TY - JOUR
T1 - Multicategory classification of body surface potential maps
AU - Reich, Yehuda
AU - Thomas, Cecil W.
AU - Pao, Yoh Han
AU - Liebman, Jerome
AU - Rudy, Yoram
N1 - Funding Information:
Manuscript received May 23, 1988; revised January 30. 1989. This work was supported in part by National Institutes of Health Grants HL17931 and HL33343. Y. Reich is with Rafael, the Armament Development Authority, Haifa, Israel 3 102 I. C. W. Thomas and Y. Rudy are with the Department of Biomedical Engineering, Case Western Reserve University, Cleveland. OH 44 106. Y.-H. Pao is with the Department of Electrical Engineering and Applied Physics, Case Western Reserve University, Cleveland, OH 44106. J. Liebman is with the Department of Pediatrics, Rainbow Babies and Children Hospital, Cleveland, OH 44106. IEEE Log Number 9037724.
PY - 1990/10
Y1 - 1990/10
N2 - A statistical classification method is suggested for body surface potential maps (BSPM). The initial data reduction utilizes the Fourier expansion and time integration, resulting in physiological-oriented features. Based on Fischer's criterion, optimal discriminant vectors are used to map the features to an optimal subdomain. Experimental criteria determine the dimensionality of the subdomain and the number of features to be mapped into it. Classification is performed in two steps. In the first, a k-nearest neighbor (k-NN) rule is used for every two-category problem, the results of which are fed into a voting rule for final classification. The method is tested with 123 patients divided into four categories: normal (NR), ischemia (IS), myocardial infarction (MI), and left bundle branch block (LB) patients. The success is between 88% (for IS) and 100% (for LB) for QRS segment integration. Departure maps were used to explain the misclassified patterns.
AB - A statistical classification method is suggested for body surface potential maps (BSPM). The initial data reduction utilizes the Fourier expansion and time integration, resulting in physiological-oriented features. Based on Fischer's criterion, optimal discriminant vectors are used to map the features to an optimal subdomain. Experimental criteria determine the dimensionality of the subdomain and the number of features to be mapped into it. Classification is performed in two steps. In the first, a k-nearest neighbor (k-NN) rule is used for every two-category problem, the results of which are fed into a voting rule for final classification. The method is tested with 123 patients divided into four categories: normal (NR), ischemia (IS), myocardial infarction (MI), and left bundle branch block (LB) patients. The success is between 88% (for IS) and 100% (for LB) for QRS segment integration. Departure maps were used to explain the misclassified patterns.
UR - https://www.scopus.com/pages/publications/0025500072
U2 - 10.1109/10.102807
DO - 10.1109/10.102807
M3 - Article
C2 - 2249867
AN - SCOPUS:0025500072
SN - 0018-9294
VL - 37
SP - 945
EP - 955
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 10
ER -