Detection of life-threatening cardiac arrhythmias using the wavelet transformation

Time-frequency wavelet theory is used for the detection of life threatening electrocardiography (ECG) arrhythmias. This is achieved through the use of the raised cosine wavelet transform (RCWT). The RCWT is found to be useful in differentiating between ventricular fibrillation, ventricular tachycardia and atrial fibrillation. Ventricular fibrillation is characterised by continuous bands in the range of 2–10 Hz; ventricular tachycardia is characterised by two distinct bands: the first band in the range of 2–5 Hz and the second in the range of 6–8 Hz; and atrial fibrillation is determined by a low frequency band in the range of 0–5 Hz. A classification algorithm is developed to classify ECG records on the basis of the computation of three parameters defined in the time-frequency plane of the wavelet transform. Furthermore, the advantage of localising and separating ECG signals from high as well as intermediate frequencies is demonstrated. The above capabilities of the wavelet technique are supported by results obtained from ECG signals obtained from normal and abnormal subjects.     

Complex-valued wavelet artificial neural network for Doppler signals classifying

OBJECTIVE: In this paper, the new complex-valued wavelet artificial neural network (CVWANN) was proposed for classifying Doppler signals recorded from patients and healthy volunteers. CVWANN was implemented on four different structures (CVWANN-1, -2, -3 and -4). MATERIALS AND METHODS: In this study, carotid arterial Doppler ultrasound signals were acquired from left carotid arteries of 38 patients and 40 healthy volunteers. The patient group had an established diagnosis of the early phase of atherosclerosis through coronary or aortofemoropopliteal angiographies. In implemented structures in this paper, Haar wavelet and Mexican hat wavelet functions were used as real and imaginary parts of activation function on different sequence in hidden layer nodes. CVWANN-1, -2 -3 and -4 were implemented by using Haar-Haar, Mexican hat-Mexican hat, Haar-Mexican hat, Mexican hat-Haar as real-imaginary parts of activation function in hidden layer nodes, respectively. RESULTS AND CONCLUSION: In contrast to CVWANN-2, which reached classification rates of 24.5%, CVWANN-1, -3 and -4 classified 40 healthy and 38 unhealthy subjects for both training and test phases with 100% correct classification rate using leave-one-out cross-validation. These networks have 100% sensitivity, 100% specifity and average detection rate is calculated as 100%. In addition, positive predictive value and negative predictive value were obtained as 100% for these networks. These results shown that CVWANN-1, -3 and -4 succeeded to classify Doppler signals. Moreover, training time and processing complexity were decreased considerable amount by using CVWANN-3. As conclusion, using of Mexican hat wavelet function in real and imaginary parts of hidden layer activation function (CVWANN-2) is not suitable for classifying healthy and unhealthy subjects with high accuracy rate. The cause of unsuitability (obtaining the poor results in CVWANN-2) is lack of harmony between type of activation function in hidden layer and type of input signals in neural network.     

Recurrent neural networks for classifying relations in clinical notes

We proposed the first models based on recurrent neural networks (more specifically Long Short-Term Memory - LSTM) for classifying relations from clinical notes. We tested our models on the i2b2/VA relation classification challenge dataset. We showed that our segment LSTM model, with only word embedding feature and no manual feature engineering, achieved a micro-averaged f-measure of 0.661 for classifying medical problem-treatment relations, 0.800 for medical problem-test relations, and 0.683 for medical problem-medical problem relations. These results are comparable to those of the state-of-the-art systems on the i2b2/VA relation classification challenge. We compared the segment LSTM model with the sentence LSTM model, and demonstrated the benefits of exploring the difference between concept text and context text, and between different contextual parts in the sentence. We also evaluated the impact of word embedding on the performance of LSTM models and showed that medical domain word embedding help improve the relation classification. These results support the use of LSTM models for classifying relations between medical concepts, as they show comparable performance to previously published systems while requiring no manual feature engineering.     

Prevention of recurrent life-threatening ventricular arrhythmias by temporary cardiac pacing

Overdrive pacing has been applied in 26 patients to prevent frequent recurrent ventricular fibrillation (VF) and ventricular tachycardia (VT) occurring in the setting of ventricular extrasystole of 2-5 degrees graded by Lown. These patients had 3-47 recurrent attacks of VF and VT (11.4 +/- 2.4) which were not prevented with antiarrhythmic agents. Overdrive pacing was continued for 2-236 hours (21.3 +/- 3.7) and appeared to be effective in 23 (88.4%) of the 26 patients including those with prolonged QT intervals. Atrial pacing was more effective than ventricular overdriving and required stimulation at a slower rate. Antiarrhythmic therapy and overdrive pacing in combination were more effective than both used independently. Suppression of ventricular extrasystole and prevention of life-threatening arrhythmias were achieved by increasing the heart rate by 23.2 +/- 4.5 beats/min.     

