Classification Methods for Computerized Interpretation of the Electrocardiogram

Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discovery

Supplemental Digital Content is available in the text.

The ECG remains the most widely used diagnostic test for characterization of cardiac structure and electrical activity. We hypothesized that parallel advances in computing power, machine learning algorithms, and availability of large-scale data could substantially expand the clinical inferences derived from the ECG while at the same time preserving interpretability for medical decision-making.

A model-based Bayesian framework for ECG beat segmentation

The study of electrocardiogram (ECG) waveform amplitudes, timings and patterns has been the subject of intense research, for it provides a deep insight into the diagnostic features of the heart's functionality. In some recent works, a Bayesian filtering paradigm has been proposed for denoising and compression of ECG signals. In this paper, it is shown that this framework may be effectively used for ECG beat segmentation and extraction of fiducial points. Analytic expressions for the determination of points and intervals are derived and evaluated on various real ECG signals. Simulation results show that the method can contribute to and enhance the clinical ECG beat segmentation performance.

Recommendations for the standardization and interpretation of the electrocardiogram: part I: the electrocardiogram and its technology a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society endorsed by the International Society for Computerized Electrocardiology

This statement examines the relation of the resting ECG to its technology. Its purpose is to foster understanding of how the modern ECG is derived and displayed and to establish standards that will improve the accuracy and usefulness of the ECG in practice. Derivation of representative waveforms and measurements based on global intervals are described. Special emphasis is placed on digital signal acquisition and computer-based signal processing, which provide automated measurements that lead to computer-generated diagnostic statements. Lead placement, recording methods, and waveform presentation are reviewed. Throughout the statement, recommendations for ECG standards are placed in context of the clinical implications of evolving ECG technology.

Recommendations for the Standardization and Interpretation of the Electrocardiogram

This statement examines the relation of the resting ECG to its technology. Its purpose is to foster understanding of how the modern ECG is derived and displayed and to establish standards that will improve the accuracy and usefulness of the ECG in practice. Derivation of representative waveforms and measurements based on global intervals are described. Special emphasis is placed on digital signal acquisition and computer-based signal processing, which provide automated measurements that lead to computer-generated diagnostic statements. Lead placement, recording methods, and waveform presentation are reviewed. Throughout the statement, recommendations for ECG standards are placed in context of the clinical implications of evolving ECG technology.

Recommendations for the standardization and interpretation of the electrocardiogram. Part I: The electrocardiogram and its technology. A scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society

This statement examines the relation of the resting ECG to its technology. Its purpose is to foster understanding of how the modern ECG is derived and displayed and to establish standards that will improve the accuracy and usefulness of the ECG in practice. Derivation of representative waveforms and measurements based on global intervals are described. Special emphasis is placed on digital signal acquisition and computer-based signal processing, which provide automated measurements that lead to computer-generated diagnostic statements. Lead placement, recording methods, and waveform presentation are reviewed. Throughout the statement, recommendations for ECG standards are placed in context of the clinical implications of evolving ECG technology.

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 patient's 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.

Intelligent classification of electrocardiogram (ECG) signal using extended Kalman Filter (EKF) based neuro fuzzy system

This study presents the development of a hybrid system consisting of an ensemble of Extended Kalman Filter (EKF) based Multi Layer Perceptron Network (MLPN) and a one-pass learning Fuzzy Inference System using Look-up Table Scheme for the recognition of electrocardiogram (ECG) signals. This system can distinguish various types of abnormal ECG signals such as Ventricular Premature Cycle (VPC), T wave inversion (TINV), ST segment depression (STDP), and Supraventricular Tachycardia (SVT) from normal sinus rhythm (NSR) ECG signal.

Diagnostic performance of a computer-based ECG rhythm algorithm

We examined the accuracy of computer-based rhythm interpretation from one electrocardiograph manufacturer (GE Healthcare Technologies MUSE software 005C) in 4297 consecutive recordings in a university hospital setting. Overreading was performed by either of 2 experienced cardiologists, and all disagreements with the initial computer rhythm statement were reviewed by the second cardiologist to achieve physician consensus used as the "gold standard" for rhythm diagnosis. Overall, 13.2% (565/4297) of computer-based rhythm statements required revision, but excluding tracings with pacemakers, the revision rate was 7.8% (307/3954), including 3.8% involving the primary rhythm diagnosis and 3.9% involving definition of ectopic complexes. The false-negative rate for sinus rhythm was only 1.3%, but a computer diagnosis of sinus rhythm was incorrect in 9.9% of other rhythms. The false-negative rate for atrial fibrillation was 9.2%, whereas a computer diagnosis of atrial fibrillation was incorrect in 1.1% of other rhythms, including sinus. Computer diagnosis of paced rhythms remains problematic, and physician overreading to correct computer-based electrocardiogram rhythm diagnoses remains mandatory.

Multi-component based cross correlation beat detection in electrocardiogram analysis

Background

The first stage in computerised processing of the electrocardiogram is beat detection. This involves identifying all cardiac cycles and locating the position of the beginning and end of each of the identifiable waveform components. The accuracy at which beat detection is performed has significant impact on the overall classification performance, hence efforts are still being made to improve this process.

Methods

A new beat detection approach is proposed based on the fundamentals of cross correlation and compared with two benchmarking approaches of non-syntactic and cross correlation beat detection. The new approach can be considered to be a multi-component based variant of traditional cross correlation where each of the individual inter-wave components are sought in isolation as opposed to being sought in one complete process. Each of three techniques were compared based on their performance in detecting the P wave, QRS complex and T wave in addition to onset and offset markers for 3000 cardiac cycles.

Results

Results indicated that the approach of multi-component based cross correlation exceeded the performance of the two benchmarking techniques by firstly correctly detecting more cardiac cycles and secondly provided the most accurate marker insertion in 7 out of the 8 categories tested.

Conclusion

The main benefit of the multi-component based cross correlation algorithm is seen to be firstly its ability to successfully detect cardiac cycles and secondly the accurate insertion of the beat markers based on pre-defined values as opposed to performing individual gradient searches for wave onsets and offsets following fiducial point location.

Prediction models in the design of neural network based ECG classifiers: a neural network and genetic programming approach

BACKGROUND

Classification of the electrocardiogram using Neural Networks has become a widely used method in recent years. The efficiency of these classifiers depends upon a number of factors including network training. Unfortunately, there is a shortage of evidence available to enable specific design choices to be made and as a consequence, many designs are made on the basis of trial and error. In this study we develop prediction models to indicate the point at which training should stop for Neural Network based Electrocardiogram classifiers in order to ensure maximum generalisation.

METHODS

Two prediction models have been presented; one based on Neural Networks and the other on Genetic Programming. The inputs to the models were 5 variable training parameters and the output indicated the point at which training should stop. Training and testing of the models was based on the results from 44 previously developed bi-group Neural Network classifiers, discriminating between Anterior Myocardial Infarction and normal patients.

RESULTS

Our results show that both approaches provide close fits to the training data; p = 0.627 and p = 0.304 for the Neural Network and Genetic Programming methods respectively. For unseen data, the Neural Network exhibited no significant differences between actual and predicted outputs (p = 0.306) while the Genetic Programming method showed a marginally significant difference (p = 0.047).

CONCLUSIONS

The approaches provide reverse engineering solutions to the development of Neural Network based Electrocardiogram classifiers. That is given the network design and architecture, an indication can be given as to when training should stop to obtain maximum network generalisation.

An intelligent framework for the classification of the 12-lead ECG

An intelligent framework has been proposed to classify an unknown 12-Lead electrocardiogram into one of a possible number of mutually exclusive and combined diagnostic classes. The framework segregates the classification problem into a number of bi-dimensional classification problems, requiring individual bi-group classifiers for each individual diagnostic class. The bi-group classifiers were generated employing Neural Networks (NN), combined with a combination framework containing an Evidential Reasoning framework to accommodate for any conflicting situations between the bi-group classifiers. A number of different feature selection techniques were investigated with the aim of generating the most appropriate input vector for the bi-group classifiers. It was found that by reducing the original input feature vector, the generalisation ability of the classifiers, when exposed to unseen data, was enhanced and subsequently this reduced the computational requirements of the network itself. The entire framework was compared with a conventional approach to NN classification and a rule based classification approach. The framework attained a significantly higher level of classification in comparison with the other methods; 80.0% compared with 66.7% for the rule based technique and 68.00% for the conventional neural approach.

New trends in computer ECG analysis

Electrocardiographic (ECG) processing systems are operational in hospitals, outpatient clinics, primary care, and occupational medicine, and are used for population screening and epidemiologic studies. It appears that computer ECG analysis has been accepted, in spite of not yet performing quite as well as expert readers. The question is whether computerized ECG classification can be further improved. Possible new directions for research are: using information from all available beats, combining knowledge contained in different programs, incorporating knowledge gained in body surface mapping and modeling using information from non-ECG data, and collecting large ECG databases for the assessment of ECG programs. This article reviews these developments.

[Categorization of clinical findings; reduction of data without loss of information]

Depending on the individual skill of doctors the results of clinical investigations and laboratory findings are weighted differently according to their reliability today. Dealing with medical data the statistical way they have to be handled differently as well depending on the degree of reproducability and thus reliability. The problem of safety and quality of data in medicine is known to every experienced doctor as long as he himself "processes" them, nevertheless data tend to be treated uncritically when "automatically" processed by a computer. A way out of this pitfall is given by standardization of data using check-lists without transfer to any kind of coding-system or thesauri because none of those systems exists today that is capable of regaining the input-informations as they were from the codes.