BAEP dynamic estimation in case of endocochlear pathologies using a time delay correction method

Extraction of Brainstem Auditory Evoked Potentials (BAEPs) from the electroencephalogram (EEG) is generally difficult when both BAEP and EEG are non-stationary. In this paper we focus on the problem of BAEP non-stationarities, in particular those observed in some endocochlear pathologies assumed causing random delays of BAEPs due to an abnormal behaviour of the cochlea. The technique developed in this paper, called the Time Delay Correction (TDC) method, allows us to estimate the averaged BAEP by an optimal alignment of responses based on a correlation criterion. We demonstrate that the TDC method avoids wave smoothness, generally produced with the classical ensemble averaging method, especially in the case when the hypothesis of the time delay non-stationarity is verified. The TDC method is performed using simulated annealing (SA) algorithm, since the criterion to be optimized is nonlinear. Real signals recorded from pathological subjects are used to validate the model of non-stationarity.     

Fast simulated annealing algorithm for BAEP time delay estimation using a reduced order dynamic model

The extraction of Brainstem Auditory Evoked Potentials (BAEPs), from the EEG background, is of high clinical interest. The present paper can be considered as a continuation of our previous work related to the BAEP estimation in endocochlear pathologies. In our previous published work, we proposed a technique for time delay estimation on the basis of the BAEPs in response to successive stimulations. Put in a different manner, our objective was the estimation of the dynamics of the cochlea that is responsible for the delayed responses. The estimation technique was based on optimization of a non-linear criterion by means of Simulated Annealing Time Delay Estimation (SATDE) algorithm. However, it is well known that such heuristic algorithms are time consuming and largely depend on the number of parameters to be estimated. The present paper demonstrates that modeling the non-stationarity of responses considerably decreases the convergence time to the global minimum. The newly proposed method in this paper, called Fast Simulated Annealing Time Delay Estimation (FSATDE) algorithm, has been validated on both simulated and real signals.     

A novel approach for the averaging of magnetocardiographically recorded heart beats

Performing signal averaging in an efficient and correct way is indispensable since it is a prerequisite for a broad variety of magnetocardiographic (MCG) analysis methods. One of the most common procedures for performing the signal averaging to increase the signal-to-noise ratio (SNR) in magnetocardiography, as well as in electrocardiography (ECG), is done by means of spatial or temporal techniques. In this paper, an improvement of the temporal averaging method is presented. In order to obtain an accurate signal detection, temporal alignment methods and objective classification criteria are developed. The processing technique based on hierarchical clustering is introduced to take into account the non-stationarity of the noise and, to some extent, the biological variability of the signals reaching the optimum SNR. The method implemented is especially designed to run fast and does not require any interaction from the operator. The averaging procedure described in this work is applied to the averaging of MCG data as an example, but with its intrinsic properties it can also be applied to the averaging of ECG recording, averaging of body-surface-potential mapping (BSPM) and averaging of magnetoencephalographic (MEG) or electroencephalographic (EEG) signals.     

Measurement of human BAERs by the maximum length sequence technique

The traditional brainstem auditory evoked response (BAER) measurement technique (ensemble averaging) is time-consuming and is not acceptable for some time-critical clinical applications. In the paper the application of a pseudorandom binary sequence, the maximum length sequence, to human BAER measurements is examined. This technique permits a faster click rate to stimulate the test subject, and obtaines a higher signal-to-noise ratio (SNR) response through deconvolution. When compared with conventional averaging, the method can result in an improved SNR or in faster measurement of BAER. The theory of the technique and the experimental setup are presented, and theoretical analysis on the SNR improvement by this technique against averaging is also given. Actual measurements of BAER on both humans and cats indicate that this technique is effective, especially when the measurement time is not too long, or the number of trials is not too large.     

Wavelet-based enhancement of signalaveraged electrocardiograms for late potential detection

An optimal wavelet filter to improve the signal-to-noise ratio (SNR) of the signal-averaged electrocardiogram is described. As the averaging technique leads to the best unbiased estimator, the challenge is to attenuate the noise while preserving the low amplitude signals that are usually embedded in it. An optimal, in the meansquare sense, wavelet-based filter has been derived from the model of the signal. However, such a filter needs exact knowledge of the noise statistic and the noise-free signal. Hence, to implement such a filter, a method based on successive subaveraging and wavelet filtering is proposed. Its performance was evaluated using simulated and real ECGs. An improvement in SNR of between 6 and 10 dB can be achieved compared to a classical averaging technique which uses an ensemble of 64 simulated ECG beats. Tests on real ECGs demonstrate the utility of the method as it has been shown that by using fewer beats in the filtered ensemble average, one can achieve the same noise reduction. Clinical use of this technique would reduce the ensemble needed for averaging while obtaining the same diagnostic result.     

Wavelet-based enhancement of signal-averaged electrocardiograms for late potential detection

An optimal wavelet filter to improve the signal-to-noise ratio (SNR) of the signal-averaged electrocardiogram is described. As the averaging technique leads to the best unbiased estimator, the challenge is to attenuate the noise while preserving the low amplitude signals that are usually embedded in it. An optimal, in the mean-square sense, wavelet-based filter has been derived from the model of the signal. However, such a filter needs exact knowledge of the noise statistic and the noise-free signal. Hence, to implement such a filter, a method based on successive sub-averaging and wavelet filtering is proposed. Its performance was evaluated using simulated and real ECGs. An improvement in SNR of between 6 and 10 dB can be achieved compared to a classical averaging technique which uses an ensemble of 64 simulated ECG beats. Tests on real ECGs demonstrate the utility of the method as it has been shown that by using fewer beats in the filtered ensemble average, one can achieve the same noise reduction. Clinical use of this technique would reduce the ensemble needed for averaging while obtaining the same diagnostic result.     

Objective detection of brainstem auditory evoked potentials with a priori information from higher presentation levels

This paper describes a brainstem auditory evoked potentials (BAEPs) detection method based on supervised pattern recognition. A previously used pattern recognition technique relying on cross-correlation with a template was modified in order to include a priori information allowing detection accuracy. Reference is made to the patient's audiogram and to the latency-intensity (LI) curve with respect to physiological mechanisms. Flexible and adaptive constraints are introduced in the optimization procedure by means of eight rules. Several data samples were used in this study. The determination of parameters was performed through 270 BAEPs from 20 subjects with normal and high audiometric thresholds and through additional BAEPs from 123 normal ears and 14 ears showing prominent wave VI BAEPs. The evaluation of the detection performance was performed in two steps: first, the sensitivity, specificity and accuracy were estimated using 283 BAEPs from 20 subjects showing normal and high audiometric thresholds and secondly, the sensitivity, specificity and accuracy of the detection and the accuracy of the response threshold were estimated using 213 BAEPs from 18 patients in clinic.Taking into account some a priori information, the accuracy in BAEPs detection was enhanced from 76 to 90%. The patient response thresholds were determined with a mean error of 5 dB and a standard deviation error of 8.3 dB. Results were obtained using experimental data; therefore, they are promising for routine use in clinic.     

用奇异性检测技术提取诱发电位

本文介绍了用 小波变换模极大 值检测信号奇 异性的方法， 讨论了 信号与 白噪声 的小 波变换 和奇 异性指数之间区 别，模极大值沿 尺度 传递 的不同 特点 ，并 利用它 们的 区别 消除 诱发 电位 信号 中的噪 声，重 构出消 噪后 的信号， 取得 了较好 的效果 ，利用 较少的 刺激 次数就 可获取 诱发电 位信 号，有 效地提高 了信 噪比，大 大减 少了迭 加次数 ，特征 波的潜 伏期 及幅值 容易辨 认，易 于测量 ，且无 信号 失真。奇异性检 测技术有望成为 临床实用的诱 发电位提取 技术，并 可应用 于其他 生物 医学信 号的 消噪。     

