Issue 4 (206), article 4


Cybernetics and Computer Engineering, 2021, 4(206)

Researcher, Medical Information Systems Department
ORCID: 0000-0002-4407-5990, e-mail:

KOZAK L.M., DSc (Biology), Senior Researcher,
Leading Researcher, Medical Information Systems Department
ORCID: 0000-0002-7412-3041, e-mail:

KOVALENKO O.S., DSc (Medicine), Professor,
Head of Medical Information Systems Department
ORCID: 0000-0001-6635-0124, e-mail:

Junior Researcher, Medical Information Systems Department
ORCID: 0000-0003-1760-2801, e-mail:

International Research and Training Center for Information Technologies
and Systems of the National Academy of Sciences of Ukraine
and Ministry of Education and Science of Ukraine,
40, Acad. Glushkov av., Kyiv, 03187, Ukraine


Introduction. In the Big Data era, decision tree methods, machine learning, and neural networks, along with other Data Mining methods became an alternative to classical statistical methods as a more useful tool for analyzing large and inhomogeneous data. Neural Networks methods have emerged as a more accurate and effective technology in a wide range of medical problems such as diagnosis, prediction, treatment. 

The purpose of the paper is to identify the control parameters of the surgical intervention to optimize the EF ejection fraction after the surgery using a Data Mining method (neural network) models.

Results. The analysis of changes in hemodynamic parameters of children with severe heart defects due to surgery — implantation of conduit. Changes in these parameters after surgery were analyzed using analysis of variance for repeated measurements (RepANOVA). It was determined that after the surgery there was a significant, statistically significant decrease in 3 hemodynamic parameters (end diastolic index, aortic pressure gradient, and augmentation index). According to the cluster analysis, three groups of patients were identified, which were differed in all hemodynamic parameters and in the peculiarities of changes in the studied parameters after surgery. A model based on a neural network of the RBF type (with radial-based activation functions) was built using the Data Mining Automated Neural Networksmodule of the STATISTICA package. According to the developed models, the dependence of the emission fraction after the surgery on the control parameters — dopamine dose and conduit diameter was determined.

Conclusions. The use of predictive models of neural networks developed by the type of RBF network with radially symmetric functions in single-layer networks, allowed to analyze the effectiveness of surgical interventions in the case of congenital heart disease in infants and children. Taking into account the results of the developed predictive model of the dependence of the cardiac output fraction on the parameters of surgery (dose, conduit diameter) and factors such as age, weight, hemodynamic status, gives the surgeon essential information to achieve good results of a surgery.

Keywords: Data Mining classification models, predictive models, neural networks, surgical efficiency

Download full text!


1 Kalantari A. et all. Computational intelligence approaches for classification of medical data: State-of-the-art, future challenges and research directions. Neurocomputing. 2018, No 2(7), pp. 2-22.

2 Dietterich T. G. Ensemble Methods in Machine Learning. International Workshop on Multiple Classifier Systems, 2000, Springer, Berlin, Heidelberg. Vol 18576, pp. 1-15.

3 Acharya A., Hruschka E., Ghosh J., Acharyya S. C3E: A framework for combining ensembles of classifiers and clusterers. International Workshop on Multiple Classifier Systems. 2011, Vol. 6 (15), pp.269-278.

4 Rahman A., Verma B. Cluster-based ensemble of classifiers. Expert Systems. 2013, Vol. 30, No. 3, pp. 270-282.

5 Shouman M, Turner T, Stocker R. Integrating Clustering with Different Data Mining Techniques in the Diagnosis of Heart Disease. J. Comput. Sci. Eng. 2013, Vol. 20(1), pp. 1-10.

6 Abawajy JH, Kelarev AV, Chowdhury M Multistage approach for clustering and classification of ECG data. Computer methods and programs. 2013, 112(3), pp. 720-730.

7 Mohan S, Thirumalai C, Srivastava G Effective heart disease prediction using hybrid machine learning techniques. IEEE Access. 2019, 7, pp.81542-81554.

8 Dolce G, Quinteri M, Serra S, Lagani V, Pignolo L: Clinical signs and early prognosis in vegetative state: a decisional tree, data-minig study. Brain Inj. 2008, 22 (7-8), pp. 617-623.

9 Exarchos T.P, Tzallas AT, D Baga, et all Using partial decision trees to predict Parkinson’s symptoms: A new approach for diagnosis and therapy in patients suffering from Parkinson’s disease. Computers in biology and medicine. 2012, 42 (2), pp.195-204.

10 Takahashi O, Cook EF, Nakamura T, Saito J, Ikawa F, Fukui T: Risk stratification for in-hospital mortality in spontaneous intracerebral haemorrhage: a Classification and Regression Tree analysis. QJM, 2006, 99:743-50.

