xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features
Authors:
Open Access
- 7 June 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-14
Abstract
Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( $$n = 9854$$ ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( $$+24\%$$ compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.
Keywords
All Related Versions
Funding Information
- European Union's Horizon 2020 research and innovation programme (101017424)
- Technische Universität Dresden
This publication has 58 references indexed in Scilit:
- Automatic screening method for atrial fibrillation based on lossy compression of the electrocardiogram signalPhysiological Measurement, 2020
- PTB-XL, a large publicly available electrocardiography datasetScientific Data, 2020
- A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patientsScientific Data, 2020
- Accurate detection of atrial fibrillation from 12-lead ECG using deep neural networkComputers in Biology and Medicine, 2020
- Early differentiation of long-standing persistent atrial fibrillation using the characteristics of fibrillatory waves in surface ECG multi-leadsScientific Reports, 2019
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machineComputers in Biology and Medicine, 2015
- Worldwide Epidemiology of Atrial FibrillationCirculation, 2014
- How can we best detect atrial fibrillation?Journal of the Royal College of Physicians of Edinburgh, 2012
- Clinical value of fibrillatory wave amplitude on surface ECG in patients with persistent atrial fibrillationJournal of Interventional Cardiac Electrophysiology, 2009