An Evaluation of the Ensemble Averaged Impedance Cardiogram

The ensemble averaged impedance cardiogram was evaluated during rest and during vocal mental arithmetic stress in samples of female (n = 17) and male (n = 40) undergraduates. Measures of myocardial performance determined from ensemble averaged signals were compared to those determined by simple beat-to-beat averaging over 60-s and 20-s sampling intervals. In addition, the influence of cardiac interval variability on dZ/dt amplitude measures was assessed. As expected, measures derived by the two averaging techniques corresponded closely, with correlations ranging from r = 0.882 to r = 1.000 for the 60-s sampling intervals, and from r = 0.726 to r = 1.000 for the 20-s sampling intervals. Inverse relationships of comparable magnitude were found between cardiac interval variability and dZ/dt amplitude measures determined by both averaging techniques, suggesting that these relationships did not result simply from artifacts introduced by the ensemble averaging technique. The results support the validity of ensemble averaging as a method for deriving impedance cardiographic measures of myocardial performance.     

Quantifying rapid changes in cardiovascular state with a moving ensemble average

MEAP, the moving ensemble analysis pipeline, is a new open‐source tool designed to perform multisubject preprocessing and analysis of cardiovascular data, including electrocardiogram (ECG), impedance cardiogram (ICG), and continuous blood pressure (BP). In addition to traditional ensemble averaging, MEAP implements a moving ensemble averaging method that allows for the continuous estimation of indices related to cardiovascular state, including cardiac output, preejection period, heart rate variability, and total peripheral resistance, among others. Here, we define the moving ensemble technique mathematically, highlighting its differences from fixed‐window ensemble averaging. We describe MEAP's interface and features for signal processing, artifact correction, and cardiovascular‐based fMRI analysis. We demonstrate the accuracy of MEAP's novel B point detection algorithm on a large collection of hand‐labeled ICG waveforms. As a proof of concept, two subjects completed a series of four physical and cognitive tasks (cold pressor, Valsalva maneuver, video game, random dot kinetogram) on 3 separate days while ECG, ICG, and BP were recorded. Critically, the moving ensemble method reliably captures the rapid cyclical cardiovascular changes related to the baroreflex during the Valsalva maneuver and the classic cold pressor response. Cardiovascular measures were seen to vary considerably within repetitions of the same cognitive task for each individual, suggesting that a carefully designed paradigm could be used to capture fast‐acting event‐related changes in cardiovascular state.     

Extraction of short-latency evoked potentials using a combination of wavelets and evolutionary algorithms

Somatosensory evoked potentials, recorded at the spine or scalp of a patient, are contaminated by noise. It is common practice to use ensemble averaging to remove the noise, which usually requires a large number of responses to produce one averaged signal. In this paper a post-processing technique is shown which uses a combination of wavelets and evolutionary algorithms to produce a representative waveform with fewer responses. The most suitable wavelets and a set of weights are selected by an evolutionary algorithm to form a filter bank, which enhances the extraction of evoked potentials from noisy recordings.     

Modelling and recognition of brainstem auditory evoked potentials using Symlet wavelet

In Brainstem Auditory Evoked Potentials (BAEPs) extraction systems, BAEP recognition by determining wave latencies I, II, III and IV/V is an importantant stage for pronostic assistance. We suggest in this paper a new approach for BAEP recognition. The recognition is based on modelling BAEP using wavelet transform; latencies are then automatically measured. We show that the application of a sixth-order Symlet wavelet gives good results.     

An improved approach for measurement of stroke volume during treadmill exercise

In this study, a new ensemble averaging technique was developed to measure cardiac output during treadmill exercise. Each dz/dt peak is used as a starting point for ensemble averaging, instead of the conventionally used R point of ECG, in order to prevent the peak dz/dt waveform (C point) to be smoothed, which results in increased dz/dtmax. When using the R point as a reference, time interval from the R point to the peak dz/dt varies for each heart beat. Signal to noise ratios (SNR) of the five subjects with the new technique were 12.9, 16. 4, 10.6, 14.0, and 4.6% higher than those with the conventional one at rest and during four levels of exercise, respectively. Power density spectra of the averaged dz/dt waveforms by the peak dz/dt and R point referencing were also analyzed. Stroke volumes of the five subjects averaged by the peak dz/dt were 4.9, 6.8, 7.6, 7.4, and 9.8% higher than those by the R point at rest and during four levels of exercise, respectively.     

