Based on mobile communication networks, the remote ECG monitoring system can provides special cardiac care for the patients at home or in community and a high quality system need provide disease warning, emergency treatment and doctors’ order according to diagnosis for the ambulatory ECG signal. Against the risk and random of cardiac disease, we need the remote ECG system have three characters: 1) The system must detect the abnormal ECG signal in high accuracy 2) The system must diagnose the cardiac disease in real time. 3) The system must be ubiquitous which provide patients with assistance anywhere and at any time. According to these requirements, we develop a novel remote ECG real time monitoring system. The users carry a PDA which just do simple computing and transmit the ECG data t...[ Read more ]

Based on mobile communication networks, the remote ECG monitoring system can provides special cardiac care for the patients at home or in community and a high quality system need provide disease warning, emergency treatment and doctors’ order according to diagnosis for the ambulatory ECG signal. Against the risk and random of cardiac disease, we need the remote ECG system have three characters: 1) The system must detect the abnormal ECG signal in high accuracy 2) The system must diagnose the cardiac disease in real time. 3) The system must be ubiquitous which provide patients with assistance anywhere and at any time. According to these requirements, we develop a novel remote ECG real time monitoring system. The users carry a PDA which just do simple computing and transmit the ECG data to the remote computer center by GPRS and finish the complex computing in it. The main questions answered in this paper are which algorithm has an excellent performance in the system and if the classifier has a good accuracy and if they can do it in real time. In order to answer these questions, in this paper we show the steps that we have followed to build the algorithm that classifies beats and rhythms, and the obtained results which test the accuracy in detection of arrthymia and myocardial ischemia on MIT-BIH arrhythmia database and MIT-BIH long term database. And result show low accuracy in detection of myocardial ischemia, because of wrong prediction in J point position. And we first apply the random forest to forecast the position of J point with the accuracy of 96.6873 %.