Kernel machines for epilepsy diagnosis via EEG signal classification: A comparative study

Objective: We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. Methods and materials: The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely. Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. Results: We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Conclusions: Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). (C) 2011 Elsevier B.V. All rights reserved.

Use of Medical Subject Headings (MeSH) in Portuguese for categorizing web-based healthcare content

Introduction: Internet users are increasingly using the worldwide web to search for information relating to their health. This situation makes it necessary to create specialized tools capable of supporting users in their searches. Objective: To apply and compare strategies that were developed to investigate the use of the Portuguese version of Medical Subject Headings (MeSH) for constructing an automated classifier for Brazilian Portuguese-language web-based content within or outside of the field of healthcare, focusing on the lay public. Methods: 3658 Brazilian web pages were used to train the classifier and 606 Brazilian web pages were used to validate it. The strategies proposed were constructed using content-based vector methods for text classification, such that Naive Bayes was used for the task of classifying vector patterns with characteristics obtained through the proposed strategies. Results: A strategy named InDeCS was developed specifically to adapt MeSH for the problem that was put forward. This approach achieved better accuracy for this pattern classification task (0.94 sensitivity, specificity and area under the ROC curve). Conclusions: Because of the significant results achieved by InDeCS, this tool has been successfully applied to the Brazilian healthcare search portal known as Busca Saude. Furthermore, it could be shown that MeSH presents important results when used for the task of classifying web-based content focusing on the lay public. It was also possible to show from this study that MeSH was able to map out mutable non-deterministic characteristics of the web. (c) 2010 Elsevier Inc. All rights reserved.

Predictive Validity of the Braden Scale for Pressure Ulcer Risk in Elderly Residents of Long-Term Care Facilities

The aim of this study was to evaluate the predictive validity of the Braden Scale for Predicting Pressure Sore Risk in elderly residents of long-term care facilities (LTCFs) in Brazil. The determination of the cutoff score for the Brazilian population is important for the comparison between Brazilian and international studies and establishment of guidelines for prevention of pressure ulcers in our health care facilities. This is the first study of its kind in Brazil. This was a secondary analysis of a prospective cohort study conducted with 233 LTCF residents aged 60 and over who underwent complete skin examination and Braden Scale rating every 2 days for 3 months. Two groups of patients were considered: the total group (N = 233) and risk group (n = 94, total scores <= 18). Data from the first and last assessments were analyzed for sensitivity, specificity, and likelihood ratios. The best results were obtained for the total group, with cutoff scores of 18 and 17, sensitivity of 75.9% and 74.1%, specificity of 70.3% and 75.4%, and area under the receiver operating characteristic curve (AUC-ROC) of 0.79 and 0.81 at the first and last assessments, respectively. For the risk group, the cutoff scores of 16 (first assessment) and 13 (last assessment) were associated with a smaller AUC-ROC and, therefore, lower predictive accuracy. The Braden Scale showed good predictive validity in elderly LTCF residents. (Geriatr Nurs 2010;31:95-104)

Predictive Validity of Waterlow Scale for Pressure Ulcer Development Risk in Hospitalized Patients

AIM: We sought to evaluate the predictive validity of the Waterlow Scale in hospitalized patients. SUBJECTS AND SETTING: The study was conducted at a general private hospital with 220 beds and a mean time of hospitalization of 7.4 days and a mean occupation rate of approximately 80%. Adult patients with a Braden Scale score of 18 or less and a Waterlow Scale score of 16 or more were studied. The sample consisted of 98 patients with a mean age of 71.1 +/- 15.5 years. METHODS: Skin assessment and scoring by using the Waterlow and Braden scales were completed on alternate days. Patients were examined at least 3 times to be considered for analysis. The data were submitted to sensitivity and specificity analysis by using receiver operating characteristic (ROC) curves and positive (+LR) and negative (-LR) likelihood ratios. RESULTS: The cutoff scores were 17, 20, and 20 in the first, second, and third assessment, respectively. Sensitivity was 71.4%, 85.7%, and 85.7% and specificity was 67.0%, 40.7%, and 32.9%, respectively. Analysis of the area under the ROC curve revealed good accuracy (0.64, 95% confidence interval [CI]: 0.35-0.93) only for the cutoff score 17 in the first assessment. The results also showed probabilities of 14%, 10%, and 9% for the development of pressure ulcer when the test results were positive (+LR) and of 3% (-LR) when the test results were negative for the cutoff scores in the first, second, and third assessment, respectively. CONCLUSION: The Waterlow Scale achieved good predictive validity in predicting pressure ulcer in hospitalized patients when a cutoff score of 17 was used in the first assessment.

Baroreflex Sensitivity Impairment Is Associated With Cardiac Diastolic Dysfunction in Rats

Background: Studies have shown that the autonomic dysfunction accompanied by impaired baroreflex sensitivity was associated with higher mortality. However, the influence of decreased baroreflex sensitivity on cardiac function, especially in diastolic function, is not well understood. This study evaluated the morpho-functional changes associated with baroreflex impairment induced by chronic sinoaortic denervation (SAD). Methods and Results: Animals were divided into sinoaortic denervation (SAD) and control (C) groups. Baroreflex sensitivity was evaluated by tachycardic and bradycardic responses, induced by vasoactive drugs. Cardiac function was studied by echocardiography and by left ventricle (LV) catheterization. LV collagen content and the expression of regulatory proteins involved in intracellular Ca(2+) homeostasis were quantified. Results showed higher LV mass in SAD versus C animals. Furthermore, an increase in deceleration time of E-wave in the SAD versus the C group (2.14 +/- 0.07 ms vs 1.78 +/- 0.03 ms) was observed. LV end-diastolic pressure was increased and the minimum dP/dt was decreased in the SAD versus the C group (12 +/- 1.5 mm Hg vs 5.3 +/- 0.2 mm Hg and 7,422 +/- 201 vs 4,999 +/- 345 mm Hg/s, respectively). SERCA/NCX ratio was lower in SAD than in control rats. The same was verified in SERCA/PLB ratio. Conclusions: The results suggest that baroreflex dysfunction is associated with cardiac diastolic dysfunction independently of the presence of other risk factors. (J Cardiac Fail 2011;17:519-525)

Effects of creatine supplementation on glucose tolerance and insulin sensitivity in sedentary healthy males undergoing aerobic training

Recent findings have indicated that creatine supplementation may affect glucose metabolism. This study aimed to examine the effects of creatine supplementation, combined with aerobic training, on glucose tolerance in sedentary healthy male. Subjects (n = 22) were randomly divided in two groups and were allocated to receive treatment with either creatine (CT) (similar to 10g .day over three months) or placebo (PT) (dextrose). Administration of treatments was double blind. Both groups underwent moderate aerobic training. An oral glucose tolerance test (OGTT) was performed and both fasting plasma insulin and the homeostasis model assessment (HOMA) index were assessed at the start, and after four, eight and twelve weeks. CT demonstrated significant decrease in OGTT area under the curve compared to PT (P = 0.034). There were no differences between groups or over time in fasting insulin or HOMA. The results suggest that creatine supplementation, combined with aerobic training, can improve glucose tolerance but does not affect insulin sensitivity, and may warrant further investigation with diabetic subjects.

Performance of body fat and body mass index cutoffs in elevated blood pressure screening among male children and adolescents

For percentage of body fat (%BF), there are no internationally accepted cutoffs. The primary function of body fat cutoffs should be to identify not only excessive body fatness, but also the increased risk of unhealthy outcomes, such as hypertension. The purpose of this study was to analyze the accuracy of different %BF and body mass index (BMI) cutoffs as screening measures for EBP in pediatric populations. It was a cross-sectional study with a sample of 358 male subjects from 8 to 18 years old. BP was measured by the oscilometric method, and body composition was measured by dual-energy X-ray absorptiometry (DXA). The accuracy of three reference tables used for body fat cutoffs was assessed. The three body fat reference tables were highly specific, but insensitive, for elevated BP screening. For elevated BP screening, all body fat cutoffs presented similar sensitivity (range=48.3-53.7%) and specificity (range=79.2-84.1%). The body fat cutoffs performed no better than BMI in screening of children and adolescents at risk of elevated BP (EBP). BMI seems a more attractive tool for this function, as it performed similarly and can be applied in large surveys and with lower costs. Hypertension Research (2011) 34, 963-967; doi:10.1038/hr.2011.61; published online 26 May 2011