Hybrid time-frequency adaptive filtering for the recovery of ventricular late potentials

Ventricular late potentials are small ECG components that have significant diagnostic importance. Temporal averaging is used to recover these signals from high levels of background noise, but is not the optimum approach. A new form of hybrid time-frequency adaptive filtering is introduced that is based on signal division into a series of frequency bands. This technique is able to process the averaged data further and to reduce significantly the noise levels beyond that achieved by simple averaging. Examples of the processing are shown and its applicability is discussed.     

Explaining the output of ensembles in medical decision support on a case by case basis

The use of ensembles in machine learning (ML) has had a considerable impact in increasing the accuracy and stability of predictors. This increase in accuracy has come at the cost of comprehensibility as, by definition, an ensemble model is considerably more complex than its component models. This is of significance for decision support systems in medicine because of the reluctance to use models that are essentially black boxes. Work on making ensembles comprehensible has so far focused on global models that mirror the behaviour of the ensemble as closely as possible. With such global models there is a clear tradeoff between comprehensibility and fidelity. In this paper, we pursue another tack, looking at local comprehensibility where the output of the ensemble is explained on a case-by-case basis. We argue that this meets the requirements of medical decision support systems. The approach presented here identifies the ensemble members that best fit the case in question and presents the behaviour of these in explanation.     

Mitigating the effect of non-stationarity in spectral analysis—An application to neonate heart rate analysis

In order to mitigate the effect of non-stationarity in frequency domain analysis of data, we propose a modification to the power spectral estimation, a widely used technique to characterize physiological signals. Spectral analysis requires partitioning data into smaller epochs determined by the desired frequency resolution. The modified approach proposed here involves dividing the data within each epoch by the standard deviation of the data for that epoch. We applied this modified approach to cardiac beat-to-beat interval data recorded from a newborn infant undergoing hypothermia treatment for birth asphyxia. The critically ill infant had episodes of tachyarrhythmia, distributed sporadically throughout the study, which affected the stationarity of the heart rate. Over the period of continuous heart rate recording, the infant's clinical course deteriorated progressively culminating in death. Coinciding with this clinical deterioration, the heart rate signal showed striking changes in both low-frequency and high-frequency power indicating significant impairment of the autonomic nervous system. The standard spectral approach failed to capture these phenomena because of the non-stationarity of the signal. Conversely, the modified approach proposed here captured the deteriorating physiology of the infant clearly.     

Classification of auditory brainstem responses through symbolic pattern discovery

IntroductionNumeric time series are present in a very wide range of domains, including many branches of medicine. Data mining techniques have proved to be useful for knowledge discovery in this type of data and for supporting decision-making processes.ObjectivesThe overall objective is to classify time series based on the discovery of frequent patterns. These patterns will be discovered in symbolic sequences obtained from the time series data by means of a temporal abstraction process.MethodsFirstly, we transform numeric time series into symbolic time sequences, where the symbols aim to represent the relevant domain concepts. These symbols can be defined using either public or expert domain knowledge. Then we apply a symbolic pattern discovery technique to the output symbolic sequences. This technique identifies the subsequences frequently found in a population group. These subsequences (patterns) are representative of population groups. Finally, we employ a classification technique based on the identified patterns in order to classify new individuals. Thanks to the inclusion of domain knowledge, the classification results can be explained using domain terminology. This makes the results easier to interpret for the domain specialist (physician).ResultsThis method has been applied to brainstem auditory evoked potentials (BAEPs) time series. Preliminary experiments were carried out to analyse several aspects of the method including the best configuration of the pattern discovery technique parameters. We then applied the method to the BAEPs of 83 individuals belonging to four classes (healthy, conductive hearing loss, vestibular schwannoma—brainstem involvement and vestibular schwannoma—8th-nerve involvement). According to the results of the cross-validation, overall accuracy was 99.4%, sensitivity (recall) was 97.6% and specificity was 100% (no false positives).ConclusionThe proposed method effectively reduces dimensionality. Additionally, if the symbolic transformation includes the right domain knowledge, the method arguably outputs a data representation that denotes the relevant domain concepts more clearly. The method is capable of finding patterns in BAEPs time series and is very accurate at correctly predicting whether or not new patients have an auditory-related disorder.     

