N. Maglaveras

Indicators of sleepiness in an ambulatory EEG study of night driving.

Driver sleepiness due to sleep deprivation is a causative factor in 1% to 3% of all motor vehicle crashes. In recent studies, the importance of developing driver fatigue countermeasure devices has been stressed, in order to help prevent driving accidents and errors. Although numerous physiological indicators are available to describe an individuals level of alertness, the EEG signal has been shown to be one of the most predictive and reliable, since it is a direct measure of brain activity. In the present study, multichannel EEG data that were collected from 20 sleep-deprived subjects during real environmental conditions of driving are presented for the first time. EEG datas annotation made by two independent Medical Doctors revealed an increase of slowing activity and an acute increase of the alpha waves 5-10 seconds before driving events. From the EEG data that were collected, the Relative Band Ratio (RBR) of the EEG frequency bands, the Shannon Entropy, and the Kullback-Leibler (KL) Entropy were estimated for each one second segment. The mean values of these measurements were estimated for 5 minutes periods. Analysis revealed a significant increase of alpha waves relevant band ratios (RBR), a decrease of gamma waves RBR, and a significant decrease of KL entropy when the first and the last 5-min periods were compared. A rapid decrease of both Shannon and K-L entropies was observed just before the driving events. Conclusively, EEG can assess effectively the brain activity alterations that occur a few seconds before sleeping/drowsiness events in driving, and its quantitative measurements can be used as potential sleepiness indicators for future development of driver fatigue countermeasure devices

Investigation of heart rate and blood pressure variability, baroreflex sensitivity, and approximate entropy in acute brain injury patients

PURPOSE The purpose of the study was to investigate longitudinally over time heart rate (HR) and blood pressure variability and baroreflex sensitivity in acute brain injury patients and relate them with the severity of neurologic dysfunction and outcome. METHODS Data from 20 brain injured patients due to multiple causes and treated in the intensive care unit were used, with HR and blood pressure recorded from monitors and analyzed on a daily basis. We performed power spectral analysis estimating low frequencies (LF: 0.04-0.15 Hz), high frequencies (HF: 0.15-0.4 Hz), and their ratio and calculated the approximate entropy, which assesses periodicity within a signal and transfer function (TF), that estimates baroreflex sensitivity. Heart rate variance was considered as a measure of HR variability. RESULTS Nonsurvivors (brain dead) had lower approximate entropy (0.65 +/- 0.24 vs 0.84 +/- 0.26, P < .05) and lower variance mean values (0.48 +/- 0.54 vs 1.29 +/- 0.42 ms(2)/Hz, P < .01), lower LF and HF minimum values (0.31 +/- 0.88 vs 1.11 +/- 0.46, P < .01; and 0.27 +/- 0.42 vs 0.86 +/- 0.30, P < .01, respectively), lower LF/HF (0.22 +/- 0.29 vs 0.62 +/- 0.28, P < .01), and lower TF mean values (0.43 +/- 0.29 vs 1.11 +/- 0.74, P < .05) during their whole stay in the intensive care unit in relation with survivors. The mean variance (P < .05), mean TF (P < .05), and mean LF/HF (P < .05) were significantly successful in separating survivors from nonsurvivors. CONCLUSIONS We conclude that in acute brain injury patients, low variability, low baroreflex sensitivity, and sustained decrease in LF/HF of HR signals are linked with a high mortality rate.

Changes of heart and respiratory rate dynamics during weaning from mechanical ventilation: A study of physiologic complexity in surgical critically ill patients

PURPOSE The aim of the study was to investigate heart rate (HR) and respiratory rate (RR) complexity in patients with weaning failure or success, using both linear and nonlinear techniques. MATERIALS AND METHODS Forty-two surgical patients were enrolled in the study. There were 24 who passed and 18 who failed a weaning trial. Signals were analyzed for 10 minutes during 2 phases: (1) pressure support (PS) ventilation (15-20 cm H(2)O) and (2) weaning trials with PS (5 cm H(2)O). Low- and high-frequency (LF, HF) components of HR signals, HR multiscale entropy (MSE), RR sample entropy, cross-sample entropy between cardiorespiratory signals, Poincaré plots, and α1 exponent were computed in all patients and during the 2 phases of PS. RESULTS Weaning failure patients exhibited significantly decreased RR sample entropy, LF, HF, and α1 exponent, compared with weaning success subjects (P < .001). Their changes were opposite between the 2 phases, except for MSE that increased between and within groups (P < .001). A new model including rapid shallow breathing index (RSBI), α1 exponent, RR, and cross-sample entropies predicted better weaning outcome compared with RSBI, airway occlusion pressure at 0.1 second (P(0.1)), and RSBI × P(0.1) (conventional model, R(2) = 0.887 vs 0.463; P < .001). Areas under the curve were 0.92 vs 0.86, respectively (P < .005). CONCLUSIONS We suggest that nonlinear analysis of cardiorespiratory dynamics has increased prognostic impact upon weaning outcome in surgical patients.

