Issue 1 (211), article 6


Cybernetics and Computer Engineering, 2023, 1(211)

KOVALENKO O.S., DSc (Medicine), Professor,
Head of the Medical Information Systems Department ,

KOZAK L.M., DSc (Biology), Senior Researcher,
Leading Researcher of the Medical Information Systems Department ,

Researcher of the Medical Information Systems Department ,

BYCHKOV V.V., DSc (Medicine),
Senior Researcher of the Medical Information Systems Department ,

Junior Researcher of the Medical Information Systems Department ,

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 recent years, the scientific community, especially in the medical field, has been putting a lot of efforts and resources into the development of eHealth technologies and systems. Various methods of intellectual support, which are necessary to ensure high quality of medical care, have been developed. The study of the effectiveness of the application of various methods of diagnosis, treatment of patients and restoration of their health is one of the important components of the assessment of the quality of medical care.

The purpose of the paper is to analyze the results of providing medical care with the use of developed models based on Data Mining methods to identify factors that affect the results of treatment.

The results. A method of estimating the medical care results using Data Mining methods has been developed, the feature of which is the combination of filtering algorithms, clustering and classification methods. Models of the medical care result depending on significant factors were built. To test the developed method, a retrospective analysis was carried out using a database of hospital patients of various departments of clinical facilities. The distribution of treatment results evaluation (according to the standardized formulation) of cardiac and diabetic patients was obtained, and concomitant diseases and complications were analyzed. A model for determining the factors influencing the treatment outcome, based on the decision tree method (CART), has been developed. Analysis of the decision tree structure makes it possible to draw conclusions about the decision-making logic by a specific doctor. With the help of decision tree models, the relationship between complications, the main diagnosis and other factors, in particular, concomitant diagnoses, recurrence of hospitalization etc., was analyzed.

Conclusions. The combination of statistical methods and the developed method and models based on Data Mining (a decision tree calculated according to the CART algorithm and 10-fold cross-validation) for  analysis of medical hospital databases made it possible to identify the frequency characteristics of concomitant diseases and complications typical for cardiac and diabetic patients, and also allowed to determine the main factors that depend on the decision-making by doctors about the outcome of treatment.

Keywords: eHealth, Data Mining methods, CART algorithm, information technology, treatment outcomes

Download full text!


1. Rademakers J, Delnoij D, de Boer D. Structure, process or outcome: which contributes most to patients’ overall assessment of healthcare quality? BMJ Qual Saf. 2011 Apr;20(4):326-331. [doi: 10.1136/bmjqs.2010.042358].

2. Ossebaard HC, Van Gemert-Pijnen L. eHealth and quality in health care: implementation time. Int J Qual Health Care. 2016 Jun;28(3):415-419. [doi: 10.1093/intqhc/mzw032]

3. Tossaint-Schoenmakers R., Versluis A., Chavannes N., Talboom-Kamp E., Kasteleyn M. The Challenge of Integrating eHealth Into Health Care:Systematic Literature Review of the Donabedian Model of Structure, Process,and Outcome. J Med Internet Res. 2021;23(5):e27180 doi: 10.2196/27180

4. Triberti S., Savioni L., Sebri V., Pravettoni G. eHealth for improving quality of life in breast cancer patients: A systematic review. Cancer Treatment Reviews, 2019, Vol. 74, pp. 1-14.

5. Rybarczyk-Szwajkowska А., Marczak M. Quality assessment of health care services in patients and medical staff opinion. January 2011. URL: publication/273335138_Quality_assessment_of_health_care_services_in_patients_and_medical_staff_opinion

6. Legido-Quigley H., McKee M., Walshe K., Suñol R., Ellen Nolte E., Klazinga N. How can quality of health care be safeguarded across the European Union? BMJ. 2008 Apr 26; 336(7650): 920-923. doi: 10.1136/bmj.39538.584190.47

7. ASA physical status classification system. URL:

8. Owens W.D., Felts J.A., et al. A physical status classifications: A study of consistency of ratings. Anesthesiology. 1978, Vol. 49, pp. 239-243.

9. Melchenko M.G., Eliy L.B. Possibilities of assessing the patient’s condition. Child. surgery, 2007, no. 2(55), pp. 102-108 (in Ukrainian).

10. Havens J.M., Columbus A.B., Seshadri A.J., et al. Risk stratification tools in emergency general surgery. Trauma Surg. Acute Care Open. 2018, № 3, pp. 1-8.

11. Formalized assessment of the patient’s condition using scales for major internal diseases. Zaporizhzhia state medical university. 2015, 79 p. (in Ukrainian).

12. Rogach I.M., Slabky G.O., Kachala L.O. et al. Quality control of medical care at the level of a health care facilities. Guidelines. Uzhgorod: MES of Ukraine, 2014, 48 p. (in Ukrainian).

13. Royal College of Physicians. NEWS2 and deterioration in COVID-19. URL:

14. MediCalc. National Early Warning Score 2. URL: pwfhc210.htm

15. Frimpong J., Jackson B. et al. Health information technology capacity at federally qualified health centers: a mechanism for improving quality of care. BMC Health Services Research. 2013, № 1, pp. 13-35. URL: articles/10.1186/1472-6963-13-35

16. Kisekka V., Giboney J. S. The Effectiveness of Health Care Information Technologies: Evaluation of Trust, Security Beliefs, and Privacy as Determinants of Health Care Outcomes. J Med Internet Res. 2018, V.20, №4, pp. 1-11.

17. Kushniruk A., Hall S., Baylis T., Borycki E., Kannry J. Approaches to demonstrating the effectiveness and impact of usability testing of healthcare information technology. Studies in health technology and informatics. 2019, 257, pp. 244-249.

18. Minne L., Abu-Hanna A., de Jonge, E. Evaluation of SOFA-based models for predicting mortality in the ICU: A systematic review. Crit Care. 2008, 12, 161.

19. Last M., Tosas O., Cassarino T.G., et al. Evolving classification of intensive care patients from event data. Artif Intell Med. 2016; 69:22-32.

20. Houthooft R., Ruyssinck J., van der Herten J., et al. Predictive modelling of survival and length of stay in critically ill patients using sequential organ failure scores. Artif Intell Med. 2015;63:191-207.

Received 26.12.2022