Key result
A Convolutional Neural Network using Lorenz plot imaging of ECG R-R intervals detected atrial fibrillation with 100% sensitivity and 100% specificity.
Why the study?
Detection of AF is critical due to the increased risk of serious brain infarction from cerebral embolism, prompting efforts to improve the reliability of AF detection during long-term heartbeat monitoring.
Does a Convolutional Neural Network using Lorenz plot imaging of ECG R-R intervals accurately detect atrial fibrillation in 24-h ambulatory ECGs?
Does a Convolutional Neural Network using Lorenz plot imaging of ECG R-R intervals accurately detect atrial fibrillation in 24-h ambulatory ECGs?
A deep learning algorithm using Lorenz plot imaging of R-R intervals can detect paroxysmal atrial fibrillation from 24-hour ambulatory ECGs with extremely high accuracy.
Answers are grounded in this paper and cite their sources.
Supports high-accuracy AF detection on ambulatory ECGs; extends CNN validation to Lorenz plot imaging in RCT settings.
Detection of atrial fibrillation (AF) is a critical issue of healthcare because it is an increased risk of serious brain infarction due to cerebral embolism despite that it is the commonest sustained arrhythmia. To improve the reliability of the detection of AF by the long-term monitoring of heartbeat signals, we developed machine-learning systems for detecting AF using the Allostatic State Mapping by Ambulatory ECG Repository (ALLSTAR) database of 24-h ambulatory electrocardiograms. Lorenz plot images were generated from consecutive segment of 600 R-R intervals and the pattern of image characteristic to AF was discriminated from those of non-AF segments, including sinus rhythm, frequent atrial ectopic beats, and atrial flutter. Lorenz plot images consisting of 10,035 known AF and 10,107 non-AF samples were provided to the machine learning algorithms of Convolutional Neural Network (CNN). The performance to detect AF was evaluated in the independent 50 samples of 24-h ECG including paroxysmal AF episodes. As the results, the CNN that detected Lorenz plot of AF with 100% sensitivity and 100% specificity was developed through the deep learning. The developed CNN system classified accurately all 24-h ECG data including paroxysmal AF episodes. Lorenz plot imaging of R-R interval dynamics is useful for effectively discriminating AF from non-AF by artificial intelligence.
No takes yet. Share an insight, caveat, or question.
Hayano et al. (2019) studied Atrial fibrillation (n=20,192). Convolutional Neural Network using Lorenz plot imaging vs. Non-AF segments was evaluated on Detection of atrial fibrillation. A Convolutional Neural Network using Lorenz plot imaging of ECG R-R intervals detected atrial fibrillation with 100% sensitivity and 100% specificity.
Synapse has enriched 10 related papers. Consider them for comparative context: