographical EEG was recorded simultaneously with fMRI during an open versus closed eyes and an auditory stimulation versus silence condition. EEG was separated into spatial components of maximal temporal independence using independent component analysis. Alpha component amplitudes and stimulus conditions served as general linear model regressors of the fMRI signal time course. In both paradigms, EEG alpha component amplitudes were associated with BOLD signal decreases in occipital areas, but not in thalamus, when a standard BOLD response curve (maximum effect at approximately 6 s) was assumed. The part of the alpha regressor independent of the protocol condition, however, revealed significant positive thalamic and mesencephalic correlations with a mean time delay of approximately 2.5 s between EEG and BOLD signals. The inverse relationship between EEG alpha amplitude and BOLD signals in primary and secondary visual areas suggests that widespread thalamocortical synchronization is associated with decreased brain metabolism. While the temporal relationship of this association is consistent with metabolic changes occurring simultaneously with changes in the alpha rhythm, sites in the medial thalamus and in the anterior midbrain were found to correlate with short time lag. Assuming a canonical hemodynamic response function, this finding is indicative of activity preceding the actual EEG change by some seconds.

Dosimetric impact of geometric errors due to respiratory motion prediction on dynamic multileaf collimator-based four-dimensional radiation delivery

The synchronization of dynamic multileaf collimator (DMLC) response with respiratory motion is critical to ensure the accuracy of DMLC-based four dimensional (4D) radiation delivery. In practice, however, a finite time delay (response time) between the acquisition of tumor position and multileaf collimator response necessitates predictive models of respiratory tumor motion to synchronize radiation delivery. Predicting a complex process such as respiratory motion introduces geometric errors, which have been reported in several publications. However, the dosimetric effect of such errors on 4D radiation delivery has not yet been investigated. Thus, our aim in this work was to quantify the dosimetric effects of geometric error due to prediction under several different conditions. Conformal and intensity modulated radiation therapy (IMRT) plans for a lung patient were generated for anterior-posterior/posterior-anterior (AP/PA) beam arrangements at 6 and 18 MV energies to provide planned dose distributions. Respiratory motion data was obtained from 60 diaphragm-motion fluoroscopy recordings from five patients. A linear adaptive filter was employed to predict the tumor position. The geometric error of prediction was defined as the absolute difference between predicted and actual positions at each diaphragm position. Distributions of geometric error of prediction were obtained for all of the respiratory motion data. Planned dose distributions were then convolved with distributions for the geometric error of prediction to obtain convolved dose distributions. The dosimetric effect of such geometric errors was determined as a function of several variables: response time (0-0.6 s), beam energy (6/18 MV), treatment delivery (3D/4D), treatment type (conformal/IMRT), beam direction (AP/PA), and breathing training type (free breathing/audio instruction/visual feedback). Dose difference and distance-to-agreement analysis was employed to quantify results. Based on our data, the dosimetric impact of prediction (a) increased with response time, (b) was larger for 3D radiation therapy as compared with 4D radiation therapy, (c) was relatively insensitive to change in beam energy and beam direction, (d) was greater for IMRT distributions as compared with conformal distributions, (e) was smaller than the dosimetric impact of latency, and (f) was greatest for respiration motion with audio instructions, followed by visual feedback and free breathing. Geometric errors of prediction that occur during 4D radiation delivery introduce dosimetric errors that are dependent on several factors, such as response time, treatment-delivery type, and beam energy. Even for relatively small response times of 0.6 s into the future, dosimetric errors due to prediction could approach delivery errors when respiratory motion is not accounted for at all. To reduce the dosimetric impact, better predictive models and/or shorter response times are required.

