An on-line ischemia monitoring algorithm for mobile devices

Abstract

The early diagnosis of ischemic events may prevent irreversible damage to the heart muscle. Mobile IntroductionMyocardial ischemia is one of the diseases with highest incidence rate in the industrialised countries. Physiologically, is identified by an insufficient oxygenated blood supply compared to current myocardial demand. This event is reflected in a ECG signal as anomalous variations during the ventricular re-polarization. Although the ECG signal analysis is not the most accurate method that exists to detect the ischemic events, it is without question, the least invasive and costly one, and still maintain a high sensitivity level in the detection.Moreover, prolonged, severe or repeated ischemic episodes can lead to irreversible damages to the cardiac tissue. Therefore it comes up the importance of the early detection of such kind of episodes.The latest technological advances in the communication and mobile devices have led to significant progresses of the mobile computing area and give the possibility of new any time and anywhere telemonitoring solution. The combination of real time ischemia detection methods with mobile computing techniques may give the solution to the early detection of ischemic events through innovative telemonitoring systems.The aim of this paper is to present the structure and the validation results of a detection algorithm of transient ischemic events based on ECG signal analysis. The algorithm can be embedded in a mobile such as a PDA and can be executed in real time. Those requirements involve some rules that we had in mind during the development of the algorithm: 1. to be simple enough and with a low computation cost to fulfill the time restrictions of a real time execution in a device with limited computation capabilities and memory capacity (PDA); 2. to generate a minimal number of false alarms 3. to be highly sensitive to ischemic episodes and above all to the most dangerous ones. We start this paper by mentioning some related work, followed by a description of the transient ischemia detection algorithm. We finish presenting the performances of the algorithm and conclusions. Related work and materialsThe ischemic transient events are associated with variations (elevations or depressions) of the ST segment in the ECG signal. Nevertheless, similar variations may be also produced by diurnal changes, postural changes, changes in ventricular conduction which make difficult the distinction between ischemic and non-ischemic events. There are several distinct algorithms that address the automatically ischemic detection in the ECG signals applying different methods that consider time domain analysis, KL transform, neural network or fuzzy logic. Nevertheless only a few of them deal explicitly with non-ischemic events such as axis shift events (an interesting reference of the existing ischemia algorithms can be found in [1]). Moreover the majority of the existing algorithms are difficult to be adjusted for real time execution and up to our knowledge, only a few algorithms specia...

Using DecisionTrees for Real-Time Ischemia Detection

“…The use of the decision trees techniques rediscovered some of the rejection rules proposed in the previous paper [1], other ones reappeared more refined, new ones have been discovered and the new rejection module proved to be more accurate.…”

“…The detection algorithm is based on a previous own algorithm for real-time transient ST-segment episodes detection that was developed and validated over the freely available part of the LTST database [1]. In this work we improve this algorithm and incorporate to it a more sophisticated rejection module using techniques based on decision trees.…”

Real-time detection of transient cardiac ischemic episodes from ECG signals

“…Nevertheless, repetitive patterns suitable for real-time discrimination between ischemic and non-ischemic episodes have been noticed in Dranca et al (2005) and confirmed in Dranca et al (2006) by decision tree methods.…”

Validation of the detection of ischemia using 12 lead smartphone based electrocardiography - a non-randomized, single blinded, cross-sectional, multicenter study

“…[10][11][12][13][14][15] A new device, the Spandan portable ECG device 12L is a portable ECG designed for quick access of 12 Lead ECG at homes and clinics has become available in the diagnostics market.…”