Automatic classification of heartbeats using ECG morphology and heartbeat interval features

By Philip de Chazal, Maria O'Dwyer, Richard B. Reilly. IEEE Transactions on Biomedical Engineering, 2004

1,664 citations recorded by the source corpus.

A method for the automatic processing of the electrocardiogram (ECG) for the classification of heartbeats is presented. The method allocates manually detected heartbeats to one of the five beat classes recommended by ANSI/AAMI EC57:1998 standard, i.e., normal beat, ventricular ectopic beat (VEB), supraventricular ectopic beat (SVEB), fusion of a normal and a VEB, or unknown beat type. Data was obtained from the 44 nonpacemaker recordings of the MIT-BIH arrhythmia database. The data was split into two datasets with each dataset containing approximately 50 000 beats from 22 recordings. The first dataset was used to select a classifier configuration from candidate configurations. Twelve configurations processing feature sets derived from two ECG leads were compared. Feature sets were based on ECG morphology, heartbeat intervals, and RR-intervals. All configurations adopted a statistical classifier model utilizing supervised learning. The second dataset was used to provide an independent performance assessment of the selected configuration. This assessment resulted in a sensitivity of 75.9%, a positive predictivity of 38.5%, and a false positive rate of 4.7% for the SVEB class. For the VEB class, the sensitivity was 77.7%, the positive predictivity was 81.9%, and the false positive rate was 1.2%. These results are an improvement on previously reported results for automated heartbeat classification systems.

Subfields: Cardiology and Cardiovascular Medicine, Cognitive Neuroscience, Pulmonary and Respiratory Medicine

View Paper: https://www.semanticscholar.org/paper/587fa3976583a4721742a241bdaaf5429e81967f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Cognitive Neuroscience

In Pulmonary and Respiratory Medicine

Citations in the corpus

Optimization of ECG Classification by Means of Feature Selection (2011, methodology): “Applied to the MITDB, this standard leaves 44 records which should be divided using an interpatient division scheme such as the one proposed in [5] if a realistic estimation of the real-world performance is desired.”
Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks (2016, methodology): “With the limited training data as proposed in [10] and [14]–[17], we shall demonstrate that simple CNNs will suffice to achieve a superior classification performance rather than the complex ones that are commonly used for deep learning tasks.”
Classification of Electrocardiogram Signals With Support Vector Machines and Particle Swarm Optimization (2008, methodology): “In [5], different classification systems based on linear discriminant classifiers are explored, together with different morphological and timing features obtained from single and multiple ECG leads.”
Heartbeat Classification Using Morphological and Dynamic Features of ECG Signals (2012, methodology): “As discussed in Section II-B, the same database division is adopted as in the literature [8], [15], [17], i.”
Kernel Methods and Machine Learning (2014, methodology): “Morphology features For arrhythmia detection, waveform morphology features are considered to be most generic and effective for classification of all kinds of abnormal heart beats [46].”
A Generic and Robust System for Automated Patient-Specific Classification of ECG Signals (2009, methodology): “temporal features related to interbeat time interval to improve accuracy and robustness of classification, as suggested by the results of previous studies [15].”
Block-Based Neural Networks for Personalized ECG Signal Classification (2007, methodology): “In agreement with the AAMI-recommended practice, paced beats are not included in the classification experiments in this paper as well as in the previous works [5], [12] chosen for comparison.”
Heartbeat classification using disease-specific feature selection (2014, methodology): “It was reported that this approach outperformed those achieved by pure inter-patient classifiers [6].”
A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features (2006, methodology): “Features include ECG morphology [8], [9], [13], [14], heartbeat interval features [8], [9], [11], [13], [14], frequency based features [7], higher order cumulant features [10], Karhunen-Loeve expansion of ECG morphology [11], and hermite polynomials [12].”
LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices (2018, methodology): “Many previous ECG classification algorithms are mainly focused on signal processing techniques including extraction of morphological features [7], frequency domain analysis [8], Hermite function decomposition [9], wavelet transform [10], [11], support vector machines [12] and hidden Markov models [1”