Exercise Intensity, Inflammatory Signaling, and Insulin Resistance in Obese Rats

DA SILVA, A. S. R., J. R. PAULI, E. R. ROPELLE, A. G. OLIVEIRA, D. E. CINTRA, C. T. DE SOUZA, L. A. VELLOSO, J. B. C. CARVALHEIRA, and M. J. A. SAAD. Exercise Intensity, Inflammatory Signaling, and Insulin Resistance in Obese Rats. Med. Sci. Sports Exerc., Vol. 42, No. 12, pp. 2180-2188, 2010. Purpose: To evaluate the effects of intensity of exercise on insulin resistance and the expression of inflammatory proteins in the skeletal muscle of diet-induced obese (DIO) rats after a single bout of exercise. Methods: In the first exercise protocol, the rats swam for two 3-h bouts, separated by a 45-min rest period (with 6 h in duration-DIO + EXE), and in the second protocol, the rats were exercised with 45 min of swimming at 70% of the maximal lactate steady state-MLSS (DIO + MLSS). Results: Our data demonstrated that both protocols of exercise increased insulin sensitivity and increased insulin-stimulated tyrosine phosphorylation of insulin receptor and insulin receptor substrate 1 and serine phosphorylation of protein kinase B in the muscle of DIO rats by the same magnitude. In parallel, both exercise protocols also reduced protein tyrosine phosphatase 1B activity and insulin receptor substrate 1 serine phosphorylation, with concomitant reduction in c-jun N-terminal kinase and I kappa B kinase activities in the muscle of DIO rats in a similar fashion. Conclusions: Thus, our data demonstrate that either exercise protocols with low intensity and high volume or exercise with moderate intensity and low volume represents different strategies to restore insulin sensitivity with the same efficacy.

Evaluation of three brands of drug interaction software for use in intensive care units

Objective To evaluate drug interaction software programs and determine their accuracy in identifying drug-drug interactions that may occur in intensive care units. Setting The study was developed in Brazil. Method Drug interaction software programs were identified through a bibliographic search in PUBMED and in LILACS (database related to the health sciences published in Latin American and Caribbean countries). The programs` sensitivity, specificity, and positive and negative predictive values were determined to assess their accuracy in detecting drug-drug interactions. The accuracy of the software programs identified was determined using 100 clinically important interactions and 100 clinically unimportant ones. Stockley`s Drug Interactions 8th edition was employed as the gold standard in the identification of drug-drug interaction. Main outcome Sensitivity, specificity, positive and negative predictive values. Results The programs studied were: Drug Interaction Checker (DIC), Drug-Reax (DR), and Lexi-Interact (LI). DR displayed the highest sensitivity (0.88) and DIC showed the lowest (0.69). A close similarity was observed among the programs regarding specificity (0.88-0.92) and positive predictive values (0.88-0.89). The DIC had the lowest negative predictive value (0.75) and DR the highest (0.91). Conclusion The DR and LI programs displayed appropriate sensitivity and specificity for identifying drug-drug interactions of interest in intensive care units. Drug interaction software programs help pharmacists and health care teams in the prevention and recognition of drug-drug interactions and optimize safety and quality of care delivered in intensive care units.