Cell cycle-dependent regulation of extra-adrenal glucocorticoid synthesis in murine intestinal epithelial cells

Glucocorticoids are anti-inflammatory steroids with important applications in the treatment of inflammatory diseases. Endogenous glucocorticoids are mainly produced by the adrenal glands, although there is increasing evidence for extra-adrenal sources. Recent findings show that intestinal crypt cells produce glucocorticoids, which contribute to the maintenance of intestinal immune homeostasis. Intestinal glucocorticoid synthesis is critically regulated by the transcription factor liver receptor homologue-1 (LRH-1). As expression of steroidogenic enzymes and LRH-1 is restricted to the proliferating cells of the crypts, we aimed to investigate the role of the cell cycle in the regulation of LRH-1 activity and intestinal glucocorticoid synthesis. We here show that either pharmacological or molecular modulation of cell cycle progression significantly inhibited expression of steroidogenic enzymes and synthesis of glucocorticoids in intestinal epithelial cells. Synchronization of intestinal epithelial cells in the cell cycle revealed that expression of steroidogenic enzymes is preferentially induced at the G(1)/S stage. Differentiation of immature intestinal epithelial cells to mature nonproliferating cells also resulted in reduced expression of steroidogenic enzymes. This cell cycle-related effect on intestinal steroidogenesis was found to be mediated through the regulation of LRH-1 transcriptional activity. This mechanism may restrict intestinal glucocorticoid synthesis to the proliferating cells of the crypts.

Applications of finite geometries to designs and codes

This dissertation concerns the intersection of three areas of discrete mathematics: finite geometries, design theory, and coding theory. The central theme is the power of finite geometry designs, which are constructed from the points and t-dimensional subspaces of a projective or affine geometry. We use these designs to construct and analyze combinatorial objects which inherit their best properties from these geometric structures. A central question in the study of finite geometry designs is Hamada’s conjecture, which proposes that finite geometry designs are the unique designs with minimum p-rank among all designs with the same parameters. In this dissertation, we will examine several questions related to Hamada’s conjecture, including the existence of counterexamples. We will also study the applicability of certain decoding methods to known counterexamples. We begin by constructing an infinite family of counterexamples to Hamada’s conjecture. These designs are the first infinite class of counterexamples for the affine case of Hamada’s conjecture. We further demonstrate how these designs, along with the projective polarity designs of Jungnickel and Tonchev, admit majority-logic decoding schemes. The codes obtained from these polarity designs attain error-correcting performance which is, in certain cases, equal to that of the finite geometry designs from which they are derived. This further demonstrates the highly geometric structure maintained by these designs. Finite geometries also help us construct several types of quantum error-correcting codes. We use relatives of finite geometry designs to construct infinite families of q-ary quantum stabilizer codes. We also construct entanglement-assisted quantum error-correcting codes (EAQECCs) which admit a particularly efficient and effective error-correcting scheme, while also providing the first general method for constructing these quantum codes with known parameters and desirable properties. Finite geometry designs are used to give exceptional examples of these codes.

USING PROBABILISTIC GRAPHICAL MODELS TO DRAW INFERENCES IN SENSOR NETWORKS WITH TRACKING APPLICATIONS

Sensor networks have been an active research area in the past decade due to the variety of their applications. Many research studies have been conducted to solve the problems underlying the middleware services of sensor networks, such as self-deployment, self-localization, and synchronization. With the provided middleware services, sensor networks have grown into a mature technology to be used as a detection and surveillance paradigm for many real-world applications. The individual sensors are small in size. Thus, they can be deployed in areas with limited space to make unobstructed measurements in locations where the traditional centralized systems would have trouble to reach. However, there are a few physical limitations to sensor networks, which can prevent sensors from performing at their maximum potential. Individual sensors have limited power supply, the wireless band can get very cluttered when multiple sensors try to transmit at the same time. Furthermore, the individual sensors have limited communication range, so the network may not have a 1-hop communication topology and routing can be a problem in many cases. Carefully designed algorithms can alleviate the physical limitations of sensor networks, and allow them to be utilized to their full potential. Graphical models are an intuitive choice for designing sensor network algorithms. This thesis focuses on a classic application in sensor networks, detecting and tracking of targets. It develops feasible inference techniques for sensor networks using statistical graphical model inference, binary sensor detection, events isolation and dynamic clustering. The main strategy is to use only binary data for rough global inferences, and then dynamically form small scale clusters around the target for detailed computations. This framework is then extended to network topology manipulation, so that the framework developed can be applied to tracking in different network topology settings. Finally the system was tested in both simulation and real-world environments. The simulations were performed on various network topologies, from regularly distributed networks to randomly distributed networks. The results show that the algorithm performs well in randomly distributed networks, and hence requires minimum deployment effort. The experiments were carried out in both corridor and open space settings. A in-home falling detection system was simulated with real-world settings, it was setup with 30 bumblebee radars and 30 ultrasonic sensors driven by TI EZ430-RF2500 boards scanning a typical 800 sqft apartment. Bumblebee radars are calibrated to detect the falling of human body, and the two-tier tracking algorithm is used on the ultrasonic sensors to track the location of the elderly people.

