DOI: https://doi.org/10.31071/kit2015.12.14

Inventory reference

ISSN 1812-7231 Klin.inform.telemed. Volume 11, Issue 12, 2015, Pages 91–97

Author(s)

T. V. Kolesnik

Institution(s)

SE "Dnipropetrovsk medical academy of the Ministry of Healthcare of Ukraine"

Article title

Latest information technology operational analysis and modeling as a tool improve diagnosis of arterial hypertension chronobiological features

Abstract (resume)

Introduction. The diagnostic potential of ambulatory blood pressure monitoring (ABPM) can be expanded through the introduction of advanced information technologies aimed directly at the systematic processing of monitoring data using modern mathematical methods of investigation of dynamic systems and the identification of new, more informative indicators.

Objective: To evaluate the variability of blood pressure according to BPM with the dynamic properties of short-term fluctuations, and to determine the severity of the hypertension using the latest information technology.

Material and methods. A SMAD 321 patients with essential hypertension (EH) II stage of the definition of the classic indicators of circadian blood pressure profile. ABPM results processed by a specially created information technology, based on the sharing of polynomial splines, Markov processes, and artificial neural networks.

Results of the study. The suggested information technology allows by sharing polynomial splines, Markov processes, and artificial neural networks fundamentally new way to assess the variability in blood pressure because of its dynamic properties and to determine the severity of the GB. This technology evaluation of ABPM enables a whole new level to identify and analyze hidden patterns chronobiological features of AD, which significantly expands the diagnostic capabilities and allows you to select options as relatively favorable or extremely unfavorable course of the disease.

Keywords

hypertension, ambulatory blood pressure monitoring, blood pressure variability, Markov's processes, artificial neural network.

References

1. Baybuz O. G., Pristavka O. P. Splayni v nadiynosti [Splines in reliability]. D., Dniepropetrovsk Univ. Publ., 2003, 216 p. (In Ukr.).

2. Gnedenko B. V., Kovalenko I. N. Vvedenie v teoriyu massovogo obsluzhivaniya [Introduction to the theory of mass Service]. Moscow, Nauka Publ., 1987, 336 p. (in Russ.)

3. Kovalenko I. N. Raschet veroyatnostnyh harakteristik sistem [The calculation of probability characteristics of systems]. Kiev, Tehnika Publ., 1982. 96 p. (in Russ.)

4. Koks D., Lyuis P. Statistichesky analiz posledovatelnostey sobytiy [Statistical analysis of the events sequences]. Moscow, Mir Publ., 1969, 312 p. (in Russ.)

5. Osovskiy S. Neyronnye seti dlya obrabotki informatsii [Neural network for information processing]. Moscow, Finansy i statistika Publ., 2004, 344 p. (in Russ.)

6. Pristavka O. P., Hachapurizde T. M., Kolesnik T. V. Sposib otsinki variabelnosti arterialnogo tisku ta viznachennya tyazhkosti perebigu arterialnoyi gipertenziiyi [The method of assessment of blood pressure variability and determine the severity of arterial hypertension]. Patent for utility model UKR iss. 26761, Published 10.10.2007, Bulletin iss. 16. (In Ukr.).

7. Polyakov R. V., Starkov V. N., Tivonchuk V. I. Solution of Class actual problems of medical-biological and ecological modeling with methods of computational physics using spline functions. Vestnik novyih meditsinskih tehnologiy [Herald of new medical technologies], 1997, iss. 3. pp. 57–62. (in Russ.)

8. Polyakov R. V., Starkov V. N., Tivonchuk V. I. Solution of Class actual problems of medical-biological and ecological modeling with methods of computational physics using spline functions. Vestnik novyih meditsinskih tehnologiy [Herald of new medical technologies]. 1998, iss. 2, pp. 26–30. (in Russ.)

9. Polyakov R. V., Starkov V. N., Tivonchuk V. I Solution of Class actual problems of medical-biological and ecological modeling with methods of computational physics using spline functions. Vestnik novyih meditsinskih tehnologiy [Herald of new medical technologies], 1997, iss. 4, pp. 24–26. (in Russ.)

10. Pristavka A. F., Beloborodko O. I. [Approximation of continuous functions of intensity in the average]. "Aktualni problemy avtomatyzatsiyi ta informatsiynyh tehnolohiy" [Actual problems of automation and information technology]. DNU Publ., Dnipropetrovsk, vol. 4, 2001, pp. 77–86. (in Russ.)

11. Pristavka P. O. Polinomialni splayni pri obrobtsi danih [Polynomial splines in data processing]. Dnipropetrovsk, Dnipropetrovsk Univ. Publ., 2004, 236 p. (In Ukr.).

12. Unіfіkovaniy klіnіchniy protokol pervinnoї, ekstrenoї ta vtorinnoї (spetsіalіzovanoї) medichnoї dopomogi "arterіal'na gіpertenzіya" [Unified clinical protocols of primary, emergency and secondary (specialized) medical care "Hypertension"]. MOZ Ukraїni, Kiev, 2012, 107 p. (In Ukr.).

13. Duncan J. A., Scholey J. W., Miller J. A. Angiotensin II type 1 receptor gene polymorphisms in humans: physiology and pathophysiology of the genotypes. Curr. Opin. Nephrol. Hypertens. 2001, vol. 10, iss. 1, рр. 111–116.

14. Mancia G., Ferrari A., Gregorini L., Parati G., Pomidossi G. et al. Blood pressure and heart rate variabilities in normotensive and hypertensive human beings. Circulation Research, 1983, vol. 53, iss. 1, pp. 96–104.

Full-text version http://kit-journal.com.ua/en/viewer_en.html?doc/2015_12/16.pdf