The Feasibility of Predicting Impending Malignant Ventricular Arrhythmias on the basis of Signal Complexity of Heartbeat Intervals
Malignant ventricular arrhythmias (MAs), such as ventricular tachycardia (VT) that presages cardiac arrest, present the highest hurdle for the healthcare community to overcome. Given that MAs occur unpredictably and lead to emergencies, convenient tracking devices, e.g. photoplethysmogram (PPG), that could predict MAs would be irreplaceably valuable. Since the use of heartbeat intervals (HbI) to predict the occurrence of arrhythmias is becoming more feasible, a further attempt to establish a new convenient approach for predicting impending MAs with HbI is worth trying. Assuming that intrinsic characteristics of MAs (VT and ventricular ﬁbrillation: VF) can be revealed by a suitable approach on the basis of signal complexity, we propose an approach that ﬁrst expresses the physiological status of the heart by HbI; then delineates the patterns of HbI by a new complexity metric (reﬁned composite multi-scale entropy: RCMsEn); and ﬁnally trains a nonlinear machine learning model (random forest: RF) to learn the speciﬁc patterns of MAs so as to differentiate them from the normal sinus heart rhythm (N) and other prevalent arrhythmias (atrial ﬁbrillation: AF, and premature ventricular contraction: V). For calculating entropy values and predicting MAs as early as possible (which is the aim of this study), two speciﬁcations are of interest: the minimal length of HbI needed to delineate the MAs patterns sufﬁciently (len min ), and the maximum time length at which our model can predict impending MAs (time max ). We compared the RF models with support vector machine (SVM) models based on linear and Gaussian kernels. Results show that the RF model performs the best, reaching a 99.24% recall and a 99.87% precision for a HbI of 500 heartbeats (the len min ) 374 seconds (the time max ) preceding the occurrence of MAs. The HbI samples in this study were extracted from an electrocardiograph (ECG). However, given the subtle difference (0.1 ms typically) between the R-R interval of ECG and the P-P interval of PPG, this approach could be extended to HbI acquired by the PPG sensor and thus should be of substantial theoretical and practical signiﬁcance in cardiac arrest prevention.
- Downloaded 304 times
- Download rankings, all-time:
- Site-wide: 119,857
- In bioinformatics: 9,771
- Year to date:
- Site-wide: 124,503
- Since beginning of last month:
- Site-wide: 131,143
Downloads over time
Distribution of downloads per paper, site-wide
- 27 Nov 2020: The website and API now include results pulled from medRxiv as well as bioRxiv.
- 18 Dec 2019: We're pleased to announce PanLingua, a new tool that enables you to search for machine-translated bioRxiv preprints using more than 100 different languages.
- 21 May 2019: PLOS Biology has published a community page about Rxivist.org and its design.
- 10 May 2019: The paper analyzing the Rxivist dataset has been published at eLife.
- 1 Mar 2019: We now have summary statistics about bioRxiv downloads and submissions.
- 8 Feb 2019: Data from Altmetric is now available on the Rxivist details page for every preprint. Look for the "donut" under the download metrics.
- 30 Jan 2019: preLights has featured the Rxivist preprint and written about our findings.
- 22 Jan 2019: Nature just published an article about Rxivist and our data.
- 13 Jan 2019: The Rxivist preprint is live!