Key result
A Convolutional Autoencoder-based system (AUTAN-ECG) achieved a ROC AUC of 99.75% on a real test set and 97.82% on a simulated test set for detecting anomalies in ECG signals.
Why the study?
Reliable automatic anomaly detection can support physicians in reading ECG signals, and convolutional autoencoders may automatise and support this task.
Does a Convolutional Autoencoder (CAE)-based system improve anomaly detection in ECG signals compared to other state-of-the-art approaches?
Does a Convolutional Autoencoder (CAE)-based system improve anomaly detection in ECG signals compared to other state-of-the-art approaches?
A novel Convolutional Autoencoder-based system demonstrates high accuracy in detecting anomalies in ECG signals, potentially supporting cardiologists in clinical practice.
CAE-based ECG anomaly detection may aid clinical decision support; leaves open prospective validation before routine use.
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. 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.
No takes yet. Share an insight, caveat, or question.
Lomoio et al. (2023) studied ECG anomalies. Convolutional Autoencoder (CAE) based system (AUTAN-ECG) vs. Other state-of-the-art ECG anomaly detection approaches was evaluated on Anomaly detection performance (ROC AUC). A Convolutional Autoencoder-based system (AUTAN-ECG) achieved a ROC AUC of 99.75% on a real test set and 97.82% on a simulated test set for detecting anomalies in ECG signals.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: