SOLUTIONS SYNTHESIS METHOD TO THE CONDITION PREDICTION PROBLEM OF PATIENTS IN THE MEDICAL MONITORING SYSTEMS

Вероника Александровна Горячая, Михаил Леонидович Угрюмов, Олег Александрович Гайденко, Нина Станиславовна Бакуменко, Ирина Алексеевна Трофимова

Abstract


This article proposes a mathematical model and computational method for solutions synthesis to the condition prediction problem of patients in medical monitoring systems. Research describes construction method of diagnostic models for quality criteria assessment of a bio-medical system (BMS) elements condition using monitoring data. Authors show an informativeness (significance) estimation method of the systems diagnosing models variables, obtained based on artificial neural networks (ANN) theory. The article describes a forecasting method of multidimensional time series obtained based on the condition variables monitoring data of the dynamic systems. Authors present a method for solving the condition classification problem of the complex systems elements. The developed method for solutions synthesis to the prediction problem is implemented in the computer decision support system (CDSS) for diagnosing patients in medical monitoring systems. Application examples of the described method for solutions synthesis to the condition prediction problem of patients in medical institutions are presented.

The paper propose following developed innovations:

a)   Mathematical method for solutions synthesis to the condition prediction problem of patients based on trend-analysis concept. Unlike existing, this method takes into account the high dimensionality of the states space and informativeness changes of monitored variables, which depend on the patients’ condition.

b)   Method of informativeness (significance) variables estimation. It takes into account the measurement accuracy of the state variables and the presence of pair correlation between them, that allows to use this method for the analysis of the completeness of the models.

c)   Statistical method of the patients’ condition classification. It contains orthogonalization procedure and the dimension reduction procedure of the condition variables factor space. In contrast to the existing it uses as a closeness measure precedents in the principal components space and the ability to determine the disease stage, which is not recognized by modern bio-markers (for example, hormone-refractory state);

The classification problem of the patients condition was solved for the diagnosing result verification. The results of solving the classification problem of patients condition based on the monitoring data are obtained for the selected type of disease. It was found that with the using developed method and its implementation in CDSS the itself- recognizing probability of the class exceeds 75%.


Keywords


decision support software system; medical monitoring system; computational methods

References


Mirgorod, V. F., Gvozdeva, I. M. Optymal'naya approksymatsyya trendovoy komponenty vremennoho ryada [Optimal approximation of the time series trend component]. Elektrotekhnichni ta komp"yuterni systemy – Electrical engineering and computer systems, 2011, no. 04/80, pp. 121-125.

Mirgorod, V. F.,Ranchenko G. S., Kravchenko V. M. Prymenenye dyahnostycheskykh modeley I metodov trendovoho analyza dlya otsenky tekhnycheskoho sos-toyanyya hazoturbynnykh dvyhateley [Application of diagnostic models and methods of trend analysis for assessing the technical state of gas turbine engines]. Avyatsyonno-kosmycheskaya tekhnyka y tekhnolohyya – Aviation and space technology and technology, 2008, no. 9/56, pp. 192-197.

Mirgorod, V. F.,Sergeev, A. Yu., Obodovsky A. S., Mogilyanets, Т. М. Dyahnostycheskye modely i metody trendovoho analyza otsenky tekhnycheskoho sostoyanyya hazoturbynnykh dvyhateley v sostave sylo-vykh ustanovok [Diagnostic models and methods of trend analysis of technical condition assessment of gas turbine engines in power plants]. Vijskova akademiya – Military Academy. Zbirnik naukovyh prat., 2014, no. 1 (1), pp. 99-108.

Boyko, I. I., Stakhovsky, E. A. Matematycheskaya obrabotka dannykh medytsynskykh yssledovanyy [Mathematical processing of medical research data]. Kiev, Publishing house "Veta-Press", 2008. 232 p.

Cambell, Michael J., Machin, D. Medical Statistics. A Commonsense approach. Second Edition. NY, John Willey& Sons Publ., 1993. 189 p.

Simon, Haykin. Neyronnыe sety: polnyykurs [Neural networks: a complete course], second edition: Trans. from English. Moscow publishin ghouse “Williams”, 2006. 1104 p.

Loboda, I., Yepifanov, S. On the selection of an opti-mal pattern recognition technique for a gas turbine diagnosis. SME Turbo Expo 2013: Turbine Technical Conference and Exposition (GT2013). San Antonio, Texas (USA), 2013. 11 p. (GT2013-95198).

