Exploiting Graphoelements and Convolutional Neural Networks with Long Short Term Memory for Classification of the Human Electroencephalogram.

The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.

Respiratory-induced hemodynamic changes measured by whole-body multichannel impedance plethysmography.

The cardiovascular system is described by parameters including blood flow, blood distribution, blood pressure, heart rate and pulse wave velocity. Dynamic changes and mutual interactions of these parameters are important for understanding the physiological mechanisms in the cardiovascular system. The main objective of this study is to introduce a new technique based on parallel continuous bioimpedance measurements on different parts of the body along with continuous blood pressure, ECG and heart sound measurement during deep and spontaneous breathing to describe interactions of cardiovascular parameters. Our analysis of 30 healthy young adults shows surprisingly strong deep-breathing linkage of blood distribution in the legs, arms, neck and thorax. We also show that pulse wave velocity is affected by deep breathing differently in the abdominal aorta and extremities. Spontaneous breathing does not induce significant changes in cardiovascular parameters.

Heart sounds analysis using probability assessment.

OBJECTIVE: This paper describes a method for automated discrimination of heart sounds recordings according to the Physionet Challenge 2016. The goal was to decide if the recording refers to normal or abnormal heart sounds or if it is not possible to decide (i.e. 'unsure' recordings). APPROACH: Heart sounds S1 and S2 are detected using amplitude envelopes in the band 15-90 Hz. The averaged shape of the S1/S2 pair is computed from amplitude envelopes in five different bands (15-90 Hz; 55-150 Hz; 100-250 Hz; 200-450 Hz; 400-800 Hz). A total of 53 features are extracted from the data. The largest group of features is extracted from the statistical properties of the averaged shapes; other features are extracted from the symmetry of averaged shapes, and the last group of features is independent of S1 and S2 detection. Generated features are processed using logical rules and probability assessment, a prototype of a new machine-learning method. MAIN RESULTS: The method was trained using 3155 records and tested on 1277 hidden records. It resulted in a training score of 0.903 (sensitivity 0.869, specificity 0.937) and a testing score of 0.841 (sensitivity 0.770, specificity 0.913). The revised method led to a test score of 0.853 in the follow-up phase of the challenge. SIGNIFICANCE: The presented solution achieved 7th place out of 48 competing entries in the Physionet Challenge 2016 (official phase). In addition, the PROBAfind software for probability assessment was introduced.

Can we hear ventricle dyssynchrony? Yes, we can.

This study introduces a method for detection of ventricular depolarization activity and the transfer of this activity into an audible stereo audio signal. Heart potentials are measured by an ultra-high-frequency high-dynamic-range electrocardiograph (UHF-ECG) with a 25-kHz sampling rate. Averaged and prolonged UHF amplitude envelopes of V1-3 and V4-6 leads at a frequency range of 500-1000 Hz are used as a modulating function for two carrier audio frequencies. The right speaker makes it possible to listen to the depolarization of the septum and right ventricle (V1-3) and the left speaker the left ventricle lateral wall (V4-6). In the healthy heart, both speakers can be heard simultaneously. A delayed L or R speaker represents the dyssynchronous electrical activation of the ventricles. Examples of the normal heart, right bundle branch block and left bundle branch block can be heard at www.medisig.com/uhfecg.

Excitation specificity of repolarization parameters.

UNLABELLED: The excitation specificity of QT dynamic parameters was tested on three groups of subjects: healthy subjects; non-medicated hypertensive subjects with metabolic syndrome; and subjects with essential hypertension. Four different excitations of RR were used: bicycling exercise; tilt with breathing 0.1 and 0.33 Hz; and deep breathing. Linear dynamic feedback model of QT/RR coupling was supposed at the analysis and next repolarization parameters were tested: QTc; gain of QT/RR coupling for slow and fast RR variability; time constant of QT adaptation; and random QT variability. RESULTS: Dynamic repolarization parameters statistically significantly depend on the type of RR excitation. The gain of QT/RR coupling for slow RR variability, the time constant of QT adaptation and QTc are maximal at RR excitation given by the bicycling exercise. The frequency of breathing, i.e. corresponding vagal modulation has no effect on repolarization parameters. The measurements with deep breathing, without any other slow excitation of heart rate, has low signal-to-noise ratio of analyzed data and resulting QT parameters are inaccurate. CONCLUSION: The use of heart rate excitation and all measurements conditions should be defined for the exact analysis of the repolarization dynamic parameters.