Analysis of cardiac health using fractal dimension and wavelet transformation

Analysis of heart rate variation (HRV) has become a popular non-invasive tool for assessing the activities of the autonomic nervous system (ANS). HRV analysis is based on the concept that fast fluctuations may specifically reflect changes of sympathetic and vagal activity. It shows that the structure generating the signal is not simply linear, but also involves nonlinear contributions. These signals are essentially non-stationary; may contain indicators of current disease, or even warnings about impending diseases. The indicators may be present at all times or may occur at random in the time scale. However, to study and pinpoint abnormalities in voluminous data collected over several hours is strenuous and time consuming. This paper presents the continuous time wavelet analysis of heart rate variability signal for disease identification. Fractal dimension (FD) of heart rate signals are calculated and compared with the wavelet analysis patterns. The FD obtained indicates more than 90% confidence interval for all the classes studied.     

Frontal latching networks: a possible neural basis for infinite recursion

Understanding the neural basis of higher cognitive functions, such as those involved in language, requires a shift from mere localisation to an analysis of network operation. A recent proposal points at infinite recursion as the core of several higher functions, and thus challenges cortical network theorists to describe network behaviour that could subserve infinite recursion. I propose here that a capacity for infinite recursion may be associated with the natural adaptive dynamics of large semantic associative networks, once their connectivity becomes sufficiently extensive to support structured transition probabilities between global network states. The crucial development endowing a semantic system with a nonrandom dynamics would thus be an increase in connectivity, perhaps to be identified with the dramatic increase in spine numbers recently observed in the basal dendrites of pyramidal cells in Old World monkey and particularly in human frontal cortex.     

Therapies for ventricular cardiac arrhythmias

During recent years, engineers and physicists have become increasingly interested in studying the electrical activity of the heart. Despite the fact that the heart is a complex and highly nonlinear system, its electrical behavior can be studied using a variety of experimental and clinical techniques, and can be modeled mathematically using relatively simple systems of differential equations, allowing scientists to perform both real and virtual (in silico) experiments to gain insights into its physiology and pathophysiology. Although these approaches have in recent years allowed great headway to be made into understanding the dynamic behavior of the heart, cardiac arrhythmias such as ventricular fibrillation still claim the lives of hundreds of thousands of people each year in the United States alone. Bridging the gap between understanding the mechanistic bases of arrhythmias and applying such knowledge to improving therapy presents one of the greatest challenges in the field of cardiac electrophysiology. In this review, we describe the basic electrical properties and dynamic behavior of the heart and review the current state of the art in ventricular arrhythmia therapy. We also discuss some possibilities for future therapies, with the hope that such informed speculation will promote new investigations in these areas.     

Radial basis function neural networks for the characterization of heart rate variability dynamics

This study introduces new neural network based methods for the assessment of the dynamics of the heart rate variability (HRV) signal. The heart rate regulation is assessed as a dynamical system operating in chaotic regimes. Radial-basis function (RBF) networks are applied as a tool for learning and predicting the HRV dynamics. HRV signals are analyzed from normal subjects before and after pharmacological autonomic nervous system (ANS) blockade and from diabetic patients with dysfunctional ANS. The heart rate of normal subjects presents notable predictability. The prediction error is minimized, in fewer degrees of freedom, in the case of diabetic patients. However, for the case of pharmacological ANS blockade, although correlation dimension approaches indicate significant reduction in complexity, the RBF networks fail to reconstruct adequately the underlying dynamics. The transient attributes of the HRV dynamics under the pharmacological disturbance is elucidated as the explanation for the prediction inability.     

A simulation unit for cardiac arrhythmias

This paper describes an electronic model of the conduction system of the heart, in the form of a simulation unit for cardiac arrhythmias. The basic assumptions made are the existence of two distinct cardiac pacemaking centres, and the possibility of reciprocal interaction between them. Details concerning the construction of the simulation unit are given, and its operation is illustrated by means of a few simple examples of cardiac arrhythmias. The advantages presented by this device for teaching and demonstration of various cardiac arrhythmic patterns are also emphasized.     