Trial-to-trial size variability of motor-evoked potentials. A study using the triple stimulation technique

Motor-evoked potentials (MEPs) vary in size from one stimulus to the next. The objective of this study was to determine the cause and source of trial-to-trial MEP size variability. In two experiments involving 10 and 14 subjects, the variability of MEPs to cortical stimulation (cortical-MEPs) in abductor digiti minimi (ADM) and abductor hallucis (AH) was compared to those responses obtained using the triple stimulation technique (cortical-TST). The TST eliminates the effects of motor neuron (MN) response desynchronization and of repetitive MN discharges. Submaximal stimuli were used in both techniques. In six subjects, cortical-MEP variability was compared to that of brainstem-MEP and brainstem-TST. Variability was greater for MEPs than that for TST responses, by approximately one-third. The variability was the same for cortical- and brainstem-MEPs and was similar in ADM and AH. Variability concerned at least 10-15% of the MN pool innervating the target muscle. With the stimulation parameters used, repetitive MN discharges did not influence variability. For submaximal stimuli, approximately two-third of the observed MEP size variability is caused by the variable number of recruited alpha-MNs and approximately one-third by changing synchronization of MN discharges. The source of variability is most likely localized at the spinal segmental level.

BOLD correlates of EEG alpha phase-locking and the fMRI default mode network

Phase locking or synchronization of brain areas is a key concept of information processing in the brain. Synchronous oscillations have been observed and investigated extensively in EEG during the past decades. EEG oscillations occur over a wide frequency range. In EEG, a prominent type of oscillations is alpha-band activity, present typically when a subject is awake, but at rest with closed eyes. The spectral power of alpha rhythms has recently been investigated in simultaneous EEG/fMRI recordings, establishing a wide-range cortico-thalamic network. However, spectral power and synchronization are different measures and little is known about the correlations between BOLD effects and EEG synchronization. Interestingly, the fMRI BOLD signal also displays synchronous oscillations across different brain regions. These oscillations delineate so-called resting state networks (RSNs) that resemble the correlation patterns of simultaneous EEG/fMRI recordings. However, the nature of these BOLD oscillations and their relations to EEG activity is still poorly understood. One hypothesis is that the subunits constituting a specific RSN may be coordinated by different EEG rhythms. In this study we report on evidence for this hypothesis. The BOLD correlates of global EEG synchronization (GFS) in the alpha frequency band are located in brain areas involved in specific RSNs, e.g. the 'default mode network'. Furthermore, our results confirm the hypothesis that specific RSNs are organized by long-range synchronization at least in the alpha frequency band. Finally, we could localize specific areas where the GFS BOLD correlates and the associated RSN overlap. Thus, we claim that not only the spectral dynamics of EEG are important, but also their spatio-temporal organization.

Parameter-free extraction of the functional network topology from intracranial EEG recordings: a time-resolved study of graph properties in focal onset seizures

