Electrical cardioversion presents one of the treatment options for atrial fibrillation (AF). However, the early recurrence rate is high, reaching ~40% three months after the procedure. Features based on vectorcardiographic signals were explored to find association with early recurrence of AF. Eighty-four patients with non-paroxysmal AF referred to electrical cardioversion were prospectively studied; early AF recurrence was present in 40 (47.6%). Patients underwent 24-h Holter ECG monitoring three months after the procedure to assess AF recurrence. Pre-procedural 12-lead ECGs (10 s, 1 kHz) were recorded and automatically analyzed. We explored associations of VCG-based features with early AF recurrence. Two features were strongly associated with AF recurrence: (1) a mean VCG (y-axis) signal slope in a window starting 145 ms before QRS center, lasting for 190 ms (AUC 0.778, p < 0.001), and (2) a mean VCG (z-axis) signal slope in a window starting 60 ms after QRS center, lasting for 465 ms (AUC 0.744, p < 0.001). These features showed higher association to the outcome than eighteen baseline clinical features. Our approach revealed features based on a slope of vectorcardiographic signals. This work also suggests that state of ventricles strongly affects the AF recurrence after electrical cardioversion.
- MeSH
- elektrická defibrilace * MeSH
- elektrokardiografie ambulantní MeSH
- fibrilace síní * terapie patofyziologie MeSH
- lidé středního věku MeSH
- lidé MeSH
- prospektivní studie MeSH
- recidiva * MeSH
- senioři MeSH
- vektorkardiografie * metody MeSH
- výsledek terapie MeSH
- Check Tag
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
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.
- MeSH
- artefakty MeSH
- datové soubory jako téma MeSH
- deep learning * MeSH
- elektroencefalografie klasifikace přístrojové vybavení metody MeSH
- lidé MeSH
- ROC křivka MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- pozorovací studie MeSH
- práce podpořená grantem MeSH
- Research Support, N.I.H., Extramural MeSH
- validační studie MeSH
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.
False alarms in intensive care units represent a serious threat to patients. We propose a method for detection of five live-threatening arrhythmias. It is designed to work with multimodal data containing electrocardiograph and arterial blood pressure or photoplethysmograph signals. The presented method is based on descriptive statistics and Fourier and Hilbert transforms. It was trained using 750 records. The method was validated during the follow-up phase of the CinC/Physionet Challenge 2015 on a hidden dataset with 500 records, achieving a sensitivity of 93% (95%) and a specificity of 87% (88%) for real-time (retrospective) files. The given sensitivity and specificity resulted in score of 81.62 (84.96) for real-time (retrospective) records. The presented method is an improved version of the original algorithm awarded the first and the second prize in CinC/Physionet Challenge 2015.
- MeSH
- algoritmy * MeSH
- elektrokardiografie přístrojové vybavení MeSH
- falešně pozitivní reakce MeSH
- fotopletysmografie přístrojové vybavení MeSH
- jednotky intenzivní péče * MeSH
- klinické alarmy * MeSH
- krevní tlak MeSH
- lidé MeSH
- monitorování fyziologických funkcí přístrojové vybavení MeSH
- počítačové zpracování signálu * MeSH
- srdeční arytmie diagnóza patofyziologie MeSH
- strojové učení MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
The growing technical standard of acquisition systems allows the acquisition of large records, often reaching gigabytes or more in size as is the case with whole-day electroencephalograph (EEG) recordings, for example. Although current 64-bit software for signal processing is able to process (e.g. filter, analyze, etc) such data, visual inspection and labeling will probably suffer from rather long latency during the rendering of large portions of recorded signals. For this reason, we have developed SignalPlant-a stand-alone application for signal inspection, labeling and processing. The main motivation was to supply investigators with a tool allowing fast and interactive work with large multichannel records produced by EEG, electrocardiograph and similar devices. The rendering latency was compared with EEGLAB and proves significantly faster when displaying an image from a large number of samples (e.g. 163-times faster for 75 × 10(6) samples). The presented SignalPlant software is available free and does not depend on any other computation software. Furthermore, it can be extended with plugins by third parties ensuring its adaptability to future research tasks and new data formats.
