Low-Power ECG-Based Processor for Predicting Ventricular Arrhythmia

Abstract

This paper presents the design of a fully integrated electrocardiogram (ECG) signal processor (ESP) for the prediction of ventricular arrhythmia using a unique set of ECG features and a naive Bayes classifier. Real-time and adaptive techniques for the detection and the delineation of the P-QRS-T waves were investigated to extract the fiducial points. Those techniques are robust to any variations in the ECG signal with high sensitivity and precision. Two databases of the heart signal recordings from the MIT PhysioNet and the American Heart Association were used as a validation set to evaluate the performance of the processor. Based on application-specified integrated circuit (ASIC) simulation results, the overall classification accuracy was found to be 86% on the out-of-sample validation data with 3-s window size. The architecture of the proposed ESP was implemented using 65-nm CMOS process. It occupied 0.112-mm 2 area and consumed 2.78-µW power at an operating frequency of 10 kHz and from an operating voltage of 1 V. It is worth mentioning that the proposed ESP is the first ASIC implementation of an ECG-based processor that is used for the prediction of ventricular arrhythmia up to 3 h before the onset.

EPOWT: A denoising technique of the electrocardiography signal transmission via 5G wireless communications

“…Long haul ECG observing is the standard paradigm for finding the ventricular arrhythmia. The ECG signals quality variations are identified by acquiring and investigating the 12‐lead ECGs . The dynamic electrocardiogram (ECG) checking framework is an efficient means to avert heart illnesses .…”

“…The ECG signals quality variations are identified by acquiring and investigating the 12-lead ECGs. 11 The dynamic electrocardiogram (ECG) checking framework is an efficient means to avert heart illnesses. 12 It can catch the coincidental arrhythmias and unexpected cardiovascular diseases by tracking the heart's actions in the ECG for a long period.…”

A Modular Low-Complexity ECG Delineation Algorithm for Real-Time Embedded Systems

“…The work we present in this paper goes one step further, proposing a similar structure as the algorithm for heartbeat classification presented in [22], where a simple and energy efficient classification algorithm is running all the time, to identify which parts of an ECG are critical, and activate, only in those cases, detailed (and more computationally intensive) diagnosis algorithms; and as in [23] where filters and thresholds are used in the detection of the ECG fiducial points for predicting ventricular arrhythmias in their real-time hardware implementation. Therefore, this paper proposes a new delineation algorithm that is not only less computationally complex and more energy efficient than state-of-the-art techniques, but also much more flexible and modular, being able to always achieve an optimal trade-off between energy consumption and delineation accuracy, depending on the available energy budget and the required performance, to carry out a precise arrhythmia detection.…”

A granular resampling method based energy-efficient architecture for heartbeat classification in ECG

“…However, it is challenging to establish a robust model for correct diagnosis, as external noise and between-class imbalance have influence on the classification performance [2]. Besides, designs with low-power consumption based on the robust model are essential for many ECG classification systems [3,4].…”

“…To solve the problems aforementioned, there are several kinds of methods: obtaining low-noise signals with a specific analog frontend and extracting a unique set of ECG features to reduce effects of the noise and imbalance, using an easyimplementation classifier to satisfy low-power demands, such as naive bayes, maximum likelihood classification, linear support vector machine (SVM), and so on [3,5,6]. However, most methods in the literature are put forward to establish a robust model or obtain an energy-efficient implementation of the model.…”