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.
We present the first systematic evidence for the origins and breakdown
of 1/f scaling in human heart rate. We confirm a previously posed conjecture that 1/f scaling in heart rate is caused by the intricate balance between antagonistic activity of sympathetic (SNS) and parasympathetic (PNS) nervous systems. We demonstrate that modifying the relative importance of either of the two branches leads to a substantial decrease of 1/f scaling. In particular, the relative PNS suppression both by congestive heart failure (CHF) and by the parasympathetic blocker atropine results in a substantial increase in the Hurst exponent H and a shift of the multifractal spectrum f(α) from 1/f towards random walk scaling 1/f2. Surprisingly, we observe a similar breakdown in the case of relative and neurogenic SNS suppression by primary autonomic failure (PAF). Further, we observe an intriguing interaction between multifractality of heart rate and absolute variability. While it is generally believed that lower absolute variability results in monofractal behaviour, as has been demonstrated both for CHF and the parasympathetic blockade, in PAF
patients we observe conservation of multifractal properties at
substantially reduced absolute variability to levels closer to
CHF. This novel and intriguing result leads us to the conjecture that
the multifractality of the heart rate can be traced back to the
intrinsic dynamics of the parasympathetic nervous system.
Using the method of local Continuous Detrended Fluctuation Analysis CDFA) we analyze the correlations of ventricular interbeat intervals of patients with Atrial Fibrillation (AF). CDFA yields a local Hoelder exponent h for a neighborhood around each point in the time series by determining the scaling of fluctuations with window size after detrending. We compare the histograms of Hoelder exponents for original data with those of randomly shuffled data and find some correlations not only in long-range windows but also at short time scales where interbeat intervals during AF have been believed to be random in nature. Furthermore, we find unique temporal correlation structures to occur only in the heart rate of patients who were in the survivor group when a follow up was conducted at least one year after data acquisition. We conclude that ventricular interbeat intervals during AF contain richer information than previously considered and the study of the local correlations may be useful in predicting mortality of the patients.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.