Issue 2 (188), article 5


Kibern. vyčisl. teh., 2017, Issue 2 (188), pp.

Rudenko А.V.1, Professor, Corresponding member NAS of Ukraine,
First deputy of director
Nastenko I.А.1,2, Doctor (in Biology), PhD (in Technics),
Head of the Department of Information technologies and mathematical modeling
of physiological processes, Head of the Department of Biomedical Cybernetics
Zhurba O.А.1, Cardiovascular surgeon
Nosovets О.K.2, (in Technics),
Senior lecturer of the Department of Biomedical Cybernetics
Shardukova Y.V.1, Researcher at the Department of Information technology
and mathematical modeling of physiological processes
Lasoryshinets V.V.1, Professor, (in Medicine), Director
1 National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute», 37, Pobedi st., Kyiv, 03056, Ukraine
2 Government Facility “M.M. Amosov National Institute of Cardiovascular Surgery of National Academy of Medical Sciences of Ukraine”, 6, Amosov st., Kyiv, 03110, Ukraine


Introduction. The planned beating heart coronary aortic bypass grafting operations (BH CABG) prepares with and without parallel perfusion circulatory support. In second case the necessity of emergent use of circulatory support can appear. In these situations, the frequency of postoperative complications in circulatory system increases.

The decision about the planned use of circulatory support makes with analysis of big number of clinical data. This causes necessity to create the computer decision support systems to minimize the risk of emergent use of parallel perfusion.

The purpose of the article is to analyse statistically the risk factors for BH CABG operations on a working heart with the aim to minimize the risk of circulatory support emergent use.

Clinical material. 972 patients which undergone the BH CABG without circulatory support, 178 patients with planned use of circulatory support and 90 patients with emergent use of circulatory support. The 67 clinical parameters with package IBM SPSS Statistics 21.0 were analyzed.

Methods. The algorithm of binary logistic regression (BLR) for decision support systems development were used.

Results and discussion. The association between clinical values in groups without circulatory support, their planned and emergent use as well as their odds ratios and confidence intervals were analyzed. Then BLR algorithm to build the models for estimation of probability of planned and emergent use of circulatory support was used. The strategies of compulsory and stepwise inclusion of parameters were applied. The sensitivity, specificity and accuracy of the models obtained for learning and examination samples. The best models were chosen were calculated.

Conclusions. The created predictive models have a high sensitivity, specificity and accuracy, and can reduce the influence of subjective factors on medical decisions making regarding the use of the artificial circulatory support during off-pump coronary artery bypass surgery. Analysis of the variables included in the model, can contribute to a better understanding of the structure of existing pathogenic factors. The additional estimation the risk of cardiopulmonary bypass emergent use can reduce the likelihood of such situations occurrence.

Keywords: the beating heart coronary aortic bypass grafting, circulatory support with cardiopulmonary bypass, predicting algorithms.

Download full text (ru)!


  1. Mykheev A.A., Klyuzhev V.M., Karpun N.A. Surgery on coronary arteries on a working heart without artificial circulation in IHD patients. M.: Medicine, 2001. 43 р. (in Russian).
  2. Allen B. S., Rosenkranz E.R., Buckberg G.D. Studies of controlled reperfusion after ischemia. VII. High oxygen requirements of dyskinetic cardiac muscle. Journal of Thoracic and Cardiovascular Surgery. 1986. №92. P. 543–552.
  3. Mo A., Lin H., Wen Z.Efficacy and safety of on-pump beating heart surgery. Ann Thorac Surg. 2008. № 86. P. 1914–1918.
  4. Puskas J. Presidential Address, 2009: ISMICS Means Innovation. Innovations: Technology & Techniques in Cardiothoracic & Vascular Surgery. 2009. № 4. P. 240–247.
  5. Shabalkyn B.V., Zhbanov Y.V. Minimally invasive myocardial revascularization or aortocoronary bypass without artificial circulation? Bulletin of the Center Bakulev RAMS. V All-Russian Congress of Cardiovascular Surgeons. Novosibirsk, 1999. 152 p. (in Russian).
  6. Beauford R.B., Goldstein D.J., Sardari F.F. Multivessel off-pump revascularization in octogenarians: early and midterm outcomes. Ann. Thorac. Surg. 2003. Vol. 76.
    P. 12–17.
  7. Stamou S., Bail A., Boyce S.Coronary revascularization of the circumflex. Ann. Thorac. Surg. 2000. Vol. 70. P. 1371–1377.
  8. Witten Ian H., Frank Eibe, Hall Mark A. Data Mining: Practical Machine Learning Tools and Techniques. [3rd Ed.]. Morgan Kaufmann, 2011. P. 664.
  9. McHugh M. L. The odds ratio: calculation, usage, and interpretation. Biochemia Medica. 2009. №19 (2). P. 120–126.
  10. Sperandei S. Understanding logistic regression analysis. Biochemia Medica. 2014. 24(1). P. 12–18.

Recieved 03.04.2017

Issue 182, article 8


Kibern. vyčisl. teh., 2015, Issue 182, pp.

Nastenko I.А., Boyko A.L., Nosovets О.K., Teplyakov K.I., Pavlov V.А.

National Technical University of Ukraine “Kiev Polytechnical Institute” (Kiev)


Introduction. Requirements for modeling algorithms and their implementations varies depending upon the desired properties of the models, which has to be received in restrictions on the available computational resources. Examples of desired properties — accuracy, efficiency ratings, the lowest sensitivity to a change in the data of the model error, variance estimation of parameters, p values etc. Depending on the specific use of models, those or other criteria are taken as a basis for designing specific algorithm simulation. However, choice of the solution of resulting model is usually left to the user. This article considers the possibility of stepwise regression algorithm’s automatic optimization of parameters that is based on principles of self-organization on an example of the synthesis of the logistic model.
The purpose of this article is the improvment the quality of logistic regression classification models due to automatic optimization multivariate binary logistic regression algorithm parameters.
Results. The essence of the modification of stepwise logistic regression standard algorithm: defines penter , pleave grid for each combination of the thresholds calculates stepwise logistic algorithm and the corresponding value of the external criteria. Proposed external criteria reflects the classification accuracy on the training and test datasets, on the one hand, and the requirement to balance the quality of recognition in each class on the other. The stated procedure is repeated for the next value of the grid parameters of the algorithm. Final evaluation of the model is given in the exam sample data. For logistic model calculation and quality’s comparison of classification between standard logistic regression (glm function in R software) and proposed version of modified stepwise algorithm were taken data obtained in the laboratory of functional diagnostics at Department of Physical Education NTUU “KPI”. The purpose of the example is to get a classifying function, of group of subjects with certain states of the cardiovascular system from the rest of the test sample. Standard algorithm demonstrated on examination sample classification quality — 81%, the area under the ROC — curve — 0.8685. Graphs of sensitivity and specificity, and ROC curve for modified algorithm showed the results: quality of the classification algorithm — 90.5 %, area under the ROC — curve — 0.9717.
Conclusions. Article proposes stepwise logistic regression based on the principles of self-organization synthesis algorithm. In order to optimize the parameters of the algorithm proposed by external criterion, which reflects the classification accuracy on the training and test samples and requirement to balance the quality of recognition in each class the effect was received. For the aboved example the classification of functional states of the cardiovascular system in comparison of the standard stepwise algorithm with the proposed algorithm has shown classification quality improvement on 10 % on examination sample.
Keywords: logistic regression, stepwise regression, self-organization’s principles.

Download full text (ru)!


  1. Strighov V., Krimova E., Selection methods of regression models — Moscow: CC RAS — 2010. — 45 p. (in Russian).
  2. Ivakhnenko A., Stepashko V. Noisestability modelling — Kiev: «Nauk.dumka». — 1985, — 216 p. (in Russian).
  3. Ivakhnenko A. Muller J. Self-organization of predictive models — Kiev: Technic. — 1984, — 223 p. (in Russian).
  4. Akaike H.A new look at the statistical model identification // IEEE Transactions on Automatic Control — 1974. — Vol. 19. — P.716–723.
  5. Schwarz E. Estimating the dimension of a model // Annals of Statistics — 1978. — Vol. 6. — № 2. — P. 461–464.
  6. Mallows C.L. Some Comments on CP//Technometrics — 1973. — Vol. 15. — № 4. — P. 661–675.
  7. Efroymson M.A. Multiple regression analysis // Mathematical Methods for Digital Computers — 1960.
  8. Green P.G. Iteratively Reweighted Least Squares for Maximum Likelihood Estimation, and some Robust and Resistant Alternatives (with discussions) // Journal of the Royal Statistical Society, Series — 1984. — B 46. — P. 149–192.

Received 15.06.2015