Automatic Atrial Arrhythmia Detection Based on RR Interval Analysis in Conscious Rats

A CNN Model for Cardiac Arrhythmias Classification Based on Individual ECG Signals

PURPOSE

Wearable devices in the scenario of connected home healthcare integrated with artificial intelligence have been an effective alternative to the conventional medical devices. Despite various benefits of wearable electrocardiogram (ECG) device, several deficiencies remain unsolved such as noise problem caused by user mobility. Therefore, an insensitive and robust classification model for cardiac arrhythmias detection system needs to be devised.

METHODS

A one-dimensional seven-layer convolutional neural network (CNN) classification model with dedicated design of structure and parameters is developed to perform automatic feature extraction and classification based on large volume of original noisy signals. Record-based ten-fold cross validation scheme is devised for evaluation to ensure the independence of the training set and test set, and further improve the robustness of our method.

RESULTS

The model can effectively detect cardiac arrhythmias, and can reduce the computational workload to a certain extent. Our experimental results outperform most recent literature on the cardiac arrhythmias classification with diagnostic accuracy of 0.9874, sensitivity of 0.9811, and specificity of 0.9905 for original signals; diagnostic accuracy of 0.9876, sensitivity of 0.9813, and specificity of 0.9907 for de-noised signals, respectively.

CONCLUSION

The evaluation indicates that our proposed approach, which performs well on both original signals and de-noised signals, fits well with wearable ECG monitoring and applications.

Long-Term Effects of Ivabradine on Cardiac Vagal Parasympathetic Function in Normal Rats

Background: The complex interactions that exist between the pacemaker current, I _f, and the parasympathetic nervous system could significantly influence the course of patients undergoing chronic therapy with the I _f blocker ivabradine. We thus aimed to assess the effects of chronic ivabradine therapy on autonomic modulation and on the cardiovascular response to in situ and in vitro parasympathetic stimulation. The right atrial expression of HCN genes, encoding proteins for I _f, was also evaluated. Methods: Sympathetic and parasympathetic heart rate variability parameters and right atrial HCN(1-4) RNA levels were analyzed in 6 Control and 10 ivabradine-treated male Wistar rats (IVA; 3 weeks, 10 mg/kg/day). The heart rate (HR) and systolic blood pressure (SBP) responses to in situ electrical stimulation of the vagus nerve (2-20 Hz) were assessed in 6 additional Control and 10 IVA rats. The spontaneous sinus node discharge rate (SNDR) response to in vitro cholinergic receptors stimulation using carbamylcholine (10^-9-10^-6 mol/L) was also assessed in these later rats. Results: Ivabradine significantly increased vagal modulation and shifted the sympatho-vagal balance toward vagal dominance. In Control, in situ vagus nerve stimulation induced progressive decrease in both the SBP (p = 0.0001) and the HR (p< 0.0001). Meanwhile, in IVA, vagal stimulation had no effect on the HR (p = 0.16) and induced a significantly lower drop in SBP (p< 0.05). IVA also displayed a significantly lower SNDR drop in response to carbamylcholine (p< 0.01) and significantly higher right atrial HCN4 expression (p = 0.02). Conclusion: Chronic ivabradine administration enhanced vagal modulation in healthy rats. In addition, ivabradine reduced the HR response to direct muscarinic receptors stimulation, canceled the cardioinhibitory response and blunted the hemodynamic response to in situ vagal stimulation. These data bring new insights into the mechanisms of ivabradine-related atrial proarrhythmia and suggest that long-term I _f blockade may protect against excessive bradycardia induced by acute vagal activation.

