An Automated System for On-line Monitoring and Detection of ST Changes in ECG Signal

In this paper, we present n new automated system for on-line monitoring and detection of ST changes in one channel electrocardiograms (ECG). This system consists of a preprocessing step for QRS detection, baseline wandering removal, and noise suppression. In the next step, the system uses a normal beat template as reference and a set of rules defined by cardiologists for detecting ischemic beats based on ST slope/deviation measurements. In the third step, the system uses a window classification for detecting sequences of ischemic beats. In the final step ischemic episodes in ECG signal are detected by merging sequences which are close together. Our system is advantageous with respect to similar algorithms; because it uses a template for rejecting abnormal ECG waveforms and accurate measurement of ST deviations. We have also modified some rules used by previous similar works in order to correspond better to the criteria used by cardiac specialists. A graphical user interface has been also developed for real time monitoring of the ST amplitude/slope along with the ECG signal. The performance of the system was evaluated using a subset of ESC ST-T database including 48 records. This evaluation demonstrated high sensitivity (94.5%) and good positive predictivity (85.03%) of our system.

[1]  R G Mark,et al.  Detection of transient ST segment episodes during ambulatory ECG monitoring. , 1998, Computers and biomedical research, an international journal.

[2]  I.K. Duskalov,et al.  Developments in ECG acquisition, preprocessing, parameter measurement, and recording , 1998, IEEE Engineering in Medicine and Biology Magazine.

[3]  S. Barro,et al.  A proposal for the fuzzy evaluation of ischaemic episodes , 1995, Computers in Cardiology 1995.

[4]  Dimitrios I. Fotiadis,et al.  An ischemia detection method based on artificial neural networks , 2002, Artif. Intell. Medicine.

[5]  A. Taddei,et al.  A system for the detection of ischemic episodes in ambulatory ECG , 1995, Computers in Cardiology 1995.

[6]  Dimitrios I Fotiadis,et al.  Use of a novel rule-based expert system in the detection of changes in the ST segment and the T wave in long duration ECGs. , 2002, Journal of electrocardiology.

[7]  Fabio Badilini,et al.  Cubic Spline Baseline Estimation In Ambulatory ECg Recordings For The Measurement Of ST Segment Displacements , 1991, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991.

[8]  Xiaoyan Li,et al.  ST-T complex automatic analysis of the electrocardiogram signals based on wavelet transform , 2003, 2003 IEEE 29th Annual Proceedings of Bioengineering Conference.

[9]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[10]  José García,et al.  Automatic detection of ST-T complex changes on the ECG using filtered RMS difference series: application to ambulatory ischemia monitoring , 2000, IEEE Transactions on Biomedical Engineering.

[11]  C. Pappas,et al.  An adaptive backpropagation neural network for real-time ischemia episodes detection: development and performance analysis using the European ST-T database , 1998, IEEE Transactions on Biomedical Engineering.

[12]  Michael G. Strintzis,et al.  ECG analysis using nonlinear PCA neural networks for ischemia detection , 1998, IEEE Trans. Signal Process..

[13]  Daniel Mason,et al.  Principles of Clinical Electrocardiography , 1965 .

[14]  C. Papaloukas,et al.  A knowledge-based technique for automated detection of ischaemic episodes in long duration electrocardiograms , 2006, Medical and Biological Engineering and Computing.

[15]  C. Marchesi,et al.  Computer system for analysis of ST segment changes on 24 hour Holter monitor tapes: comparison with other available systems. , 1984, Journal of the American College of Cardiology.