José Luis Rodríguez-Sotelo

Automatic Sleep Stages Classification Using EEG Entropy Features and Unsupervised Pattern Analysis Techniques

Sleep is a growing area of research interest in medicine and neuroscience. Actually, one major concern is to find a correlation between several physiologic variables and sleep stages. There is a scientific agreement on the characteristics of the five stages of human sleep, based on EEG analysis. Nevertheless, manual stage classification is still the most widely used approach. This work proposes a new automatic sleep classification method based on unsupervised feature classification algorithms recently developed, and on EEG entropy measures. This scheme extracts entropy metrics from EEG records to obtain a feature vector. Then, these features are optimized in terms of relevance using the Q-α algorithm. Finally, the resulting set of features is entered into a clustering procedure to obtain a final segmentation of the sleep stages. The proposed method reached up to an average of 80% correctly classified stages for each patient separately while keeping the computational cost low.

Unsupervised feature relevance analysis applied to improve ECG heartbeat clustering

The computer-assisted analysis of biomedical records has become an essential tool in clinical settings. However, current devices provide a growing amount of data that often exceeds the processing capacity of normal computers. As this amount of information rises, new demands for more efficient data extracting methods appear. This paper addresses the task of data mining in physiological records using a feature selection scheme. An unsupervised method based on relevance analysis is described. This scheme uses a least-squares optimization of the input feature matrix in a single iteration. The output of the algorithm is a feature weighting vector. The performance of the method was assessed using a heartbeat clustering test on real ECG records. The quantitative cluster validity measures yielded a correctly classified heartbeat rate of 98.69% (specificity), 85.88% (sensitivity) and 95.04% (general clustering performance), which is even higher than the performance achieved by other similar ECG clustering studies. The number of features was reduced on average from 100 to 18, and the temporal cost was a 43% lower than in previous ECG clustering schemes.

Unsupervised classification of atrial heartbeats using a prematurity index and wave morphology features

ECG heartbeat type detection and classification are regarded as important procedures since they can significantly help to provide an accurate automated diagnosis. This paper addresses the specific problem of detecting atrial premature beats, that had been demonstrated to be a marker for stroke risk or cardiac arrhythmias. The proposed methodology consists of a stage to estimate characteristics such as morphology of P wave and QRS complex as well as indices of prematurity and a non-supervised stage used by the algorithm J-means to separate heartbeat feature vectors into classes. Partition initialization is carried out by a Max–Min approach. Experimental data set is taken from MIT-BIH arrhythmia database. Results evidence the reliability of the method since achieved sensitivity and specificity are high, 92.9 and 99.6%, respectively, for an average output number of 12 discovered clusters that can be considered as appropriate value to separate heartbeat classes from recordings.

Weighted-PCA for unsupervised classification of cardiac arrhythmias

A method that improves the feature selection stage for non-supervised analysis of Holter ECG signals is presented. The method corresponds to WPCA approach developed mainly in two stages. First, the weighting of the feature set through a weight vector based on M-inner product as distance measure and a quadratic optimization function. The second one is the linear projection of weighted data using principal components. In the clustering stage, some procedures are considered: estimation of the number of groups, initialization of centroids and grouping by means a soft clustering algorithm. In order to decrease the procedure computational cost, segment analysis, grouping contiguous segments and establishing union and exclusion criteria per each cluster, is carried out. This work is focused to classify cardiac arrhythmias into 5 groups, according to the standard of the AAMI (ANSI/AAMI EC57:1998/ 2003). To validate the method, some recordings from MIT/BIH arrhythmia database are used. By employing the labels of each recording, the performance is assessed with supervised measures (Se = 90.1%, Sp = 98.9% y Cp = 97.4%), enhancing other works in the literature that do not take into account all heartbeat types.

