Marina Ronzhina

Sleep scoring using artificial neural networks

Rapid development of computer technologies leads to the intensive automation of many different processes traditionally performed by human experts. One of the spheres characterized by the introduction of new high intelligence technologies substituting analysis performed by humans is sleep scoring. This refers to the classification task and can be solved - next to other classification methods - by use of artificial neural networks (ANN). ANNs are parallel adaptive systems suitable for solving of non-linear problems. Using ANN for automatic sleep scoring is especially promising because of new ANN learning algorithms allowing faster classification without decreasing the performance. Both appropriate preparation of training data as well as selection of the ANN model make it possible to perform effective and correct recognizing of relevant sleep stages. Such an approach is highly topical, taking into consideration the fact that there is no automatic scorer utilizing ANN technology available at present.

ECG features and methods for automatic classification of ventricular premature and ischemic heartbeats: A comprehensive experimental study

Accurate detection of cardiac pathological events is an important part of electrocardiogram (ECG) evaluation and subsequent correct treatment of the patient. The paper introduces the results of a complex study, where various aspects of automatic classification of various heartbeat types have been addressed. Particularly, non-ischemic, ischemic (of two different grades) and subsequent ventricular premature beats were classified in this combination for the first time. ECGs recorded in rabbit isolated hearts under non-ischemic and ischemic conditions were used for analysis. Various morphological and spectral features (both commonly used and newly proposed) as well as classification models were tested on the same data set. It was found that: a) morphological features are generally more suitable than spectral ones; b) successful results (accuracy up to 98.3% and 96.2% for morphological and spectral features, respectively) can be achieved using features calculated without time-consuming delineation of QRS-T segment; c) use of reduced number of features (3 to 14 features) for model training allows achieving similar or even better performance as compared to the whole feature sets (10 to 29 features); d) k-nearest neighbours and support vector machine seem to be the most appropriate models (accuracy up to 98.6% and 93.5%, respectively).

Classification of ventricular premature and ischemic beats in animal electrograms

Many approaches have been proposed for automatic classification of different pathological events in ECG signals. Present study is focused on analysis and classification of non-ischemic, moderate and severe ischemic, and VPB segments in data obtained in rabbit isolated hearts. It is shown, that use of low number of morphological parameters calculated from electrograms combined with even simple classification method allows achieving of accurate results (with overall accuracy up to 0.99) for four types of the segments.

Computer analysis of isolated cardiomyocyte contraction process via advanced image processing techniques

Isolated cardiomyocytes have been used as valid and useful model in experimental cardiology research for decades. The cell contraction function is usually measured via expensive and complex instruments which can either damage the cell or take much time for setting up. In contrary, recent development of optical microscopy and digital cameras suggests utilization of touch-less cardiomyocyte video acquisition in connection with advanced image processing techniques for evaluation of the cell contraction process. The proposed paper presents an automatic membrane detection method via computer processing of acquired video-sequences by utilization of an active contour model. Evaluation of detected cell area is used for estimation of cardiomyocyte contraction function. The method is evaluated utilizing the comparison with contraction measurement performed via atomic force microscopy technique.

Real-time measurement of cardiomyocyte contraction and calcium transients using fast image processing algorithms

An improved technique for recording of contrac-tion of heart cells simultaneously with recording of calcium transients by fluorescence method is introduced. The tech-nique aims to quantify contractions under conditions including low image quality caused by reduced transmitted light. The proposed methods allow more accurate detection, lower error rate using the up-to-date image processing, and automation of the process comparing to recent approaches. The technique is compared with direct optical measurement method using processing of two-dimensional digital images of the cardiac cell. The technique is improved to be fast enough to be includ-ed in the system for real-time measurements.

Use of EEG for validation of flicker-fusion test

There are many different methods for evaluation of alertness level of a person. The commonly used questionnaires and some physiological test such as flicker-fusion (FF) test are not objective. Other objective methods based on the analysis of biological signals can be used for validation of these tests. The present study is focused on analysis of spectral features of EEG measured in sleep deprived subjects during experiment containing FF test performing. The results of the study show that FF test does not affect electrical brain activity dramatically and, thus, can be used for alertness level evaluation. It is also shown that subjective determination of state using questionnaires can differ from those obtained by objective method based on the analysis of EEG. These results can be useful for correct interpretation of FF test results.

