Advanced methods of heart rate signals processing and their usefulness in diagnosis support II. Univariate statistical techniques

• Autorzy: Moczko J. A.
• Języki publikacji: EN

Abstrakty

EN

A tentative cardiological database was established using virtual instrumentation described in the first part of presented paper. Some additional not heart rate variability parameters were added. Three selected univariate statistical techniques were used for illustration diagnosis support techniques in discrimination between healthy and coronary heart disease people. Comparison of nonparametric Mann-Whitney test, receiver operating characteristic ROC analysis and univariate logistic regression results was performed. In all used methods long term heart rate variability indices were most useful in prediction of patient's status. The correctness of classification was between 55 to 79 percent with ROC technique and 68 to 78 percent with logistic regression. However high number of false negative FN cases excludes univariate techniques as reliable screening test.

• Wydawca: Institute of Bioorganic Chemistry Scientific Publishers OWN, Polish Academy of Sciences
• Czasopismo: Computational Methods in Science and Technology
• Rocznik: 2004
• Tom: Vol. 10, nr 1
• Strony: 73--82
• Opis fizyczny: Bibliogr. 5 poz., rys.

Twórcy

autor

Moczko J. A.

• Chair and Department of Computer Science and Statistics University of Medical Sciences in Poznań Dąbrowskiego 79, 60-529 Poznań, Poland,

Bibliografia

• [1] J. Moczko, Advanced methods of heart rate signals processing and their usefulness in diagnosis support I. Mathematical heart rate descriptors and virtual instrumentation, Comp. Meth. in Sci. and Tech., 8(2), 65-76, (2002).
• [2] M. Hollander, D. A. Wofe, Nonparametric Statistical Methods. John Wiley & Sons, Inc. (1973).
• [3] S. W. Smith, Digital Signal Processing. A practical guide for engineers and scientists. Newnes-Elsevier Science (2003).
• [4] Y. Lu and J.-Q. Fang, Advanced Medical Statistics, World Scientific (2003)
• [5] D. W. Hosmer and S. Lemeshow, Applied Logistic Regression, John Wiley & Sons, Inc. (1989)