Generalized Bonhoeffer-van der Pol oscillator for modelling cardiac pulse: Preliminary results

This work presents an approach for modelling cardiac pulse from electrocardiographic signals (ECG). We explore the use of the Bonhoeffer-van der Pol (BVP) model-being a generalized version of the van der Pol oscillator - which, under proper parameters, is able to describe action potentials, and it can be then adapted to modelling normal cardiac pulse. Using basics of non-linear dynamics and some algebra, the BVP system response is estimated. To account for an adaptive response for every single heartbeat, we propose a parameter tuning method based on a heuristic search in order to yield responses that morphologically resemble real ECG. This aspect is important since heartbeats have intrinsically strong variability in terms of both shape and length. Experiments are carried out over real ECG from MIT-BIH arrhythmias database. We perform a bifurcation and phase portrait analysis to explore the relationship between non-linear dynamics features and pathology. Preliminary results provided here are promising showing some hints about the ability of non-linear systems modelling ECG to characterize heartbeats and facilitate the classification thereof, being latter very important for diagnosing purposes.

Developments on Solutions of the Normalized-Cut-Clustering Problem Without Eigenvectors

Normalized-cut clustering (NCC) is a benchmark graph-based approach for unsupervised data analysis. Since its traditional formulation is a quadratic form subject to orthogonality conditions, it is often solved within an eigenvector-based framework. Nonetheless, in some cases the calculation of eigenvectors is prohibitive or unfeasible due to the involved computational cost – for instance, when dealing with high dimensional data. In this work, we present an overview of recent developments on approaches to solve the NCC problem with no requiring the calculation of eigenvectors. Particularly, heuristic-search and quadratic-formulation-based approaches are studied. Such approaches are elegantly deduced and explained, as well as simple ways to implement them are provided.

Effectiveness of morphological and spectral heartbeat characterization on arrhythmia clustering for Holter recordings

Heartbeat characterization is an important issue in cardiac assistance diagnosis systems. In particular, wide sets of features are commonly used in long term electrocardiographic signals. Then, if such a feature space does not represent properly the arrhythmias to be grouped, classification or clustering process may fail. In this work a suitable feature set for different heartbeat types is studied, involving morphology, representation and time-frequency features. To determine what kind of features generate better clusters, feature selection procedure is used and assessed by means clustering validity measures. Then the feature subset is shown to produce fine clustering that yields into high sensitivity and specificity values for a broad range of heartbeat types.

The shape of dementia: new measures of morphological complexity in event-related potentials (ERP) and its application to the detection of Alzheimer’s disease

Abstract In this paper, we address the problem of quantifying the commonly observed disorganization of the stereotyped wave form of the ERP associated with the P300 component in patients with Alzheimer’s disease. To that extent, we propose two new measures of complexity which relate the spectral content of the signal with its temporal waveform: the spectral matching coefficient and the spectral matching entropy. We show by means of experiments that those measures effectively measure complexity and are related to the shape in an intuitive way. Those indexes are compared with commonly used measures of complexity when comparing AD patients against age-matched healthy controls. The results indicate that AD ERP signals are, indeed, more complex in the shape than that of controls, and this result is evidenced mainly by means of our new measures which have a better performance compared to similar ones. Finally, we try to explain this increase in complexity in light of the communication through coherence hypothesis framework, relating commonly found changes in the EEG with our own results.

Unsupervised feature selection in cardiac arrhythmias analysis

The problem of detecting clinical events related to cardiac arrhythmias in long term electrocardiograms is a difficult one due to the large amount of irrelevant information that hides such events. This problem has been addressed in the literature by means of clustering or classification algorithms that create data partitions according to a cost function based on heartbeat features dissimilarity measures. However, studies about the type or number of heartbeat features is lacking. Usually, the feature sets used are relevant but redundant, which degrades algorithm performance. This paper describes a method for automatic selection of heartbeat features. This method is assessed using real signals from the MIT database and common features used in previous works.

An improved method for unsupervised analysis of ECG beats based on WT features and J-means clustering

Clustering is advisable technique for analysis and interpretation of long-term ECG Holter records. As a non-supervised method, several challenges are posed due to factors such as signal length (very long duration), noise presence, dynamic behavior and morphology variability (different patient physiology and/or pathology). This work describes an improved version of the k-means clustering algorithm (J-means) for this task. In order to reduce the number of heartbeats to process, a preclustering stage is also employed. Dissimilarity measure calculation is based on the Dynamic Time Warping approach. To assess the validity of the proposed method, a comparative study is carried out, using k-means, k-medians, hk-means, and J-means. Heartbeat features are extracted by means of WT coefficients and trace segmentation. Best results were achieved by the J-means algorithm, which reduces the clustering error down to 4.5% while the critical error tends to the minimal value.