Wang, L., Li, Y. G., Ghafir, Abdul M. F. Rough Set Diagnostic Frameworks for Gas Turbine Fault Classification. SME Turbo Expo 2013: Turbine Technical Conference and Exposition (GT2013). San Antonio, Texas (USA),2013. 10 p. (GT2013-94430).

Loboda, I. Gas Turbine Fault Classification Using Probability Density Estimation. ASME Turbo Expo 2014: Turbine Technical Conference and Exposition (GT2014). Düsseldorf (Germany), 2014. 10 p. (GT2014-27265).

Adams, Mac G. K., Hester, P. T. Accounting for Errors when using Systems Approaches. Procedia Computer Science, 2013, vol. 20, pp. 318-324.

Marascuilo, L. A., Levin, J. R. Appropriate Post Hoc Comparisons for Interaction and Nested Hypotheses in Analysis of Variance Designs: The Elimination of Type IV Errors. American Educational Research Journal, 1970, vol. 7, no. 3, pp. 397-421.

Antonyan, I. M., Goriacha, V. A., Zelensky, A. I., Ugryumova, E. M. Usovershenstvovanniy metod y ynformatsyonnaya tekhnolohyya reshenyya zadachy klassyfykatsyy sostoyanyya elementov slozhnykh system [An improved method and information technology for solving the classification problem of the elements condition of complex systems]. Journal of Kharkov National University – Visnyk Kharkivs'koho natsional'noho universytetu, Collected Works. Series: «Mathematical modeling. Information Technology. Automated control systems», 2013, Issue 22 (№1063), pp. 5-16.

Strelets, V. E., Tronchuk, A. A., Ugryumova, E. M. etc. Systemnoe sovershenstvovanye elementov slozhnykh tekhnycheskykh system na osnove kontseptsyy ob-ratnykh zadach: monohrafyya [Systemic improving the elements of complex technical systems based on the concept of inverse problems: monograph]. Kharkov, Nat. Aerospace Univ. named after N.E. Zhukovsky «Kharkiv. aviation. Inst», 2013. 148 p. – ISBN 978-966-662-312-9.

Starenkyi, V., Goryachaya, V., Sokolov, O., Ugryumova, E. Diagnostic model and information technology of classification states in the differential diagnosis nsclc (nonsmall cell lung cancer) patients with differ-ent methods of radiotherapy and chemotherapy. Journal of Health Sciences, Radom University in Radom (Poland), 2013, no. 3 (8), pp. 7-26.

Zagoruiko N. G. Prykladnye metody analyza dannykh y znanyy [Applied methods of data analysis and knowledge]. Novosibirsk, Sobolev Institute of Mathematics, 1999. 270 p.

Antonyan, I. M., Goriacha, V. A., Zelensky, A. I., Ugryumova, E. M. Metod otsenyvanyya ynformatyv-nosty peremennykh neyrosetevykh modeley system y protsessov pry neopredelennosty dannykh [A method of the variables informativeness estimation of the neural network models of systems and processes under data uncertainty], Journal of Kharkiv National University – Visnyk Kharkivs'koho natsional'noho universytetu, Collected Works. Series: «Mathematical modeling. Information Technology. Automated control systems», 2015, №1156, Issue 26, pp. 5-16.

Rumshinsky L.Z. Matematycheskaya obrabotka rezul'tatov eksperymenta [The mathematical processing of the experimental results]. Home edition of Physical and mathematical literature, Moskow, «Science» Publ., 1971. 192 p.

Antonyan, I. M., Goriacha, V. A., Zelensky, A. I., Ugryumova, E. M. Kratkosrochnoe prognozirovanie mnogomernyh vremennyh rjadov s ispol'zovaniem robastnyh nejrosetevyh modelej [Short-term forecasting of multidimensional time series using robust neural network models], Journal of Kharkiv National University – Visnyk Kharkivs'koho natsional'noho universytetu, Collected Works. Series: «Mathematical modeling. Information Technology. Automated control systems», 2015, Issue 28, pp. 5-17.

Goryacha, V. O., Ugryumov, M. L., Cherny`sh, S. V., Ugryumova, E. M. Komp'yuterna programa “Komp'juternaja interaktivnaja sistema podderzhki prinjatija reshenij pri prognozirovanii sostojanija slozhnyh dinamicheskih sistem “RMICP” v uslovijah neopredelennosti vhodnyh dannyh” [Computer program "Computer interactive decision support support system for condition prediction of complex dynamic systems "RMICP" in uncertainty of input data"], svidocztvo pro reyestraciyu avtors`kogo prava na tvir - certificate of registration of copyright to a work, № 62180 (Ukrayina). Data reyestraciyi 20.10.2015.


Refbacks

  • There are currently no refbacks.