Rationale: Focal onset epileptic seizures are due to abnormal interactions between distributed brain areas. By estimating the cross-correlation matrix of multi-site intra-cerebral EEG recordings (iEEG), one can quantify these interactions. To assess the topology of the underlying functional network, the binary connectivity matrix has to be derived from the cross-correlation matrix by use of a threshold. Classically, a unique threshold is used that constrains the topology [1]. Our method aims to set the threshold in a data-driven way by separating genuine from random cross-correlation. We compare our approach to the fixed threshold method and study the dynamics of the functional topology. Methods: We investigate the iEEG of patients suffering from focal onset seizures who underwent evaluation for the possibility of surgery. The equal-time cross-correlation matrices are evaluated using a sliding time window. We then compare 3 approaches assessing the corresponding binary networks. For each time window: * Our parameter-free method derives from the cross-correlation strength matrix (CCS)[2]. It aims at disentangling genuine from random correlations (due to finite length and varying frequency content of the signals). In practice, a threshold is evaluated for each pair of channels independently, in a data-driven way. * The fixed mean degree (FMD) uses a unique threshold on the whole connectivity matrix so as to ensure a user defined mean degree. * The varying mean degree (VMD) uses the mean degree of the CCS network to set a unique threshold for the entire connectivity matrix. * Finally, the connectivity (c), connectedness (given by k, the number of disconnected sub-networks), mean global and local efficiencies (Eg, El, resp.) are computed from FMD, CCS, VMD, and their corresponding random and lattice networks. Results: Compared to FMD and VMD, CCS networks present: *topologies that are different in terms of c, k, Eg and El. *from the pre-ictal to the ictal and then post-ictal period, topological features time courses that are more stable within a period, and more contrasted from one period to the next. For CCS, pre-ictal connectivity is low, increases to a high level during the seizure, then decreases at offset. k shows a ‘‘U-curve’’ underlining the synchronization of all electrodes during the seizure. Eg and El time courses fluctuate between the corresponding random and lattice networks values in a reproducible manner. Conclusions: The definition of a data-driven threshold provides new insights into the topology of the epileptic functional networks.

Method of collaborative detection of autonomous transport vehicles based on laser rangefinder data

To master changing performance demands, autonomous transport vehicles are deployed to make inhouse material flow applications more flexible. The socalled cellular transport system consists of a multitude of small scale transport vehicles which shall be able to form a swarm. Therefore the vehicles need to detect each other, exchange information amongst each other and sense their environment. By provision of peripherally acquired information of other transport entities, more convenient decisions can be made in terms of navigation and collision avoidance. This paper is a contribution to collective utilization of sensor data in the swarm of cellular transport vehicles.

Application of Time-Delay Estimation to Mixed Reality Multisensor Tracking

Spatial tracking is one of the most challenging and important parts of Mixed Reality environments. Many applications, especially in the domain of Augmented Reality, rely on the fusion of several tracking systems in order to optimize the overall performance. While the topic of spatial tracking sensor fusion has already seen considerable interest, most results only deal with the integration of carefully arranged setups as opposed to dynamic sensor fusion setups. A crucial prerequisite for correct sensor fusion is the temporal alignment of the tracking data from several sensors. Tracking sensors are typically encountered in Mixed Reality applications, are generally not synchronized. We present a general method to calibrate the temporal offset between different sensors by the Time Delay Estimation method which can be used to perform on-line temporal calibration. By applying Time Delay Estimation on the tracking data, we show that the temporal offset between generic Mixed Reality spatial tracking sensors can be calibrated. To show the correctness and the feasibility of this approach, we have examined different variations of our method and evaluated various combinations of tracking sensors. We furthermore integrated this time synchronization method into our UBITRACK Mixed Reality tracking framework to provide facilities for calibration and real-time data alignment.

Decreased functional connectivity of EEG theta-frequency activity in first-episode, neuroleptic-naïve patients with schizophrenia: preliminary results

We explored and refined the hypothesis that during a first episode of acute schizophrenia a disorganization of brain functioning is present. A novel EEG measure was introduced, Global Field Synchronization (GFS), that estimates functional connectivity of brain processes in different EEG frequency bands. The measure was applied to EEG's from 11 never-treated, first-episode, young patients with an acute, positive, schizophrenic symptomatology and from 19 controls, residing in Bern, Switzerland. In comparison to age- and sex- matched controls, patients had significantly decreased GFS in the theta EEG frequency band, indicating a loosened functional connectivity of processes in this frequency. The result was confirmed in an independent, comparable patient group from Osaka, Japan (9 patients and 9 controls), thus making a total of 20 analyzed patients. Previous EEG research in healthy, awake subjects indicated a positive correlation of theta activity with memory functions. Thus, our result suggests a loss of mutual interdependence of memory functions in patients with acute schizophrenia, which agrees well with previous reports of working memory dysfunction in schizophrenia.