Dimitrios G. Tsalikakis

Automated Epileptic Seizure Detection Methods: A Review Study

Epilepsy is a neurological disorder with prevalence of about 1-2% of the world’s population (Mormann, Andrzejak, Elger & Lehnertz, 2007). It is characterized by sudden recurrent and transient disturbances of perception or behaviour resulting from excessive synchronization of cortical neuronal networks; it is a neurological condition in which an individual experiences chronic abnormal bursts of electrical discharges in the brain. The hallmark of epilepsy is recurrent seizures termed epileptic seizures. Epileptic seizures are divided by their clinical manifestation into partial or focal, generalized, unilateral and unclassified seizures (James, 1997; Tzallas, Tsipouras & Fotiadis, 2007a, 2009). Focal epileptic seizures involve only part of cerebral hemisphere and produce symptoms in corresponding parts of the body or in some related mental functions. Generalized epileptic seizures involve the entire brain and produce bilateral motor symptoms usually with loss of consciousness. Both types of epileptic seizures can occur at all ages. Generalized epileptic seizures can be subdivided into absence (petit mal) and tonic-clonic (grand mal) seizures (James, 1997).

PERFORM: A System for Monitoring, Assessment and Management of Patients with Parkinson's Disease

In this paper, we describe the PERFORM system for the continuous remote monitoring and management of Parkinsons disease (PD) patients. The PERFORM system is an intelligent closed-loop system that seamlessly integrates a wide range of wearable sensors constantly monitoring several motor signals of the PD patients. Data acquired are pre-processed by advanced knowledge processing methods, integrated by fusion algorithms to allow health professionals to remotely monitor the overall status of the patients, adjust medication schedules and personalize treatment. The information collected by the sensors (accelerometers and gyroscopes) is processed by several classifiers. As a result, it is possible to evaluate and quantify the PD motor symptoms related to end of dose deterioration (tremor, bradykinesia, freezing of gait (FoG)) as well as those related to over-dose concentration (Levodopa-induced dyskinesia (LID)). Based on this information, together with information derived from tests performed with a virtual reality glove and information about the medication and food intake, a patient specific profile can be built. In addition, the patient specific profile with his evaluation during the last week and last month, is compared to understand whether his status is stable, improving or worsening. Based on that, the system analyses whether a medication change is needed—always under medical supervision—and in this case, information about the medication change proposal is sent to the patient. The performance of the system has been evaluated in real life conditions, the accuracy and acceptability of the system by the PD patients and healthcare professionals has been tested, and a comparison with the standard routine clinical evaluation done by the PD patients physician has been carried out. The PERFORM system is used by the PD patients and in a simple and safe non-invasive way for long-term record of their motor status, thus offering to the clinician a precise, long-term and objective view of patients motor status and drug/food intake. Thus, with the PERFORM system the clinician can remotely receive precise information for the PD patients status on previous days and define the optimal therapeutical treatment.

Endothelin-B receptors and ventricular arrhythmogenesis in the rat model of acute myocardial infarction

The arrhythmogenic effects of endothelin-1 (ET-1) are mediated via ETA-receptors, but the role of ETB-receptors is unclear. We examined the pathophysiologic role of ETB-receptors on ventricular tachyarrhythmias (VT/VF) during myocardial infarction (MI). MI was induced by coronary ligation in two animal groups, namely in wild-type (nxa0=xa063) and in ETB-receptor-deficient (nxa0=xa061) rats. Using a telemetry recorder, VT/VF episodes were evaluated during phase I (the 1st hour) and phase II (2–24xa0h) post-MI, with and without prior β-blockade. Action potential duration at 90% repolarization (APD90) was measured from monophasic epicardial recordings and indices of sympathetic activation were assessed using fast-Fourier analysis of heart rate variability. Serum epinephrine and norepinephrine were measured with radioimmunoassay. MI size was similar in the two groups. There was a marked temporal variation in VT/VF duration; during phase I, it was higher (pxa0=xa00.0087) in ETB-deficient (1,519xa0±xa0421xa0s) than in wild-type (190xa0±xa034xa0s) rats, but tended (pxa0=xa00.086) to be lower in ETB-deficient (4.2xa0±xa02.0xa0s) than in wild-type (27.7xa0±xa08.0xa0s) rats during phase II. Overall, the severity of VT/VF was greater in ETB-deficient rats, evidenced by higher (pxa0=xa00.0058) mortality (72.0% vs. 32.1%). There was a temporal variation in heart rate and in the ratio of low- to high-frequency spectra, being higher (<0.001) during phase I, but lower (pxa0<xa00.05) during phase II in ETB-deficient rats. Likewise, 1xa0h post-MI, serum epinephrine (pxa0=xa00.025) and norepinephrine (pxa0<xa00.0001) were higher in ETB-deficient (4.20xa0±xa00.54, 14.24xa0±xa01.39xa0ng/ml) than in wild-type (2.30xa0±xa00.59, 5.26xa0±xa00.67xa0ng/ml) rats, respectively. After β-blockade, VT/VF episodes and mortality were similar in the two groups. The ETB-receptor decreases sympathetic activation and arrhythmogenesis during the early phase of MI, but these effects diminish during evolving MI.