The objective is to study the involvement of the posterior medial cortex (PMC) in encoding and retrieval by visual and auditory memory processing. Intracerebral recordings were studied in two epilepsy-surgery candidates with depth electrodes implanted in the retrosplenial cingulate, precuneus, cuneus, lingual gyrus and hippocampus. We recorded the event-related potentials (ERP) evoked by visual and auditory memory encoding-retrieval tasks. In the hippocampus, ERP were elicited in the encoding and retrieval phases in the two modalities. In the PMC, ERP were recorded in both the encoding and the retrieval visual tasks; in the auditory modality, they were recorded in the retrieval task, but not in the encoding task. In conclusion, the PMC is modality dependent in memory processing. ERP is elicited by memory retrieval, but it is not elicited by auditory encoding memory processing in the PMC. The PMC appears to be involved not only in higher-order top-down cognitive activities but also in more basic, rather than bottom-up activities.
- MeSH
- akustická stimulace MeSH
- dospělí MeSH
- elektroencefalografie metody MeSH
- epilepsie patofyziologie MeSH
- implantované elektrody MeSH
- lidé MeSH
- mozek fyziologie MeSH
- paměť fyziologie MeSH
- počítačové zpracování signálu MeSH
- sluchové evokované potenciály fyziologie MeSH
- světelná stimulace MeSH
- zrakové evokované potenciály fyziologie MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mužské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
OBJECTIVE: The aim of this work was to study the oscillatory changes during target and distractor stimuli processing. We focused mainly on responses after distractor stimuli in the prefrontal cortex and their possible relation to our previous results from the basal ganglia. METHODS: Five epilepsy surgery candidates with implanted depth electrodes performed a three-stimulus paradigm. The frequent stimulus (70%; without required response) was a small blue circle, the target stimulus (15%; with motor response) was a larger blue circle, and the distractor stimulus (15%; without required response) was a checkerboard. The SEEG signals from 404 electrode contacts were analysed using event-related de/synchronization (ERD/S) methodology. RESULTS: The main response to the target stimuli was ERD in the alpha and low beta bands, predominantly in the motor control areas, parietal cortex and hippocampus. The distractor stimuli were generally accompanied by an early theta frequency band power increase most markedly in the prefrontal cortex. CONCLUSIONS: Different ERD/S patterns underline attentional shifting to rare target ("go") and distractor ("no-go") stimuli. SIGNIFICANCE: As an increase in lower frequency band power is considered to be a correlate of active inhibition, the prefrontal structures seem to be essential for inhibition of non-required movements.
- MeSH
- alfa rytmus EEG fyziologie MeSH
- beta rytmus EEG fyziologie MeSH
- biologické hodiny fyziologie MeSH
- dospělí MeSH
- elektroencefalografie * MeSH
- epilepsie patofyziologie MeSH
- evokované potenciály fyziologie MeSH
- kognice fyziologie MeSH
- korová synchronizace fyziologie MeSH
- lidé MeSH
- mladiství MeSH
- modely neurologické * MeSH
- prefrontální mozková kůra fyziologie MeSH
- psychomotorický výkon fyziologie MeSH
- světelná stimulace metody MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mladiství MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- srovnávací studie MeSH
We analysed respiratory induced heart rate and blood pressure variability in mechanically ventilated patients with different levels of sedation and central nervous system activity. Our aim was to determine whether it is possible to distinguish different levels of sedation or human brain activity from heart rate and blood pressure. We measured 19 critically ill and 15 brain death patients ventilated at various respiratory frequencies - 15, 12, 8 and 6 breaths per minute. Basal and deeper sedation was performed in the critically ill patients. We detected and analysed heart rate and blood pressure parameters induced by ventilation. Results: Respiratory induced heart rate variability is the unique parameter that can differentiate between brain death patients and sedated critically ill patients. Significant differences exist, especially during slow deep breathing with a mean period of 10 seconds. The limit values reflecting brain death are: baroreflex lower than 0.5 ms/mmHg and tidal volume normalised heart rate variability lower than 0.5 ms/ml. Reduced heart rate variability parameters of brain death patients remain unchanged even after normalisation to respiration volume. However, differences between basal and deep sedation do not appear significant on any parameter.
- MeSH
- dechový objem fyziologie MeSH
- diastola fyziologie MeSH
- dýchání * MeSH
- krevní tlak fyziologie MeSH
- kritický stav * MeSH
- lidé MeSH
- mozková smrt patofyziologie MeSH
- srdeční frekvence fyziologie MeSH
- systola fyziologie MeSH
- umělé dýchání * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
