Electrocardiography is a commonly applied method of measuring the electrical activity of the heart. The standard 12-lead electrocardiogram (ECG) provides sufficient information to allow various heart conditions to be diagnosed. Despite its relative ease of use, the standard ECG procedure could benefit from a reduction of leads which may allow for continuous monitoring, for example via a wearable device. In this study, we first investigated the use of variational autoencoders (VAEs) to assess what the most representative leads of the standard 12-lead system are. As the VAE learns to compress the ECG data, it focuses on the parts of the input that is important for the reconstruction. This information is then used to assess which leads are the most useful for a reconstruction task in general. Precordial leads V 2 , V 3 and V 4 are shown to contain the most information in the 12-lead ECG data. We then investigated the use of a convolutional neural network (CNN) architecture capable of learning patient-specific models to accurately impute 11 missing ECG signals from a single available lead. Our design is unconventional in that it keeps a twodimensional structure throughout the fully connected layers. We show that this design outperforms the traditional one-dimensional structure and that these architectures can be affected by the presence of symptoms in recorded heart signals.
Body surface potential mapping (BSPM) provides high spatial resolution recordings of the electric potential of the heart on the body surface. BSPM can involve up to 200 electrodes, in contrast to standard 12-lead ECG. The costs and complexity of a BSPM procedure are a limiting factor to its use in clinical practice. Both can be reduced by using fewer electrodes and reconstructing signals from the missing electrodes with an artificial neural network. The minimal configuration consists of the electrodes that are most relevant for reliable reconstruction. We propose an architecture for a variational autoencoder, trained on BSPM procedures from the Nijmegen dataset: EDGAR [1], to reconstruct a full 65-lead system from a reduced number of input electrodes. Further, we determine the effect of an increased numbers of missing electrodes on the corresponding reconstruction error, and show that it is possible to achieve a good 65-lead reconstruction from as few as 12 electrodes. We consider the implication of our research in the scope of current BSPM practice, as well as the limitations of using neural networks for this task.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.