An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks

In this paper, an intelligent system is presented for interpretation of the Doppler signals of the heart valve diseases based on the pattern recognition. This paper especially deals with combination of the feature extraction and classification from measured Doppler signal waveforms at the heart valve using the Doppler Ultrasound. Because of this, a wavelet packet neural network model developed by us is used. The model consists of two layers: wavelet and multi-layer perceptron. The wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of wavelet packet decomposition and wavelet packet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the developed system has been evaluated in 215 samples. The test results showed that this system was effective in detecting Doppler heart sounds. The correct classification rate was about 94% for abnormal and normal subjects.     

Combined macro-/mesoporous microelectrode arrays for low-noise extracellular recording of neural networks

Microelectrode arrays (MEAs) are appealing tools to probe large neural ensembles and build neural prostheses. Microelectronics microfabrication technologies now allow building high-density MEAs containing several hundreds of microelectrodes. However, several major problems become limiting factors when the size of the microelectrodes decreases. In particular, regarding recording of neural activity, the intrinsic noise level of a microelectrode dramatically increases when the size becomes small (typically below 20-μm diameter). Here, we propose to overcome this limitation using a template-based, single-scale meso- or two-scale macro-/mesoporous modification of the microelectrodes, combining the advantages of an overall small geometric surface and an active surface increased by several orders of magnitude. For this purpose, standard platinum MEAs were covered with a highly porous platinum overlayer obtained by lyotropic liquid crystal templating possibly in combination with a microsphere templating approach. These porous coatings were mechanically more robust than Pt-black coating and avoid potential toxicity issues. They had a highly increased active surface, resulting in a noise level ～3 times smaller than that of conventional flat electrodes. This approach can thus be used to build highly dense arrays of small-size microelectrodes for sensitive neural signal detection.     

径向基函数网络在体感诱发电位实时监测中的应用

目的 针对体感诱发电位(SEP)的特征,设计基于径向基函数网络的复合自适应滤波器,实现体感诱发电位的快速提取.方法通过径向基函数网络的关键参数优化选择,对基于径向基函数网络的复合自适应滤波器与以自适应信号增强器和自适应噪声消除器为基础构造的复合自适应滤波器提取体感诱发电位的性能进行比较分析.结果仿真实验表明:基于径向基...     

Combined optical tweezers and laser dissector for controlled ablation of functional connections in neural networks

Regeneration of functional connectivity within a neural network after different degrees of lesion is of utmost clinical importance. To test pharmacological approaches aimed at recovering from a total or partial damage of neuronal connections within a circuit, it is necessary to develop a precise method for controlled ablation of neuronal processes. We combined a UV laser microdissector to ablate neural processes in vitro at single neuron and neural network level with infrared holographic optical tweezers to carry out force spectroscopy measurements. Simultaneous force spectroscopy, down to the sub-pico-Newton range, was performed during laser dissection to quantify the tension release in a partially ablated neurite. Therefore, we could control and measure the damage inflicted to an individual neuronal process. To characterize the effect of the inflicted injury on network level, changes in activity of neural subpopulations were monitored with subcellular resolution and overall network activity with high temporal resolution by concurrent calcium imaging and microelectrode array recording. Neuronal connections have been sequentially ablated and the correlated changes in network activity traced and mapped. With this unique combination of electrophysiological and optical tools, neural activity can be studied and quantified in response to controlled injury at the subcellular, cellular, and network level.     

Combined coding and wavelet transform for ECG compression

This paper presents a combined wavelet and a modified runlength encoding scheme for the compression of electrocardiogram (ECG) signals. First, a discrete wavelet transform is applied to the ECG signal. The resulting coefficients are classified into significant and insignificant ones based on the required PRD (percent root mean square difference). Second, both coefficients are encoded using a modified run-length coding method. The scheme has been tested using ECG signals obtained from the MIT-BIH Compression Database. A compression of 20:1 (which is equivalent to 150 bit per second) is achieved with PRD less than 10.     

A device for the simulation of cardiac arrhythmias

The early and accurate detection of cardiac arrhythmias has been recognized as instrumental in the prevention of sudden death from cardiac disease. In light of this, an arrhythmia detection system utilizing separate atrial and ventricular signals is being developed. As part of this development, an arrhythmia simulator was designed and built to provide controlled pulse outputs representative of most clinically significant arrhythmias. The device consists of two identical pulse generators that can be operated either independently or slaved through a programmable slave circuit. Heart rates from 20 to 600 beats per minute as well as various time relationships between the atrial and ventricular signals are achievable.