Effect of increased left ventricle mass on ischemia assessment in electrocardiographic signals: rabbit isolated heart study

BackgroundDetailed quantitative analysis of the effect of left ventricle (LV) hypertrophy on myocardial ischemia manifestation in ECG is still missing. The associations between both phenomena can be studied in animal models. In this study, rabbit isolated hearts with spontaneously increased LV mass were used to evaluate the effect of such LV alteration on ischemia detection criteria and performance.MethodsElectrophysiological effects of increased LV mass were evaluated on sixteen New Zealand rabbit isolated hearts under non-ischemic and ischemic conditions by analysis of various electrogram (EG) parameters. To reveal hearts with increased LV mass, LV weight/heart weight ratio was proposed. Standard paired and unpaired statistical tests and receiver operating characteristics analysis were used to compare data derived from different groups of animals, monitor EG parameters during global ischemia and evaluate their ability to discriminate between unchanged and increased LV as well as non-ischemic and ischemic state.ResultsSuccessful evaluation of both increased LV mass and ischemia is lead-dependent. Particularly, maximal deviation of QRS and area under QRS associated with anterolateral heart wall respond significantly to even early phase (the 1st-3rd min) of ischemia. Besides ischemia, these parameters reflect increased LV mass as well (with sensitivity reaching approx. 80%). However, the sensitivity of the parameters to both phenomena may lead to misinterpretations, when inappropriate criteria for ischemia detection are selected. Particularly, use of cut-off-based criteria defined from control group for ischemia detection in hearts with increased LV mass may result in dramatic reduction (approx. 15%) of detection specificity due to increased number of false positives. Nevertheless, criteria adjusted to particular experimental group allow achieving ischemia detection sensitivity of 89–100% and specificity of 94–100%, respectively.ConclusionsIt was shown that response of the heart to myocardial ischemia can be successfully evaluated only when taking into account heart-related factors (such as LV mass) and other methodological aspects (such as recording electrodes position, selected EG parameters, cut-off criteria, etc.). Results of this study might be helpful for developing new clinical diagnostic strategies in order to improve myocardial ischemia detection in patients with LV hypertrophy.

Voltage sensitive dye di-4-ANNEPS prolongs impulse conduction through ventricles, but not through AV node in isolated rabbit heart

Voltage sensitive dyes are widely used for recording of action potential in various cardiac studies. The elementary condition for its application is the fact that measured electrophysiological parameters would not be affected by the measuring procedure itself. The RR interval prolongation in the presence of the most frequently used voltage sensitive dye di-4-ANEPPS has been reported, but its exact mechanism is not known. In this study, the impact of di-4-ANEPPS on impulse conduction through the atrioventricular (AV) node and through cardiac ventricles in isolated rabbit heart was examined. The impulse conduction through AV node in the presence of di-4-ANEPPS was prolonged only during dye loading in the 14th, 16th and 17th minute. Only sporadic AV blocks were observed. In comparison, the prolongation of impulse conduction through cardiac ventricles was observed from the 13th minute of loading and persisted to the end of this phase as well as over the whole wash out phase.

The effect of voltage sensitive dye di-4-ANEPPS on the RT/RR coupling in rabbit isolated heart

Voltage sensitive dye (VSD) di-4-ANEPPS is ordinary used for optical measurement of action potential in experimental cardiology. In this work, the effect of the dye on the RT/RR coupling measured in electrograms (EG) recorded on rabbit isolated hearts was studied. The results were compared with the control experiments without VSD administration. The comparison was performed in preparation stage of the experiment that consisted of three phases: stabilization (S), VSD loading (L), and washout (W). The median and interquartile range (Q0.75-Q0.25) of the difference in RR, QT and RT/RR between the beginning and the end of the phases were computed and compared between the both groups. Δ(RT/RR), in S, L and W, was -0.095, 0.061; -0.093, 0.043; -0.027, 0.039 in di-4-ANEPPS-treated group and -0.127, 0.071; 0.006, 0.016; -0.001, 0.025 in control group. The significant difference (P<;0.01) was found between two groups in L phase. Additionally, there was the significant difference in ΔRR [ms] which was 120.9, 74.8 in di-4-ANEPPS-treated group and 6.94, 19.28 in control group in the same phase. The significant difference in Δ(RT/RR) between both groups shows a possible effect of di-4-ANEPPS on the RT/RR coupling which is mainly caused by the prolongation of RR interval during loading with the dye.

The effect of heart orientation on high frequency QRS components in multiple bandwidths

Reduced power of high frequency (HF) oscillations inside the QRS complex reflects ischemic pathology in the heart. In order to show spatial and frequency dependencies, we examined the effect of heart orientation on power of high frequency components under normal and ischemia condition within various frequency bands. Root mean square (RMS) of the signal in QRS region within frequency bands from 150 Hz to 550 Hz and heart rotation around longitudinal axes (360°) were computed from four rabbit isolated hearts. Experimental protocol included control, ischemic and reperfusion phases. This pilot study shows that RMS level of HF signal in non-ischemic heart differs within lead orientation and its maximum lies in a region around specific angle. Relative decrease in RMS value also depends on lead position. When depicted in spatial-frequency plane with polar coordinates, these relative changes contributes to specific patterns under both normal and ischemic conditions, which should be further examined.