Effects of mental workload and caffeine on catecholamines and blood pressure compared to performance variations

Caffeine is characterised as a central nervous system stimulant, also affecting metabolic and cardiovascular functions. A number of studies have demonstrated an effect of caffeine on the excretion of catecholamines and their metabolites. Urinary epinephrine and norepinephrine have been shown to increase after caffeine administration. Similar trends were observed in our study in adrenaline (ADR) and noradrenaline (NORADR) levels and additionally a dose dependent effect of caffeine. The effect of caffeine on cognitive performance, blood pressure, and catecholamines was tested under resting conditions and under mental workload. Each subject performed the test after oral administration of 1 cup and then 3 cups of coffee. Root mean square error (RMSE) for the tracking task was continuously monitored. Blood pressure was also recorded before and after each stage of the experiment. Catecholamines were collected and measured for three different conditions as: at rest, after mental stress alone, after one dose of caffeine under stress, and after triple dose of caffeine under stress. Comparison of the performance of each stage with the resting conditions revealed statistically significant differences between group of smokers/coffee drinkers compared with the other two groups of non-coffee drinkers/non-smokers and non-smokers/coffee drinkers. There was no statistically significant difference between the last two groups. There was an increase of urine adrenaline with 1 cup of coffee and statistically significant increase of urine noradrenaline. Both catecholamines were significantly increased with triple dose of caffeine. Mental workload increased catecholamines. There was a dose dependent effect of caffeine on catecholamines.

One-lead ischemia detection using a new backpropagation algorithm and the European ST-T database

A supervised neural network (NN) based algorithm was used to detect ischemic episodes from electrocardiograms (ECGs). The algorithm is tested on the European ST-T database. The algorithm is very fast in its recall state due to the NN, and uses the minimum amount of information, since it is applied on a one-lead ECG. The adaptive training backpropagation algorithm reduces dramatically the training time, and makes possible adjustment training. Even though the algorithm has some problems with detecting the exact onset and end of an ischemic episode, its performance was encouraging since it had a gross sensitivity of 84.4% for ischemia episode detection in the 60 out of 90 records on which it was initially tested. Thus, it seems to be suitable for use in critical care units due to its speed and training capabilities.<<ETX>>

Temperature variability analysis using wavelets and multiscale entropy in patients with systemic inflammatory response syndrome, sepsis, and septic shock

BackgroundEven though temperature is a continuous quantitative variable, its measurement has been considered a snapshot of a process, indicating whether a patient is febrile or afebrile. Recently, other diagnostic techniques have been proposed for the association between different properties of the temperature curve with severity of illness in the Intensive Care Unit (ICU), based on complexity analysis of continuously monitored body temperature. In this study, we tried to assess temperature complexity in patients with systemic inflammation during a suspected ICU-acquired infection, by using wavelets transformation and multiscale entropy of temperature signals, in a cohort of mixed critically ill patients.MethodsTwenty-two patients were enrolled in the study. In five, systemic inflammatory response syndrome (SIRS, group 1) developed, 10 had sepsis (group 2), and seven had septic shock (group 3). All temperature curves were studied during the first 24 hours of an inflammatory state. A wavelet transformation was applied, decomposing the signal in different frequency components (scales) that have been found to reflect neurogenic and metabolic inputs on temperature oscillations. Wavelet energy and entropy per different scales associated with complexity in specific frequency bands and multiscale entropy of the whole signal were calculated. Moreover, a clustering technique and a linear discriminant analysis (LDA) were applied for permitting pattern recognition in data sets and assessing diagnostic accuracy of different wavelet features among the three classes of patients.ResultsStatistically significant differences were found in wavelet entropy between patients with SIRS and groups 2 and 3, and in specific ultradian bands between SIRS and group 3, with decreased entropy in sepsis. Cluster analysis using wavelet features in specific bands revealed concrete clusters closely related with the groups in focus. LDA after wrapper-based feature selection was able to classify with an accuracy of more than 80% SIRS from the two sepsis groups, based on multiparametric patterns of entropy values in the very low frequencies and indicating reduced metabolic inputs on local thermoregulation, probably associated with extensive vasodilatation.ConclusionsWe suggest that complexity analysis of temperature signals can assess inherent thermoregulatory dynamics during systemic inflammation and has increased discriminating value in patients with infectious versus noninfectious conditions, probably associated with severity of illness.