Atrial fibrillation is associated with hypermethylation in human left atrium, and treatment with decitabine reduces atrial tachyarrhythmias in spontaneously hypertensive rats

Atrial fibrillation (AF) is the most common cardiac arrhythmia. As the molecular mechanisms underlying the pathology are largely unknown, this cardiac arrhythmia remains difficult to treat. To identify specific molecular actors involved in AF, we have performed a transcriptomic analysis on left atrium (LA) from patients with valvular heart disease with or without AF. We showed that 1627 genes had altered basal expression level in LA tissue of AF patients compared with the control group. The significantly enriched gene ontology biological process "anatomical structure morphogenesis" contained the highest number of genes in line with changes in structure that occur when the human heart remodels following AF development (ie, LA dilatation and interstitial fibrosis). We then focused the study on Pitx2 (paired-like homeodomain 2), being the most altered transcription factor in LA from AF patients and from which compelling evidence have indicated that its reduced expression can be considered as a marker for the disease. In addition, its expression was inversely correlated with LA size. We demonstrated that AF is associated with Pitx2 promoter hypermethylation both in humans and arrhythmic aging spontaneously hypertensive rats. Chronic administration of a DNA methylation inhibitor (ie, 5-Aza-2'-deoxycitidine) improved ECG arrhythmic profiles and superoxide dismutase activities and reduced fibrosis in the left ventricle of spontaneously hypertensive rats. Taken together, these data support the notion that AF is associated with epigenetic changes in LA and provide a proof-of-concept that hypomethylating agents have to be considered in the treatment of atrial arrhythmias.

Proposition of novel classification approach and features for improved real-time arrhythmia monitoring

Arrhythmia refers to a group of conditions in which the heartbeat is irregular, fast, or slow due to abnormal electrical activity in the heart. Some types of arrhythmia such as ventricular fibrillation may result in cardiac arrest or death. Thus, arrhythmia detection becomes an important issue, and various studies have been conducted. Additionally, an arrhythmia detection algorithm for portable devices such as mobile phones has recently been developed because of increasing interest in e-health care. This paper proposes a novel classification approach and features, which are validated for improved real-time arrhythmia monitoring. The classification approach that was employed for arrhythmia detection is based on the concept of ensemble learning and the Taguchi method and has the advantage of being accurate and computationally efficient. The electrocardiography (ECG) data for arrhythmia detection was obtained from the MIT-BIH Arrhythmia Database (n=48). A novel feature, namely the heart rate variability calculated from 5s segments of ECG, which was not considered previously, was used. The novel classification approach and feature demonstrated arrhythmia detection accuracy of 89.13%. When the same data was classified using the conventional support vector machine (SVM), the obtained accuracy was 91.69%, 88.14%, and 88.74% for Gaussian, linear, and polynomial kernels, respectively. In terms of computation time, the proposed classifier was 5821.7 times faster than conventional SVM. In conclusion, the proposed classifier and feature showed performance comparable to those of previous studies, while the computational complexity and update interval were highly reduced.

Assessment of cardiac autonomic tone in conscious rats

Cardiac autonomic tone can be assessed either by estimating separately vagal and sympathetic tones or by evaluating the net effect of their interaction, the so-called sympathovagal balance (SVB). To compare the most commonly used methods in rats, telemetric recordings of the electrocardiogram were performed in normotensive WKY rats, and in groups of spontaneously hypertensive (SHR) rats that were either untreated or chronically treated with the cholinesterase inhibitor, pyridostigmine, to enhance vagal tone. Cardiac autonomic blockers were administered alone and in combination, so that heart rate (HR) could be measured (1) under resting conditions, (2) with either autonomic branch blocked, and (3) with both branches blocked (which provided intrinsic HR, iHR). SVB was assessed as the ratio of resting HR to iHR. This calculation pointed to a sympathetic predominance in untreated SHRs and even more so in WKY rats, and to a marked vagal predominance in pyridostigmine-treated SHRs. By contrast, the ratio between low and high frequency components (LF/HF) of RR interval spectra did not significantly differ between the groups. Each autonomic tone was quantified as the HR change induced by its selective blocker or as the difference between iHR and HR after blockade of its counterpart. Both pharmacological methods indicated vagal enhancement in treated SHRs, but provided opposite results in terms of vagal vs. sympathetic predominance. These data seriously question the use of the LF/HF ratio as an index of SVB, and the possibility to reliably estimate vagal and sympathetic tones separately through current pharmacological approaches in conscious rats.