Abstract
Electrocardiographic (ECG) signals that monitor heart activity can help
identifying disease-related anomalies. Reliable automatic anomaly
detection has been shown to be useful in supporting physicians in
reading ECG signals. Decision support systems may be useful in such
cases but their reliability can be guaranteed.Â
Autoencoders (AEs) have been extensively used to analyse signals in many
fields. Convolutional Autoencoders (CAE) are a particular class of AE
showing optimal performances in detecting signal anomalies. Thus, CAEs
can be used to support and automatise the task of anomaly detection. We
design and use a CAE-based system to detect anomalies in ECG signals to
support cardiologists in identifying anomalies related to possible
diseases. Our tool outperforms other state-of-the-art ECG anomaly
detection approaches tested on a real dataset. In the task of anomaly
detection, our CAE obtains a ROC AUC of 97.82% with a simulated test
set and a ROC AUC of 99.75% using on a real test set. The tool and the
source code are available at
https://github.com/UgoLomoio/EG_DSS_CAE.