Study of multiparameter respiratory pattern complexity in surgical critically ill patients during weaning trials

BackgroundSeparation from mechanical ventilation is a difficult task, whereas conventional predictive indices have not been proven accurate enough, so far. A few studies have explored changes of breathing pattern variability for weaning outcome prediction, with conflicting results. In this study, we tried to assess respiratory complexity during weaning trials, using different non-linear methods derived from theory of complex systems, in a cohort of surgical critically ill patients.ResultsThirty two patients were enrolled in the study. There were 22 who passed and 10 who failed a weaning trial. Tidal volume and mean inspiratory flow were analyzed for 10 minutes during two phases: 1. pressure support (PS) ventilation (15-20 cm H2O) and 2. weaning trials with PS: 5 cm H2O. Sample entropy (SampEn), detrended fluctuation analysis (DFA) exponent, fractal dimension (FD) and largest lyapunov exponents (LLE) of the two respiratory parameters were computed in all patients and during the two phases of PS. Weaning failure patients exhibited significantly decreased respiratory pattern complexity, reflected in reduced sample entropy and lyapunov exponents and increased DFA exponents of respiratory flow time series, compared to weaning success subjects (p < 0.001). In addition, their changes were opposite between the two phases of the weaning trials. A new model including rapid shallow breathing index (RSBI), its product with airway occlusion pressure at 0.1 sec (P0.1), SampEn and LLE predicted better weaning outcome compared with RSBI, P0.1 and RSBI* P0.1 (conventional model, R2 = 0.874 vs 0.643, p < 0.001). Areas under the curve were 0.916 vs 0.831, respectively (p < 0.05).ConclusionsWe suggest that complexity analysis of respiratory signals can assess inherent breathing pattern dynamics and has increased prognostic impact upon weaning outcome in surgical patients.

Uncertainty rule generation on a home care database of heart failure patients

In this paper we present the uncertainty rule generator tool and the algorithm used. This data-mining tool generates uncertainty rules as apart of the knowledge discovery in databases process and is tested upon a home-care database containing data from congestive heart failure patients over a period of approx. 10 months. This algorithm can handle dynamic data without the need of recovering the itemsets from the beginning. This is highly appropriate for a home-care monitoring system, where new records are constantly added. Moreover it can deal with missing values, since it uses flexible metrics, similar to those of other association rule algorithms. Finally this algorithm computes a certainty factor for each extracted rule, which is representative of its efficiency. In a future step, this extracted rule can be used on newly entered data, in order to predict the missing values, while its certainty factor will allow the exact estimation of error in this prediction.

Wave segmentation using nonstationary properties of ECG

This paper examines the nonstationary statistical properties of ECG and uses them in signal segmentation. The ECG signal is grouped in three different groups that are defined by QRS complex, P and T waves. These groups are defined by performing nonstationary spectral analysis. A standard autoregressive model is used to extract coefficients of local stationary ECG beat segment. Such a filter is useful for tracking changes in local statistical properties. Finally a Hidden Markov model is used for automatic segmentation. Due to the locality of signal statistical properties, it is important the Hidden Markov model to be initialised carefully. Thus, the initialisation of Hidden Markov chain is accomplished using autoregressive (AR) filter coefficients. The ECG signals are finally segmented into stationary regimes characterized by different autoregressive models in a beat by beat basis. This method has been tested in different ECG signals from the MIT-BIH database. The results showed that there is a good percentage in identification of ECG basic morphologies while there are a number of problems in starting and ending points of segments. The overall results are not affected by low signal to noise ratio. Another advantage of this algorithm is that it is independent of temporal signal changes because of its adaptive nature. In conclusion this algorithm could be used in automated ECG constituent wave detection, something that is useful in telemedicine based environment.

Ischemic classification techniques using an advanced neural network algorithm

The correct classification of the beats relies heavily on the efficiency of the features extracted from the ST-segment and on the desired abilities of algorithm on sensitivity and specificity indices. Nonlinear Principal Component Analysis (NLPCA) is a recently proposed method for nonlinear feature extraction. It has been observed to have better performance for representing complex ST segment features of normal and abnormal cases. The function of representation was created using only normal patterns from the same patient. The distribution of these patterns is modeled using a Radial Basis Function Network (RBFN). This model is capable of finding abnormal patterns with high sensitivity while the specificity is also acceptable (>70%), and the authors can accomplish correct classification rates of higher than 90% for the ischemic beats in many files of the European ST-T database. This technique may be used, in general, for other classification problems in medicine and other disciplines.