Real-time quantification of resting tremor in the Parkinson's disease

Resting tremor (RT) is one of the most frequent signs of the Parkinsons disease (PD), occurring with various severities in about 75% of the patients. Current diagnosis is based on subjective clinical assessment, which is not always easy to capture subtle, mild and intermittent tremors. The aim of the present study is to assess the suitability and clinical value of a computer based real-time system as an aid to diagnosis of PD, in particular the presence of RT. Five healthy subjects were asked to simulate several severities of RT in hands and feet in three static activities. The behaviour of the subjects is measured using tri-axial accelerometers, which are placed at four different positions on the body. Frequency-domain features, strongly correlated with the RT activity, are extracted from the accelerometer data. The classification of RT severity based on those features, provided accuracy 76%. The real-time system designed for efficient extraction of those features and the provision of a continuous RT severity measure is described.

Growth hormone decreases phase II ventricular tachyarrhythmias during acute myocardial infarction in rats.

GH (growth hormone) administration during acute MI (myocardial infarction) ameliorates subsequent LV (left ventricular) dysfunction. In the present study, we examined the effects of such treatment on arrhythmogenesis. A total of 53 Wistar rats (218+/-17 g) were randomized into two groups receiving two intraperitoneal injections of either GH (2 international units/kg of body weight; n=26) or normal saline (n=27), given at 24 h and 30 min respectively, prior to MI, which was generated by left coronary artery ligation. A single-lead ECG was recorded for 24 h post-MI, using an implanted telemetry system. Episodes of VT (ventricular tachyarrhythmia) and VF (ventricular fibrillation) during the first hour (phase I) and the hours following (phase II) MI were analysed. Monophasic action potential was recorded from the lateral LV epicardium at baseline and 24 h post-MI, and APD90 (action duration at 90% of repolarization) was measured. Infarct size was calculated 24 h post-MI. Infarct size and phase I VT+VF did not differ significantly between groups, but phase II hourly duration of VT+VF episodes was 82.8+/-116.6 s/h in the control group and 18.3+/-41.2 s/h in the GH group (P=0.0027), resulting in a lower arrhythmic (P=0.016) and total (P=0.0018) mortality in GH-treated animals. Compared with baseline, APD90 was prolonged significantly 24 h post-MI in the control group, displaying an increased beat-to-beat variation, but remained unchanged in the GH group. We conclude that GH decreases phase II VTs during MI in the rat. This finding may have implications in cardiac repair strategies.

Expression of microRNAs that regulate bone turnover in the serum of postmenopausal women with low bone mass and vertebral fractures

BACKGROUNDnCirculating microRNAs (miRs) are currently being investigated as novel biomarkers for osteoporosis and osteoporotic fractures.nnnAIMnThe aim of this study was to investigate serum levels of specific microRNAs, known regulators of bone metabolism, in postmenopausal women with low bone mass and with or without vertebral fractures (VFs).nnnMETHODSnFor the analysis, 14 miRs were isolated from the serum of 35 postmenopausal women with low bone mass and with at least one moderate VF and 35 postmenopausal women with low bone mass without fractures. Thirty postmenopausal women with normal BMD values and no history of fractures served as controls. Main outcome parameters were changes in the expression of selected miRs in the serum of patient population and compared with controls.nnnRESULTSnFrom the 14 miRs that were selected, we identified 5 miRs, namely miR-21-5p, miR-23a, miR-29a-3p, miR-124-3p and miR-2861 that were significantly deregulated in the serum of patients with low bone mass compared with controls. Serum miR-124 and miR-2861 were significantly higher, whereas miR-21, miR-23 and miR-29 were lower in patients compared with controls. In a sub-group analysis of the patient population, the expression of miR-21-5p was significantly lower among osteoporotic/osteopenic women with VFs, showing 66% sensitivity and 77% specificity in distinguishing women with a vertebral fracture.nnnCONCLUSIONnThis study identifies a differential expression pattern of miR-21-5p in the serum of women with low BMD and VFs.