COMPARATIVE STUDY OF THE SENSITIVITY OF DIABETIC LOWER EXTREMITIES WITH AND WITHOUT ULCERS USING THE PSSD (TM)

Introduction To determine and compare thresholds of cutaneous sensitivity of lower extremities in diabetic patients with an ulcer on only one lower extremity Methods and Materials The study group included 20 patients with mean age of 61 6 and average time with diabetes of 12 4 years All patients were previously tested using Semmes-Weinstein monofilament 5 07 Sensitivity was evaluated using the two point discrimination test and the PSSD (TM) (Pressure-Specified Sensory Device) in order to assess touch thresholds in a quantitative manner, in g/mm(2) Three skin areas were tested hallux pulp, dorsum of foot and medial heel, including four tests 1 point static, 1 point moving, 2 points static and 2 points moving Results Mean 2 point discrimination distance in mm was higher in feet with ulcers, but the difference between extremities was only statistically significant for the hallux. With the PSSD (TM), all patients had higher pressure thresholds in feet with ulcers when compared with feet without ulcers, in all tests, with statistical significance Conclusion The PSSD (TM) was able to differentiate levels of sensation between extremities with and without ulcers in diabetic patients, with statistical significance

Sensorless synchronization method for thin-film direct optical broadband monitoring system

Optical monitoring systems are necessary to manufacture multilayer thin-film optical filters with low tolerance on spectrum specification. Furthermore, to have better accuracy on the measurement of film thickness, direct monitoring is a must. Direct monitoring implies acquiring spectrum data from the optical component undergoing the film deposition itself, in real time. In making film depositions on surfaces of optical components, the high vacuum evaporator chamber is the most popular equipment. Inside the evaporator, at the top of the chamber, there is a metallic support with several holes where the optical components are assembled. This metallic support has rotary motion to promote film homogenization. To acquire a measurement of the spectrum of the film in deposition, it is necessary to pass a light beam through a glass witness undergoing the film deposition process, and collect a sample of the light beam using a spectrometer. As both the light beam and the light collector are stationary, a synchronization system is required to identify the moment at which the optical component passes through the light beam.

Harmonic identification using parallel neural networks in single-phase systems

In this paper, artificial neural networks are employed in a novel approach to identify harmonic components of single-phase nonlinear load currents, whose amplitude and phase angle are subject to unpredictable changes, even in steady-state. The first six harmonic current components are identified through the variation analysis of waveform characteristics. The effectiveness of this method is tested by applying it to the model of a single-phase active power filter, dedicated to the selective compensation of harmonic current drained by an AC controller. Simulation and experimental results are presented to validate the proposed approach. (C) 2010 Elsevier B. V. All rights reserved.

Studies of cases in power systems by Sensitivity Analysis oriented by OPF

This paper presents studies of cases in power systems by Sensitivity Analysis (SA) oriented by Optimal Power Flow (OPF) problems in different operation scenarios. The studies of cases start from a known optimal solution obtained by OPF. This optimal solution is called base case, and from this solution new operation points may be evaluated by SA when perturbations occur in the system. The SA is based on Fiacco`s Theorem and has the advantage of not be an iterative process. In order to show the good performance of the proposed technique tests were carried out on the IEEE 14, 118 and 300 buses systems. (C) 2010 Elsevier Ltd. All rights reserved.

High accuracy and fast acquisition time of polarisation nulling-based OSNR monitor

A technique for improving the performance of an OSNR monitor based on a polarisation nulling method with the downhill simplex algorithm is demonstrated. Establishing a compromise between accuracy and acquisition time, the monitor has been calibrated to 0.72 dB/390 ms and 0.98 dB/320 ms, over a range of nearly 21 dB. As far as is known, these are the best values achieved with such an OSNR monitoring method.

An approach of optimal sensitivity applied in the tertiary loop of the automatic generation control

This paper proposes an approach of optimal sensitivity applied in the tertiary loop of the automatic generation control. The approach is based on the theorem of non-linear perturbation. From an optimal operation point obtained by an optimal power flow a new optimal operation point is directly determined after a perturbation, i.e., without the necessity of an iterative process. This new optimal operation point satisfies the constraints of the problem for small perturbation in the loads. The participation factors and the voltage set point of the automatic voltage regulators (AVR) of the generators are determined by the technique of optimal sensitivity, considering the effects of the active power losses minimization and the network constraints. The participation factors and voltage set point of the generators are supplied directly to a computational program of dynamic simulation of the automatic generation control, named by power sensitivity mode. Test results are presented to show the good performance of this approach. (C) 2008 Elsevier B.V. All rights reserved.