Rodrigo Varejão Andreão

ECG signal analysis through hidden Markov models

This paper presents an original hidden Markov model (HMM) approach for online beat segmentation and classification of electrocardiograms. The HMM framework has been visited because of its ability of beat detection, segmentation and classification, highly suitable to the electrocardiogram (ECG) problem. Our approach addresses a large panel of topics some of them never studied before in other HMM related works: waveforms modeling, multichannel beat segmentation and classification, and unsupervised adaptation to the patients ECG. The performance was evaluated on the two-channel QT database in terms of waveform segmentation precision, beat detection and classification. Our waveform segmentation results compare favorably to other systems in the literature. We also obtained high beat detection performance with sensitivity of 99.79% and a positive predictivity of 99.96%, using a test set of 59 recordings. Moreover, premature ventricular contraction beats were detected using an original classification strategy. The results obtained validate our approach for real world application

Combining wavelet transform and hidden Markov models for ECG segmentation

This work aims at providing new insights on the electrocardiogram (ECG) segmentation problem using wavelets. The wavelet transform has been originally combined with a hidden Markov models (HMMs) framework in order to carry out beat segmentation and classification. A group of five continuous wavelet functions commonly used in ECG analysis has been implemented and compared using the same framework. All experiments were realized on the QT database, which is composed of a representative number of ambulatory recordings of several individuals and is supplied with manual labels made by a physician. Our main contribution relies on the consistent set of experiments performed. Moreover, the results obtained in terms of beat segmentation and premature ventricular beat (PVC) detection are comparable to others works reported in the literature, independently of the type of the wavelet. Finally, through an original concept of combining two wavelet functions in the segmentation stage, we achieve our best performances.

Spectral analysis of heart rate variability with the autoregressive method

This work assessed the influence of the autoregressive model order (ARMO) on the spectral analysis of the heart rate variability (HRV). A sample of 68 R-R series obtained from digital ECG records of young healthy adults in the supine position was used. Normalized spectral indexes for each ARMO were compared by Friedman test followed by the Dunns procedure and statistical significance was set at P<0.05. The results showed that the AR method using orders from 9 to 25 produces normalized spectral parameters statistically similar and, hence, the algorithms commonly employed to estimate optimum order are not mandatory in this case.

Tele-surveillance System for Patient at Home: The MEDIVILLE System

This work is concerned with the design and realization of a complete telecare application for remote monitoring of patients at home, including a wireless monitoring portable device held by the patient and a remote central server application located in a surveillance center. Agitation, position and cardiac rate data are used for alarm decision and can be exploited by the central server application. Originality resides in the actimetry and heart rate data combination for alarm decision and in the central server design aiming at offering flexible assistance services for both the surveillance medical team and the practitioner in charge of the patient.

Premature Ventricular beat classification using a dynamic Bayesian Network

This paper investigates the viability of using the dynamic Bayesian Network framework as a tool to classify heart beats in long term ECG records. A Decision Support System composed by two layers is considered. The first layer performs the segmentation of each heartbeat available in the ECG record, whereas the second layer classifies the heartbeat as Premature Ventricular Contraction (PVC) or Other. The use of both static and dynamic Bayesian Networks is evaluated through using the records available in the MIT-BIH database, and the results show that the Dynamic one performs better, obtaining 95% of sensitivity and 98% of positive predictivity, showing that to consider the temporal relation among events is a good strategy to increase the certainty about present events.

Efficient ECG multi-level wavelet classification through neural network dimensionality reduction

In this article, we explore the use of a unique type of wavelets for ECG beat detection and classification. Once the different beats are segmented, classification is performed using at the input of a neural network different wavelet scales. This improves the noise resistance and allows a better representation of the different morphologies. The results, evaluated on the MIT/BIH database, are excellent (97.69% on the normal and PVC classes) thanks to the use of a regularization technique.

ECG data provisioning for telehomecare monitoring

The latest computer and communication technologies in combination with an enhanced ECG analysis system can be used to improve cardiac patients follow-up out-of-hospital. In this way, real-time transmission of the so-called ambulatory electrocardiogram (AECG) to a remote health application with awareness of the patients context can support decision making as well as to allow efficient emergency attendance. However, the effectiveness of such a service requires tackling challenges of hardware and software beyond the common issues normally addressed in the literature. This paper proposes an ECG provisioning system that handles advanced issues such as flexibility and interoperability in pervasive scenarios as much as the well-known need for efficient transmission. This system architecture embraces an ECG analysis system based on hidden markov models and makes use of an original ECG markup language.

A MULTIMODAL PLATFORM FOR DATABASE RECORDING AND ELDERLY PEOPLE MONITORING

This paper describes a new platform for monitoring elderly people living alone. An architecture is proposed that includes three subsystems, with various types of sensors for different sensing modalities incorporated into a smart house. The originality of this system is the combination and the synchronization of three different televigilance modalities for acquiring and recording data. The paper focuses on the acquisition step of the system, usage and point out possibilities for future work

Incremental HMM training applied to ECG signal analysis

This work discusses the implementation of incremental hidden Markov model (HMM) training methods for electrocardiogram (ECG) analysis. The HMMs are used to model the ECG signal as a sequence of connected elementary waveforms. Moreover, an adaptation process is implemented to adapt the HMMs to the ECG signal of a particular individual. The adaptation training strategy is based on incremental versions of the expectation-maximization, segmental k-means and Bayesian approaches. Performance of the training methods was assessed through experiments considering the QT and ST-T databases. The results obtained show that the incremental training improves beat segmentation and ischemia detection performance with the advantage of low computational effort.

The Use of Bayesian Networks for Heart Beat Classification

This work proposes to use a static Bayesian network as a tool to support medical decision in the on-line detection of Premature Ventricular Contraction beats (PVC) in electrocardiogram (ECG) records, which is a well known cardiac arrhythmia available for study in standard ECG databases. The main motivation to use Bayesian networks is their capability to deal with the uncertainty embedded in the problem (the medical reasoning itself frequently embeds some uncertainty). Indeed, the probabilistic inference is quite suitable to model this kind of problem, for considering its random character; as a consequence, random variables are used to propagate the uncertainty embedded in the problem. Some topologies of static Bayesian networks are implemented and tested in this work, in order to find out the one more suitable to the problem addressed. The results of such tests are discussed in details along the text, and the conclusions are highlighted.