Improving the protein fold recognition accuracy of a reduced state-space hidden Markov model

Fold recognition is a challenging field strongly associated with protein function determination, which is crucial for biologists and the pharmaceutical industry. Hidden Markov models (HMMs) have been widely used for this purpose. In this paper we demonstrate how the fold recognition performance of a recently introduced HMM with a reduced state-space topology can be improved. Our method employs an efficient architecture and a low complexity training algorithm based on likelihood maximization. The fold recognition performance of the model is further improved in two steps. In the first step we use a smaller model architecture based on the {E,H,L} alphabet instead of the DSSP secondary structure alphabet. In the second step secondary structure information (predicted or true) is additionally used in scoring the test set sequences. The Protein Data Bank and the annotation of the SCOP database are used for the training and evaluation of the proposed methodology. The results show that the fold recognition accuracy is substantially improved in both steps. Specifically, it is increased by 2.9% in the first step to 22%. In the second step it further increases and reaches up to 30% when predicted secondary structure information is additionally used and it increases even more and reaches up to 34.7% when we use the true secondary structure. The major advantage of the proposed improvements is that the fold recognition performance is substantially increased while the size of the model and the computational complexity of scoring are decreased.

Enhancement of Multichannel Chromosome Classification Using a Region-Based Classifier and Vector Median Filtering

Multichannel chromosome image acquisition is used for cancer diagnosis and research on genetic disorders. This type of imaging, apart from aiding the cytogeneticist in several ways, facilitates the visual detection of chromosome abnormalities. However, chromosome misclassification errors result from different factors, such as uneven hybridization, spectral overlap among fluors, and biochemical noise. In this paper, we enhance the chromosome classification accuracy by making use of a region Bayes classifier that increases the classification accuracy when compared to the already developed pixel-by-pixel classifier and by incorporating the vector median filtering approach for filtering of the image. The method is evaluated using a publicly available database that contains 183 six-channel chromosome sets of images. The overall improvement on the chromosome classification accuracy is 9.99%, compared to the pixel-by-pixel classifier without filtering. This improvement in the chromosome classification accuracy would allow subtle deoxyribonucleic acid abnormalities to be identified easily. The efficiency of the method might further improve by using features extracted from each region and a more sophisticated classifier.

EEG epileptic seizure detection using k-means clustering and marginal spectrum based on ensemble empirical mode decomposition

The detection of epileptic seizures is of primary interest for the diagnosis of patients with epilepsy. Epileptic seizure is a phenomenon of rhythmicity discharge for either a focal area or the entire brain and this individual behavior usually lasts from seconds to minutes. The unpredictable and rare occurrences of epileptic seizures make the automated detection of them highly recommended especially in long term EEG recordings. The present work proposes an automated method to detect the epileptic seizures by using an unsupervised method based on k-means clustering end Ensemble Empirical Decomposition (EEMD). EEG segments are obtained from a publicly available dataset and are classified in two categories “seizure” and “non-seizure”. Using EEMD the Marginal Spectrum (MS) of each one of the EEG segments is calculated. The MS is then divided into equal intervals and the averages of these intervals are used as input features for k-Means clustering. The evaluation results are very promising indicating overall accuracy 98% and is comparable with other related studies. An advantage of this method that no training data are used due to the unsupervised nature of k-Means clustering.

A wearable system for long-term ubiquitous monitoring of common motor symptoms in patients with Parkinson's disease

PERFORM is a system for the monitoring, assessment and management of patient with Parkinsons disease (PD). It comprises of three subsystems: (i) Multi-Sensor Monitoring Unit, (ii) the Local Base Unit, and (iii) the Centralized Hospital unit. The wearable, multi-sensor monitoring unit (WMSMU) of the PERFORM system is presented in this work. This unit plays an essential role in the overall PERFORM system since it is responsible to record and pre-process accelerometer and gyroscope signals that are later used by the various components of the Local Base Unit in order to classify and quantify the symptoms and motor status of the PD patients. The WMSMU was evaluated in a large set of pilot studies in PD patients.