11 Gortzis LG, Sakellaropoulos F, Ilias I, Stamoulis K, Dimopoulou I: Predicting ICU survival: a meta-level approach. BMC Health Serv Res. 2008, 26:8-157.

12 Xie J., Su B., Li C.,. Lin K,. Li H, Hu Y., Kong G. A review of modeling methods for predicting in-hospital mortality of patients in intensive care unit. J Emerg Crit Care Med. 2017, 1(8) pp. 1-10.

13 Trujillano J., Badia M., Servia L. et al. Stratification of the severity of critically ill patients with classification trees. BMC Med Res Methodol. 2009, V. 9, no 83, pp. 1-80.

14 Romanyuk O.A., Kozak L.M., Kovalenko A.S., Kryvova O.A. Digital transformation in medicine: from formalized medical documents to information technologies of digital medicine. Cybernetics and Computer Engineering. 2018, no. 4(194), pp. 61-78.

15 Kryvova O.A., Kozak L.M. Information Technology for Classification of Donosological and Pathological States Using the Ensemble of Data Mining Methods. Cybernetics and Computer Engineering. 2021, no. 1(203), pp. 77-94.

16 Santos M., Portela F. and Vilas-Boas M. INTcare – Multi-agent Approach for Real-time Intelligent Decision Support in Intensive Medicine. In Proceedings of the 3rd International Conference on Agents and Artificial Intelligence (ICAART-2011), SciTePress 2011, pp. 364-369.

17 Kim S, Kim W, Park RW. A Comparison of intensive care unit mortality prediction models through the use of data mining Techniques. Healthc Inform Res. 2011; 17:232-243.

18 Amin M. Chiam Y., Varathan K. Identification of significant features and data mining techniques in predicting heart disease. Telematics and Informatics. 2019, 36, pp. 82-93.

19 Rubini L. J., Perumal E. Efficient classification of chronic kidney disease by using multi-kernel support vector machine and fruit fly optimization algorithm. International Journal of Imaging Systems and Technology. 2020, 30 (3), pp. 660-673.

20 Shillan D., Sterne J. A. C., Champneys, A. & Gibbison, G. Use of machine learning to analyze routinely collected intensive care unit data: a systematic review. Critical Care. 2019, 23 (1), pp. 284-295.

21 Kaieski N, da Costa CA, da Rosa Righi R, Lora PS. Application of artificial intelligence methods in vital signs analysis of hospitalized patients: A systematic literature review Applied Soft Computing, 2020, vol. 96, 106612.

22 da Silva D. B., Schmidt D., da Costa C. A., da Rosa Righi R. & Eskofier, B. DeepSigns: A predictive model based on Deep Learning for the early detection of patient health deterioration. Expert Systems with Applications. 2021, 165, 113905.

23 Kwon J.M., Lee Y., Lee Y., Lee S., Park J. An Algorithm Based on Deep Learning for Predicting In-Hospital Cardiac Arrest. J Am Heart Assoc. 2018, 7(13), e008678.

24 Papapetrou P., Kollios G., Sclaroff S., Gunopulos D. Mining frequent arrangements of temporal intervals. Knowledge and Information Systems. 2009, 21 (2), pp.133-171.

25 Moskovitch R., Choi H., Hripcsak G., Tatonetti N. Prognosis of clinical outcomes with temporal patterns and experiences with one class feature selection. EEE/ACM transactions on computational biology and bioinformatics. 2016, 14(3), pp. 555-563.

26 Choi E, Schuetz A, Stewart WF, Sun J. Using recurrent neural network models for early detection of heart failure onset. J Am Med Inform Assoc. 2017, 24, pp. 361-370.

27 Bizopoulos P., Koutsouris D. Deep learning in cardiology IEEE reviews in biomedical engineering. 2018, 12, 168-193.

28 SAS Data Mining URL: (Last accessed: 06.08.2021)

29 Data Mining: (Last accessed: 28.05.2021)

30 WEKA URL: (Last accessed: 06.08.2021)

31 RapidMiner URL: (Last accessed: 06.08.2021)

32 KNIME URL: (Last accessed: 06.08.2021)

33 Poucke S.V., Zhang Z., Schmitz M., Vukicevic M. Scalable Predictive Analysis in Critically Ill Patients Using a Visual iOpen Data Analysis Platform. PLoS one. 2016, V. 11(1), pp. 1-21.

34 Kong G., Lin K., Hu Y. Using machine learning methods to predict in-hospital mortality of sepsis patients. BMC medical informatics and decision making. 2020, V. 20 (1), pp. 1-10.

Received 01.09.2021