Real-time algorithm for a mobile cardiac monitoring system to detect life-threatening arrhythmias

Abstract

This paper presents a real-time algorithm for a mobile cardiac monitoring system to detect life-threatening arrhythmias. This detection algorithm focuses on two lifethreatening arrhythmias ventricular tachycardia and fibrillation (VT/VF), which are detected through the application of pre-detection processing and main detection processing. In pre-detection processing, applies a statistical method to detect VT/VF. In contrast, a neural fuzzy network is applied to detect VT/VF in main detection processing. The neural fuzzy network's input features are obtained by wavelet transform and several effective extraction methods. This realtime detection algorithm outperform Amann's algorithm, with 92% accuracy and 93% sensitivity. It has been implemented as a cardiac monitoring system in a mobile phone. This system meets heart patient's requirements of early detection and outof-hospital rehabilitation.

Factor Analysis for the Performance Impacts of Real-Time Ventricular Fibrillation Detection on Microcontroller

“…Previous research on VF detection primarily has focused on two main topics: 1) developing and evaluating the relative performance of detection algorithms [2-19], and 2) developing handheld devices for real-time monitoring [20][21][22][23]. Most previous performance studies have been conducted offline using prefiltered data sets, fixed threshold values, and a single time-window size (often 8 s); recently machine/deep learning-based methods have been proposed [10][11][12][13][14][15][16][17][18][19].…”

“…INTRODUCTIONAccording to the World Health Organization (WHO), cardiovascular diseases (CVDs) are the number one cause of death worldwide [1], and among CVDs, Ventricular Fibrillation (VF) is one of the most critical life-threatening cardiac arrhythmia diseases. Once a patient has suffered a VF attack, accurate detection and quick first aid are essential for improving the chance of survival.Previous research on VF detection primarily has focused on two main topics: 1) developing and evaluating the relative performance of detection algorithms [2-19], and 2) developing handheld devices for real-time monitoring [20][21][22][23]. Most previous performance studies have been conducted offline using prefiltered data sets, fixed threshold values, and a single time-window size (often 8 s); recently machine/deep learning-based methods have been proposed [10][11][12][13][14][15][16][17][18][19].…”

Efficient and robust ventricular tachycardia and fibrillation detection method for wearable cardiac health monitoring devices

“…A wavelet based method is presented to discriminate the ventricular arrhythmias using the number of islands, average time-width features extracted from the scalogram and LDA classifier [6]. A life threatening arrhythmia detection algorithm using the 14 features extracted from the detail coefficients at levels of 3 and 4 of the Haar transform [7]. The optimal features were selected using NADM based on the neural fuzzy network.…”