ECG waveform analysis by significant point extraction. I. Data reduction.

We present a new technique for automatic data reduction and pattern recognition of time-domain signals such as electrocardiogram (ECG) waveforms. Data reduction is important because only a few significant features of each heart beat are of interest in pattern analysis, while the patient data collection system acquires an enormous number of data samples. We present a significant point extraction algorithm, based on the analysis of curvature, that identifies data samples that represent clinically significant information in the ECG waveform. Data reduction rates of up to 1:10 are possible without significantly distorting the appearance of the waveform. This method is unique in that common procedures help in both data reduction as well as pattern recognition. Part II of this work deals specifically with pattern analysis of normal and abnormal heart beats.

[1]  N. Thakor.  From Holter Monitors to Automatic Defibrillators: Developments in Ambulatory Arrhythmia Monitoring , 1984, IEEE Transactions on Biomedical Engineering.

[2]  Willis J. Tompkins,et al.  A New Data-Reduction Algorithm for Real-Time ECG Analysis , 1982, IEEE Transactions on Biomedical Engineering.

[3]  J. R. Cox,et al.  Digital analysis of the electroencephalogram, the blood pressure wave, and the electrocardiogram , 1972 .

[4]  P. Sankar,et al.  A parallel procedure for the detection of dominant points on a digital curve , 1978 .

[5]  Larry S. Davis,et al.  Understanding Shape: Angles and Sides , 1977, IEEE Transactions on Computers.

[6]  W. J. Tompkins,et al.  Estimation of QRS Complex Power Spectra for Design of a QRS Filter , 1984, IEEE Transactions on Biomedical Engineering.

[7]  Azriel Rosenfeld,et al.  Angle Detection on Digital Curves , 1973, IEEE Transactions on Computers.

[8]  Ivaturi S. N. Murthy,et al.  Syntactic Approach to ECG Rhythm Analysis , 1980, IEEE Transactions on Biomedical Engineering.

[9]  Theodosios Pavlidis,et al.  Waveform Segmentation Through Functional Approximation , 1973, IEEE Transactions on Computers.

[10]  Larry S. Davis,et al.  A Corner-Finding Algorithm for Chain-Coded Curves , 1977, IEEE Transactions on Computers.

[11]  Ho Soo Lee.  Model-based pattern analysis of signals using frames , 1985 .

[12]  Kenneth P. Birman,et al.  Rule-Based Learning for More Accurate ECG Analysis , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Gene H. Hostetter,et al.  Scan-Along Polygonal Approximation for Data Compression of Electrocardiograms , 1983, IEEE Transactions on Biomedical Engineering.

[14]  Azriel Rosenfeld,et al.  An Improved Method of Angle Detection on Digital Curves , 1975, IEEE Transactions on Computers.

[15]  H S Lee,et al.  ECG waveform analysis by significant point extraction. II. Pattern matching. , 1987, Computers and biomedical research, an international journal.

[16]  M. L. Ahlstrom,et al.  Digital Filters for Real-Time ECG Signal Processing Using Microprocessors , 1985, IEEE Transactions on Biomedical Engineering.

[17]  Mueller Wc,et al.  Arrhythmia detection program for an ambulatory ECG monitor. , 1978 .

[18]  Nitish V. Thakor,et al.  SIGNIFICANT POINT EXTRACTION ALGORITHM FOR ECG DATA REDUCTION AND PATTERN RECOGNITION. , 1984 .

[19]  H A Fozzard,et al.  AZTEC, a preprocessing program for real-time ECG rhythm analysis. , 1968, IEEE transactions on bio-medical engineering.

[20]  John K. Tsotsos,et al.  CAA: A Knowledge Based System Using Causal Knowledge to Diagnose Cardiac Rhythm Disorders , 1983, IJCAI.