Noninvasive beat-to-beat detection of ventricular late potentials

The detection of ventricular late potentials is a subject of some clinical interest. Most techniques currently being investigated rely on signal averaging to extract the microvolt signals from the considerable amounts of noise which are present. Although this approach produces useful results, it does remove any beat-to-beat variations from the signal, and also requires that the signal be present for a considerable number of beats. The paper describes a technique for detecting ventricular late potentials from the body surface, which preserves beat-to-beat variations. The most important aspect of this technique is the use of an adaptive signal enhancer to minimise random noise. Representative results for one normal and two pathological subjects are presented and discussed. A comparison with signal averaging is made and the effectiveness of adaptive signal enhancement is illustrated.     

A novel method for predicting kidney stone type using ensemble learning

The high morbidity rate associated with kidney stone disease, which is a silent killer, is one of the main concerns in healthcare systems all over the world. Advanced data mining techniques such as classification can help in the early prediction of this disease and reduce its incidence and associated costs. The objective of the present study is to derive a model for the early detection of the type of kidney stone and the most influential parameters with the aim of providing a decision-support system. Information was collected from 936 patients with nephrolithiasis at the kidney center of the Razi Hospital in Rasht from 2012 through 2016. The prepared dataset included 42 features. Data pre-processing was the first step toward extracting the relevant features. The collected data was analyzed with Weka software, and various data mining models were used to prepare a predictive model. Various data mining algorithms such as the Bayesian model, different types of Decision Trees, Artificial Neural Networks, and Rule-based classifiers were used in these models. We also proposed four models based on ensemble learning to improve the accuracy of each learning algorithm. In addition, a novel technique for combining individual classifiers in ensemble learning was proposed. In this technique, for each individual classifier, a weight is assigned based on our proposed genetic algorithm based method. The generated knowledge was evaluated using a 10-fold cross-validation technique based on standard measures. However, the assessment of each feature for building a predictive model was another significant challenge. The predictive strength of each feature for creating a reproducible outcome was also investigated. Regarding the applied models, parameters such as sex, acid uric condition, calcium level, hypertension, diabetes, nausea and vomiting, flank pain, and urinary tract infection (UTI) were the most vital parameters for predicting the chance of nephrolithiasis. The final ensemble-based model (with an accuracy of 97.1%) was a robust one and could be safely applied to future studies to predict the chances of developing nephrolithiasis. This model provides a novel way to study stone disease by deciphering the complex interaction among different biological variables, thus helping in an early identification and reduction in diagnosis time.     

A new combination: scale-space filtering of projected brain activities

In the present study, well known scale-space filtering (SSF) algorithm is used in combination with a linear mapping approach (LMA) to obtain clear auditory evoked potential (EP) waveform. The proposed combination involves two sequential steps: At first, the EEG noise level is reduced from −5 to 0 dB owing to the LMA based on the singular-value-decomposition. In the secondary process, the EEG noise remaining on the projected data is removed by using the SSF. A small number of sweeps are composed as a raw matrix to project the data without using the ensemble averaging at the beginning of the proposed method. Then, single sweeps are individually filtered in wavelet domain by using the SSF in the secondary step. The experimental results show that the SSF can extract the clear single-sweep auditory EP waveform where the LMA is used as a primary filtering. As well, the results indicate that the EP signal and background EEG noise create different wavelet coefficients due to their different characteristics. However, this characteristic difference can be considered to distinguish the EP signal and the EEG noise when the Signal-to-Noise-Ratio is higher than 0 dB.